Conference Programme

Asset management and reliability teams face increasing pressure to digitalise operations and harness Artificial Intelligence (AI) to enhance asset performance, decision-making, and organisational resilience. While AI adoption is often seen through the narrow lens of predictive maintenance, this approach limits the broader potential of AI to transform asset management processes. The challenge lies in identifying where and how to start digitalisation initiatives effectively while avoiding common technical and organisational pitfalls.

This session addresses these challenges by exploring the practical use of AI agents and autonomous mobile inspection robots beyond traditional applications. It provides insights into the fundamental components of AI agents and their development within asset management contexts. Crucially, the session highlights successful implementation strategies, with a focus on change management, adoption, and governance to ensure AI initiatives deliver tangible value rather than remaining buzzwords.

Presentation content

• Rationale for digitalisation and AI adoption in asset management
• Determining starting points for digitalisation and AI implementation
• Expanding beyond predictive maintenance: AI agents and inspection robots
• Fundamental building blocks of an AI agent with practical example
• Strategies for successful AI integration within organisations
• Common technical and organisational pitfalls and how to avoid them

Practical takeaways

Participants learn to assess where AI agents can create practical value in asset management and reliability workflows. They gain an understanding of the core components required to build AI agents through real-world examples. The session also equips practitioners with knowledge of typical challenges encountered during digital and AI implementations, including organisational change and technical barriers, helping them navigate and mitigate these risks for better adoption and sustained results.

Despite mature condition monitoring programs in European heavy industries, equipment-related downtime still accounts for 1% to 8% of planned production losses annually. This persists even where online measurement systems and skilled vibration analysts are in place, largely due to the limited capacity to process and interpret the large volumes of data produced. Traditional vibration monitoring methods, whether based on fixed or adaptive alarm thresholds, frequently generate a high rate of false positives, consuming expert time and hindering timely fault detection.

Rotomate's recent study involving about 100 condition monitoring professionals highlights that existing scalar threshold methods detect changes but do not explain their causes, requiring expert manual inspection of spectral data to confirm diagnoses. The session presents an alternative approach using an agentic AI system that mimics expert reasoning by autonomously analyzing vibration spectra, identifying fault-related frequencies, comparing across measurement points, and assessing findings in the context of historical baselines. This AI runs on existing sensor infrastructure and has been deployed with measurable reductions in non-actionable alarms, faster maintenance decisions, and detection of faults missed by human analysts.

Presentation content

• Findings from interviews with 100 condition monitoring professionals
• Limitations of scalar threshold vibration monitoring methods
• Manual spectral analysis as a bottleneck in fault diagnosis
• Agentic AI replicating expert reasoning in vibration analysis
• Comparison of AI results across measurement points and historical data
• Deployment outcomes: fewer false alarms and faster decisions
• Integrating AI analysis into existing monitoring workflows without new hardware

Practical takeaways

Participants learn why 70–90% of vibration alarms are false positives and the limitations of scalar threshold methods. They gain insight into how agentic AI autonomously replicates expert spectral diagnostic reasoning to provide explainable condition assessments. The session provides a practical framework for integrating AI-driven analysis into both online and route-based monitoring workflows without requiring additional sensors or hardware, enabling faster and more reliable fault detection within existing industrial setups.

In industrial maintenance and asset management, gathering condition data is a critical but often fragmented task. The challenge lies not only in collecting inspection data but also in transforming it into actionable intelligence that enhances reliability and informs maintenance decisions. This requires integrating diverse inspection inputs securely and efficiently within existing workflows.

Flir Assetlink offers a platform approach to aggregate inspection data, promoting better asset visibility and operational insight. By consolidating data from handheld devices, sensors, and inspections, organisations can improve condition monitoring and asset health assessments. This session explores how this approach supports maintenance and asset performance professionals in converting raw inspection inputs into a structured intelligence framework that underpins more effective reliability management.

Presentation content

• Integrating diverse inspection data sources securely
• Consolidating handheld device and inspection inputs
• Linking asset data to reliability and maintenance workflows
• Enhancing condition monitoring through data aggregation

Practical takeaways

Participants learn how to bridge the gap between routine inspection data collection and actionable asset intelligence. They gain insight into methods for securely integrating and consolidating condition data from multiple sources and understand how to align inspection data with maintenance and reliability processes. This approach facilitates improved asset health visibility and supports more informed decision-making in reliability management.

Many industrial asset management and maintenance systems rely on AI-driven decision-making to optimise operations. However, these AI models often operate on outdated, manually updated, or assumed asset location and status data, leading to costly errors in maintenance planning and resource allocation. Physical assets remain difficult to track continuously and accurately in complex industrial environments due to harsh conditions and fragmented infrastructure, creating a critical visibility gap between the real-world asset status and the AI’s digital representation.

Sensolus addresses this challenge by transforming simple, rugged passive trackers into active AI agents that provide continuous, structured, real-time physical intelligence. This approach bridges the critical gap between physical assets and AI systems without requiring infrastructure overhaul or compromising data quality. By feeding reliable ground truth data into maintenance platforms, digital twins, and AI co-pilots, it enables AI to deliver on its promise with actionable and accurate insights.

Presentation content

• Impact of stale asset data on AI decision accuracy
• Challenges of tracking physical assets in industrial settings
• Converting passive trackers into active AI agents
• Ensuring data quality without infrastructure overhaul
• Integrating physical intelligence with AI-driven systems

Practical takeaways

Participants learn why reliable, real-time physical asset data is essential for effective AI applications in asset management. They gain insight into how rugged passive tracking devices can be elevated to AI agents that reliably feed ground truth into AI systems. The session provides a practical framework for bridging real-world asset visibility with digital asset management, enhancing maintenance and resource planning accuracy without requiring complex infrastructure changes.

INOPSYS operates mobile and modular on-site water purification units for the chemical and pharmaceutical industries, often deployed at isolated customer sites without permanent personnel. Ensuring reliable remote monitoring and operational autonomy is crucial to maintain performance, control variable costs like energy and catalysts, and uphold service-level agreements. Early detection of operational anomalies, particularly fouling in heat exchangers, is essential to prevent unplanned maintenance and process disruptions.

To address this challenge, INOPSYS collaborated with Indao to develop an AI-driven intelligent monitoring solution. This system transforms industrial process data into actionable operational insights by integrating historical and real-time data for early anomaly detection. A secure, scalable end-to-end data pipeline was established using industrial connectivity and OPC UA protocols, supporting real-time dashboards and AI-based inference across a distributed fleet of mobile assets. The solution combines continuous condition monitoring, anomaly detection, and root-cause analysis to enhance maintenance decision-making and engineering improvements.

Presentation content

• AI-based early detection of heat exchanger fouling
• Implementation of a secure end-to-end data pipeline with OPC UA
• Integration of real-time monitoring and anomaly detection dashboards
• Scalable architecture for distributed mobile water purification units
• Use of operational data for root-cause analysis and maintenance optimization
• Feedback loop from operational data to engineering design improvements

Practical takeaways

Participants learn how AI techniques can enable early anomaly detection in heat exchangers and other process assets to improve predictive maintenance. They explore the design of a secure, scalable data architecture supporting remote operation of mobile industrial units. The session highlights how integrated real-time dashboards and AI-based insights support maintenance decision-making, optimise cleaning schedules, and reduce unplanned downtime. Attendees gain understanding of how operational data can inform both immediate maintenance actions and ongoing engineering refinements to asset performance.

Asset-intensive organisations using SAP Enterprise Asset Management (EAM) face ongoing challenges in leveraging the system's full capabilities for maintenance and reliability excellence. Many struggle with embedding best practices consistently across sites, limiting the value realised from SAP EAM investments. Understanding how current users implement SAP EAM workflows, data management, and integration with operational processes is critical to identifying gaps and opportunities for improvement.

In response, SOA People has conducted a comprehensive field survey focused on SAP EAM adoption, examining practical implementation trends and obstacles. This survey offers a unique industrial perspective on how organisations prepare for future asset management challenges within the evolving landscape of SAP technologies. The session explores key insights from this 2026 study, highlighting lessons learned and areas needing attention to optimise SAP EAM use in maintenance and asset performance management.

Presentation content

• Overview of the 2026 SAP EAM field survey methodology
• Current adoption levels of SAP EAM best practices
• Common implementation challenges and obstacles
• Integration of SAP EAM with maintenance workflows
• Data quality and governance issues in SAP EAM
• Alignment of SAP EAM with asset management strategies

Practical takeaways

Participants learn how to assess their organisation’s current SAP EAM adoption against field survey findings, identify common pitfalls in implementation, and recognise organisational and technical factors that impact effective use. The session provides guidance on aligning SAP EAM processes with broader maintenance and asset management goals to enhance system value and operational performance.

European asset owners are under increasing pressure due to aging brownfield plants, rising labour and energy costs, regulatory burdens, and scarcity of skilled workers. These challenges threaten global competitiveness and elevate maintenance costs across industrial sites. Traditionally, the perceived complexity of AI implementation—requiring advanced data engineering skills and robust digital architectures—has slowed adoption in asset management.

Recent advancements in industrial and agentic AI technologies have reduced these barriers, making scalable AI solutions accessible for diverse operational challenges. This session examines how managers across asset management, production, quality, engineering, and supply chain functions can identify practical AI use cases aligned with enterprise strategy. It delves into straightforward implementation approaches, enabling fast pilot projects and effective rollouts that deliver measurable improvements in productivity and profitability.

Presentation content

• Definition and operation of industrial and agentic AI
• Typical AI business cases for asset management improvement
• Requirements for rapid AI implementation and digital scaling
• Data and digitization decisions relevant for AI deployment
• Aligning AI initiatives with enterprise strategy
• Steps for initiating productivity improvements with AI

Practical takeaways

Participants learn to identify relevant AI use cases and pilot projects within their areas of responsibility. They gain an understanding of different industrial AI methods, enabling them to develop actionable roadmaps for plant management enhancement. The session highlights conditions necessary for successful AI adoption, including scalable digital architectures and strategic alignment, supporting faster decision-making and sustainable investment in AI-driven asset management solutions.

Sanofi operates 39 Manufacturing & Supply sites facing the challenge of inconsistent maintenance practices and reactive strategies across a global footprint. With the complexity of managing diverse assets and operational environments, achieving standardized, reliable maintenance that maximizes asset value is critical to reducing costs and increasing uptime.

To address this, Sanofi implemented a Maintenance & Reliability Program combining its SMS 2.0 Maintenance & Reliability Ecosystem with a Value Driven Maintenance (VDM) methodology. The SMS 2.0 Ecosystem standardizes and digitizes maintenance activities through seven interconnected pillars, providing a unified maintenance philosophy that visualizes the entire asset lifecycle and connects maintenance tasks across all sites. The VDM approach prioritizes maintenance efforts based on their contribution to asset value, enabling sites to quantify improvements in cost reduction and performance uptime. Together, these initiatives guide sites from reactive toward proactive, data-driven maintenance while fostering global standardization, enhanced reliability engineering, and digital innovation.

Presentation content

• Integration of SMS 2.0 Maintenance & Reliability Ecosystem with VDM
• Standardizing and digitizing maintenance practices across seven pillars
• Visualizing the full asset life cycle to unify maintenance activities
• Prioritizing maintenance efforts based on value contribution
• Implementing structured assessments and targeted action plans
• Driving maintenance maturity and execution at 39 global sites
• Fostering data-driven maintenance and enhanced reliability engineering

Practical takeaways

Participants learn how to implement a unified maintenance framework that combines standardized, digitized processes with value-based prioritization. They gain insights into shifting from reactive to proactive, data-driven maintenance regimes, managing maintenance maturity at multiple sites, and applying structured assessments to guide improvements. The session provides practical understanding of aligning global maintenance practices with business value to enhance uptime and reduce costs while advancing reliability engineering and digital capabilities.

Many industrial organisations face complexity in managing maintenance, repair, and overhaul (MRO) inventory across multiple sites and suppliers. Disparate data sources, lack of standardisation, and unclear parts identification can lead to inefficiencies, increased downtime risk, and challenges in sourcing critical spares. This complexity hampers maintenance planning and operational resilience, making it difficult to maintain reliable production.

Addressing this, organisations implement strategies to increase transparency and streamline MRO data by adopting uniform part identification standards and consolidating spare parts information. By improving visibility across sites and supplier networks, they enhance proactive obsolescence management, support strategic sourcing decisions, and reduce coordination friction between maintenance and procurement functions. This workshop explores practical approaches to establishing a shared, accurate MRO data foundation that underpins resilient and efficient maintenance operations.

Presentation content

• Adopting a unified part identification standard
• Managing obsolescence with proactive data alignment
• Enhancing cross-site spare parts visibility
• Aligning maintenance and procurement on shared data
• Identifying OEMs and alternative suppliers effectively
• Detecting cost deviations and consolidating vendors
• Supporting strategic sourcing across internal and external networks

Practical takeaways

Participants learn how standardising MRO data reference improves transparency and reduces complexity in spare parts management. The session highlights prerequisites for successful adoption, how to integrate data consolidation across multiple sites, and how improved visibility supports maintenance planning and sourcing decisions. Attendees gain insights into establishing a shared data foundation that fosters operational resilience by enabling confident vendor consolidation, obsolescence management, and strategic procurement alignment.

Asset management and maintenance functions are facing growing complexity in managing industrial assets while maintaining reliability and operational efficiency. Current Enterprise Asset Management (EAM) systems often fall short in dynamically adapting workflows and decisions to evolving asset conditions and operational contexts. This gap challenges organisations to balance technology-driven automation with human expertise to optimise asset performance.

Agentic AI introduces a new paradigm by enabling autonomous decision-making within EAM platforms, potentially transforming how maintenance, reliability, and asset management teams operate. This session involves insights from Ultimo and asset owner Berkvens, exploring how agentic AI can be integrated into maintenance environments to enhance adaptability, predictive capabilities, and operational workflows without compromising reliability fundamentals or human oversight.

Presentation content

• Overview of agentic AI concepts in EAM
• Integration of agentic AI into existing maintenance workflows
• Balancing automated decision-making with human engineering judgment
• Case study of Berkvens’ implementation of agentic AI
• Impact of agentic AI on asset performance and reliability
• Challenges and limitations of adopting agentic AI in asset management

Practical takeaways

Participants learn how agentic AI can extend the capabilities of traditional EAM systems by enabling flexible, autonomous decision-making that adapts to asset condition and operational changes. The session provides a practical understanding of how to implement agentic AI in maintenance workflows while managing the interplay between automated insights and human expertise. Attendees gain insights into operational experiences from the Berkvens case, including challenges encountered and key factors for successful integration of AI-driven approaches in asset management.

Industrial organisations are increasingly adopting Artificial Intelligence to enhance asset reliability, optimise maintenance, and improve operational decision-making. Despite advances in analytics and machine learning, many AI projects struggle to move beyond pilot stages or fail to produce measurable business results. This performance gap is less about the technology itself and more about translating AI insights into consistent decisions, operational actions, and organisational adoption.

Reliability functions provide a complex environment that highlights challenges such as fragmented data sources, dispersed operational knowledge, and conflicting priorities. Addressing these challenges requires more than advanced algorithms—it demands integrating AI into a broader capability system involving aligned business objectives, trusted data, human expertise, scalable architecture, governance, and continuous improvement.

This session introduces a practical framework based on five foundational requirements to help reliability and asset management professionals build AI systems that deliver scalable, value-driven outcomes and support sustainable industrial decision-making.

Presentation content

• Aligning AI initiatives with business objectives and decision-making
• Combining machine analysis with human operational expertise
• Establishing trusted, high-quality data for confident decisions
• Developing scalable data architectures across assets and systems
• Implementing governance and performance mechanisms for AI value
• Assessing readiness to scale AI beyond pilot projects

Practical takeaways

Participants learn why many industrial AI initiatives fall short of sustainable impact and how successful AI integration depends on effective decision alignment, authentic human-machine intelligence, reliable data, scalable infrastructures, and robust governance. They gain a framework to evaluate current AI efforts, identify key barriers, and build the organisational capabilities necessary to convert AI insights into operational actions that improve asset performance and reliability.

Asset owners face growing challenges as an ageing workforce retires, accelerating knowledge loss critical to maintaining reliable operations. Simultaneously, maintenance teams manage increasing volumes of data, often without sufficient return on investment due to difficulties in converting information into timely, actionable decisions. These challenges emphasize the tension between leveraging advanced AI technologies and maintaining effective, human-centered asset management practices.

Agentic AI offers a promising approach by evolving beyond generative AI to autonomous systems that can collaborate with human operators in maintenance and asset management workflows. This session provides a current overview of agentic AI developments and adoption within industrial environments, addressing enablers and obstacles for integrating these new AI agents. Practical insights are drawn from recent case studies illustrating how agentic AI supports knowledge retention and decision-making on the factory floor, helping organisations balance increasing data complexity with operational reliability.

Presentation content

• Distinctions between generative AI and agentic AI
• Current adoption of agentic AI in maintenance environments
• Recent developments in agentic AI technologies
• Enablers for agentic AI integration in asset management
• Obstacles faced during AI implementation
• Anonymized industry case studies from Axians

Practical takeaways

Participants learn how agentic AI differs from generative AI and its practical applications in maintenance and asset management. They gain insights into conditions enabling successful AI integration, recognise key challenges encountered during deployment, and understand how autonomous AI agents can help address knowledge retention and data overload. The session offers actionable lessons from recent industrial experience, highlighting approaches to enhance decision-making and support operational workflows with evolving AI capabilities.

Nyrstar’s electrolysis, smelter, and zinc dust plants faced challenges with unplanned downtime caused by limited insight into failure patterns and an imbalance between reactive and preventive maintenance. This situation impacted asset reliability and maintenance efficiency within complex industrial operations.

To address these issues, Nyrstar realigned its maintenance strategy focusing on a proactive, reliability-driven approach. Key processes and tools such as variance meetings, Overall Equipment Effectiveness (OEE) analysis, risk registers, Management of Change (MOC), preventive maintenance planning, and reliability engineering were implemented. By relying on objective data and clear KPIs, they improved understanding of failure causes, prioritized critical asset risks, and fostered collaboration between production and maintenance teams to reduce disruptions.

This strategic realignment demonstrates how integrating structured performance monitoring and risk management supports more reliable asset operations and a more efficient maintenance organisation in heavy industry environments.

Presentation content

• Realignment of maintenance strategy across multiple plant areas
• Use of variance meetings to analyse failures and production losses
• Application of OEE tools to assess availability and quality losses
• Implementation of risk registers for critical asset prioritization
• Integration of Management of Change for controlled modifications
• Optimization of preventive maintenance planning and scheduling
• Use of reliability engineering and root cause analysis techniques

Practical takeaways

Participants learn how to transition from reactive to proactive maintenance by applying tools such as OEE analysis, variance meetings, risk registers, and MOC. They gain insight into aligning maintenance strategy with reliability principles, improving failure diagnosis and risk prioritization, and using KPIs to drive continuous performance improvement. The session provides practical examples of bridging data with action to reduce unplanned downtime and build a more effective maintenance organisation.

Industrial operations face ongoing challenges in improving productivity while managing complex processes and vast data flows. Establishing effective entry points for AI integration remains a key barrier for many organisations seeking tangible results from digitalisation. Balancing conventional AI's limitations with the need for robust and reliable tools is critical to transform manufacturing and plant operations.

This workshop explores practical approaches to Industrial AI, distinguishing between analytical AI, statistical decision systems, and agentic AI to provide clarity on which methods deliver replicable value. It focuses on actionable strategies to implement AI within industrial environments, supporting transitions from smart factories to autonomous plants. Participants will develop tailored roadmaps for AI microprojects designed to achieve sustainable improvements and quick payback, addressing common operational challenges with relevant use cases.

Presentation content

• Transitioning from smart factories to autonomous plants
• Overview of Industrial AI: analytical, statistical, and agentic AI
• Data flow and digitisation building blocks in industrial settings
• Identifying use cases and developing strategic AI roadmaps
• Implementing AI microprojects with measurable value and payback
• Use cases including plant control, optimisation, and condition prognosis
• Interactive creation of individual AI strategy and jump-start plans

Practical takeaways

Participants learn how to effectively differentiate key Industrial AI methods and select suitable approaches for their operations. They gain insight into structuring data flows and digitisation to support AI deployment. The workshop guides practitioners on identifying high-impact use cases and transitioning from prototyping to strategic AI initiatives. Attendees develop actionable AI microproject plans that balance operational demands with sustainable value creation and rapid return on investment.

In asset-intensive operations, maintenance data quality often suffers due to inconsistent and incomplete documentation by technicians under time pressure. Typically, findings, actions, and measurements are recorded as rushed free-text notes after work is completed, leading to missing asset context, unreliable failure descriptions, delayed work order closure, and increased back-office rework. These issues compromise the accuracy of historical data vital for reliability improvements.

BP Castrol, in partnership with Highsail, addressed this challenge by implementing a voice-first logging workflow integrated directly within their existing ERP/EAM systems. This approach enables technicians to capture structured maintenance data in real time without adding administrative burden. The solution handles plant-specific terminology and acronyms while incorporating AI-supported review loops to maintain data trustworthiness without causing process bottlenecks. The session explores how this collaboration has improved documentation completeness, reduced clarification cycles, and accelerated work order closure through a measured and iterative rollout.

Presentation content

• Identifying documentation as the key maintenance digital gap
• Designing voice-first logging aligned with ERP/EAM workflows
• Converting voice input into structured, standardized work order data
• Managing plant-specific jargon, acronyms, and multilingual inputs
• Integrating AI review loops for data validation and governance
• Piloting, adoption tactics, and change management strategies
• Measuring impact on data completeness and work order processing times

Practical takeaways

Participants learn how to assess current maintenance documentation bottlenecks and establish baseline metrics, implement voice-based logging integrated with existing enterprise systems, and apply governance models including AI-supported review loops to sustain data quality. They gain insights into managing domain-specific language challenges and change management tactics for successful rollout. The session provides a repeatable blueprint based on BP Castrol’s experience for other asset owners seeking to enhance maintenance data reliability without extensive IT projects.

Industrial assets are increasingly complex and digitally connected, yet grease—the most commonly used lubricant—remains an underutilised source of reliability data. Traditional grease assessments rely on static tests like NLGI grade, which do not reflect actual lubricant performance under operating conditions, limiting insight into component health. Obtaining representative grease samples also poses practical challenges, often leading to unreliable diagnostic conclusions.

This session presents a data-driven approach to grease diagnostics combining standardized sampling (ASTM D7718) with dynamic consistency profiling using the Grease Thief® Analyzer (GTA, ASTM D7918). By replacing static tests with kinetic measurements, the methodology captures grease behaviour under bearing-level forces, enabling earlier detection of wear, contamination, and lubrication issues. Integrating particle-level analysis further informs cleanliness classes and failure mode identification from minimal sample volumes, applicable even to sealed components.

Validated initially in wind energy and now expanding to wider industry, this approach supports reliability improvements, optimized relubrication intervals, and lifecycle cost reduction. The session explores operational challenges and practical steps to integrate grease analytics into predictive maintenance frameworks, transforming grease from a routine consumable into a strategic data source for asset performance management.

Presentation content

• Comparison of static and dynamic grease consistency measurements
• Interpretation of GTS Load and Index for fresh and in-service greases
• Standardized grease sampling practices according to ASTM D7718
• Particle classification for wear mode and contamination diagnosis
• Case studies on grease degradation and contamination impacts
• Correlation of grease condition with operational asset performance
• Integration of grease analytics into predictive maintenance systems

Practical takeaways

Participants learn how dynamic grease testing differs from traditional methods and how to apply standardized sampling techniques to obtain reliable diagnostic data. They gain insight into interpreting grease condition changes during operation to optimize relubrication schedules and asset reliability. The session also provides guidance on integrating grease analysis data into predictive maintenance ecosystems to detect early failure signs, assess contamination risks, and improve lifecycle cost management across diverse industrial applications.

Effective asset management requires a structured approach to optimise the reliability, performance and lifecycle costs of industrial assets. Many organisations face challenges in aligning their maintenance and asset management strategies with operational objectives and regulatory requirements, while ensuring consistent practices across diverse sites.

The EFNMS Asset Management Workshop focuses on advancing asset management capabilities through shared expertise and practical frameworks. It supports professionals in maintaining asset integrity and improving decision-making by addressing organisational workflows, methodologies, and standards relevant to complex asset portfolios. This workshop facilitates knowledge exchange to enhance integration between asset management principles and operational maintenance activities.

Presentation content

• Key principles and frameworks of asset management
• Aligning asset management with maintenance strategies
• Integrating asset management into operational workflows
• Assessing asset performance and lifecycle management
• Addressing organisational challenges and standards
• Enhancing cross-site asset management consistency

Practical takeaways

Participants learn structured approaches to integrate asset management with maintenance and operational practices. They gain insight into applying international frameworks and standards to improve lifecycle asset performance and organisational alignment. The workshop offers guidance on overcoming common implementation challenges and fostering consistent asset management processes across diverse operational environments.

Rockwool, a leading insulation manufacturer operating across the Nordics, faces operational challenges in streamlining maintenance and warehouse workflows for its frontline, deskless workers. These environments require hands-free, reliable access to technical information and task support, especially in noisy, industrial settings where gloves and other protective equipment limit traditional input methods.

To overcome these challenges, Rockwool has deployed SAP-integrated mobile applications developed by 2BM Software that enhance maintenance and warehouse operations. A key innovation is the integration of "Ask Odin," an AI-powered voice assistant designed specifically for maintenance and warehouse personnel. This conversational AI tool enables hands-free operation, allowing workers to query equipment manuals, access historical work orders, and receive instant technical advice, all through voice commands. This approach addresses the critical need for efficient task execution without disrupting production or compromising safety.

Presentation content

• Integration of AI voice assistant with SAP Plant Maintenance
• Hands-free operation suited for noisy industrial environments
• Accessing internal maintenance history and asset documentation
• Instant retrieval of technical specifications from equipment manuals
• Visual and audio diagnostics using AI for issue identification
• Supporting frontline workers with voice-enabled task execution

Practical takeaways

Participants learn how AI voice agents can effectively integrate with SAP maintenance systems to support hands-free workflows in industrial environments. The session highlights key conditions for successful implementation, including adapting to noisy, glove-wearing workforces and leveraging internal data sources for diagnostics and task guidance. Attendees gain insight into the practical benefits and limitations of conversational AI in maintenance operations and how these solutions can be applied to improve frontline workforce efficiency and maintenance ROI in comparable industrial settings.

Online oil sensors are vital for effective lubrication management and predictive maintenance of industrial machinery. These sensors monitor key oil parameters such as viscosity, water content, and wear debris, enabling early fault detection to enhance equipment reliability and availability. However, sensor accuracy and longevity depend on a carefully managed life cycle that extends beyond installation to include ongoing maintenance, calibration, and timely replacement.

The technical challenge lies in balancing advanced condition monitoring capabilities with fundamental reliability requirements. Correct sensor selection must consider oil type, chemical compatibility, operating conditions, and environmental factors to avoid measurement errors. Proper installation practices prevent disturbances caused by air bubbles and environmental fluctuations. A proactive maintenance approach with regular cleaning, electrical checks, and calibration is essential to mitigate measurement drift and ensure dependable data.

This session presents a comprehensive methodology for managing the full life cycle of online oil sensors. It emphasizes strategic sensor selection, standardized installation procedures, and rigorous maintenance protocols. By aligning these elements, organizations can improve the reliability of lubrication systems, reduce operational risks, and support sustainable condition-based maintenance strategies.

Presentation content

• Role of online oil sensors in predictive maintenance
• Criteria for strategic sensor selection and application matching
• Standardized installation practices to ensure data accuracy
• Maintenance routines including cleaning and electrical inspections
• Calibration protocols using certified reference standards
• Proactive life-cycle management to extend sensor operational life

Practical takeaways

Participants learn how to develop and implement a full life-cycle management strategy for online oil sensors, including selecting sensors suited to specific oils and environments, applying standardized installation methods to prevent measurement errors, and establishing preventive maintenance and calibration protocols. The session demonstrates how these practices maintain sensor accuracy over time, reduce operational costs, and enhance condition-based maintenance efforts applicable across various industrial settings.

Maintenance teams frequently encounter a critical yet often overlooked challenge: fragmented and inconsistent spare parts data. This lack of reliable information undermines maintenance planning, causing extended equipment downtime, emergency part procurement, and inflated inventory costs. Such inefficiencies directly impact asset reliability and operational continuity.

To address this, organisations are adopting robust data governance strategies focused on establishing spare parts transparency. By standardising part references and improving cross-site visibility, maintenance planning becomes more accurate and proactive. This session presents practical approaches used by leading manufacturers to transform fragmented spare parts data into a coherent, accessible network that supports efficient maintenance execution and reduces operational risks.

Presentation content

• Implementing a one part, one reference standard
• Eliminating duplicate and obsolete spare parts records
• Enhancing cross-site spare parts data transparency
• Supporting maintenance planning with reliable parts information
• Standardising and automating spare parts management processes

Practical takeaways

Participants learn how adopting a unified part reference system improves spare parts data reliability, enabling better management of duplicates and obsolescence. The session reveals how enhanced transparency across multiple sites supports more effective maintenance planning and reduces unplanned downtime risks. Attendees gain insights into reducing manual effort through standardised, automated processes that integrate with daily maintenance operations, providing a foundation for sustainable asset and inventory management improvements.

Electric motors are critical assets in many industrial environments but present challenges for condition monitoring due to complex failure modes and accessibility issues. Combining Motor Current Signature Analysis (MCSA) with established vibration analysis offers a more comprehensive diagnostic approach, enabling detection of almost all possible motor faults through aggregated data. This integrated technique helps maintenance teams overcome limitations of single-method monitoring by capturing both electrical and mechanical indicators of asset health.

Schaeffler Belgium has developed an MCSA module on their existing monitoring platform to unify electric signal analysis with vibration data. This integration supports earlier and more accurate condition assessments, which is particularly valuable for hard-to-reach or critical motors where traditional monitoring is difficult or incomplete. The approach enhances maintenance decision-making by providing a broader fault detection spectrum within a single system.

Presentation content

• Development of MCSA integration on vibration analysis platform
• Combining electrical signal and vibration data for fault detection
• Detection capabilities for various electric motor issues
• Application to condition monitoring of hard-to-reach assets

Practical takeaways

Participants learn how integrating MCSA with vibration analysis improves fault detection coverage for electric motors. The session explains the combined methodology and its role in identifying asset failures that may be missed by vibration analysis alone. Attendees gain insight into the technical considerations for implementation and how aggregated data supports maintenance teams in better diagnosing motor health, especially for challenging or critical applications.

Effective asset management is critical for maintaining operational reliability and optimising asset performance across industrial environments. Despite advances in technology and methodologies, organisations often face bottlenecks that hinder the seamless flow of information and decision-making along the asset management chain. These bottlenecks can result from fragmented data sources, disconnected maintenance processes, or gaps in integrating asset management strategies with operational realities.

Addressing these challenges requires a structured approach that identifies and removes constraints within the asset management chain, ensuring better coordination between stakeholders, enhanced data utilisation, and aligned workflows. By focusing on these operational bottlenecks, professionals can unlock improved asset availability, reduced downtime, and more effective maintenance planning. This workshop will explore key factors limiting performance in asset management and discuss practical steps to strengthen the entire process from data capture to maintenance execution.

Presentation content

• Identifying bottlenecks in the asset management workflow
• Aligning asset management strategy with operational processes
• Enhancing data integration and accessibility
• Improving coordination across maintenance and reliability teams
• Leveraging organisational measures to support asset performance
• Optimising the asset management chain for continuous improvement

Practical takeaways

Participants learn how to systematically identify and address bottlenecks that limit asset management effectiveness, improving information flow and decision-making. The session provides insights on integrating strategic asset management with operational maintenance processes and organisational practices. Attendees gain practical approaches to enhance data sharing, foster collaboration among teams, and create a more resilient asset management chain that supports reliability and performance objectives.

Asset owners often invest heavily in creating detailed digital models of their facilities using BIM, CAD, GIS, and large-scale 3D data sources. However, these rich spatial datasets typically remain fragmented across incompatible software systems, limiting access to specialists and preventing a unified view of the asset throughout the organisation. This fragmentation challenges maintenance and operational teams by restricting their ability to leverage high-fidelity geometry data in daily workflows.

The session presents a practical method to overcome these silos by integrating diverse spatial data types—including laser scans, 3D models, 2D plans, and GIS—into a cohesive, high-performance platform. Demonstrated through a chemical industry case, the approach enables smooth navigation of terabyte-scale geometry datasets with on-premise deployment and strict, role-based access controls to maintain security and data sovereignty. This unified access supports broader stakeholder use, improves decision-making, and reduces dependency on technical specialists under real industrial constraints.

Presentation content

• Challenges of fragmented spatial asset data in organisations
• Securing on-premise deployment with role-based access control
• Efficient processing and visualization of terabyte-scale geometry data
• Integrating BIM, CAD, GIS, point clouds and 3D models
• User-friendly interfaces enabling non-expert navigation
• Case study in chemical industry with real-world IT and organisational constraints
• Operational impacts including cost efficiency and decision support

Practical takeaways

Participants learn how siloed spatial data limits operational performance and maintenance efficiency, and explore methods to unify complex geometry data within secure, on-premise environments. They gain insights into performance optimisation strategies for large-scale datasets, implementation challenges including access control, and how to make detailed asset data more accessible to non-specialists. The session provides practical lessons for expanding digital asset usage beyond specialised teams to enhance daily asset management and decision-making.

Electric motors are vital assets in industrial operations but often experience degradation that progresses unnoticed during routine use. Many electrical and electromechanical faults evolve slowly and remain hidden until significant damage occurs, challenging maintenance teams to detect issues early without disrupting production.

Advanced diagnostic methods can accurately identify root causes but are typically reserved for reactive responses due to their complexity, cost, and the difficulty of taking machines offline. This session presents a systematic, non-intrusive Machine Health Scan approach that leverages operational electrical measurements to screen motors for early signs of degradation and dominant risk mechanisms across motor fleets.

By converting electrical signature data into health indicators and alarm categories, this method helps maintenance and reliability professionals prioritize assets and establish clear decision pathways. The approach integrates health screening with targeted fault diagnosis within a layered reliability strategy, enabling a shift from reactive to proactive, risk-based asset management.

Presentation content

• Concept of machine health versus fault diagnosis
• Systematic health scan methodology using electrical signals
• Identification of dominant degradation mechanisms from current data
• Risk-based escalation for trending, inspection, or diagnosis
• Translating health indicators into maintenance and reliability actions

Practical takeaways

Participants learn how to distinguish health scanning from detailed fault diagnosis and apply a structured methodology for evaluating motor condition through operational electrical measurements. The session clarifies when to escalate anomalies for more in-depth analysis and how to convert health scan findings into actionable maintenance decisions. Maintenance professionals gain practical insights into improving early detection of emerging risks, optimizing diagnostic efforts, and advancing from reactive to risk-based maintenance strategies.

Asset-intensive organisations often accumulate large volumes of operations and maintenance (O&M) data across their plants, yet struggle to apply this information effectively due to inconsistent data quality, fragmented asset hierarchies, and siloed processes. This challenge limits the ability to compare asset performance and differentiate maintenance strategies systematically, hindering optimisation and decision-making.

To address these issues, organisations can adopt a unified data model that harmonises maintenance records, work orders, asset structures, and spare-parts information. Such integration enables a common basis for analysis across assets and organisational functions, improving comparability and supporting data-driven strategy differentiation. Practical cases from the Oil & Gas sector illustrate how structured O&M data can be operationalised to enhance maintenance efficiency, streamline work-order planning, and optimise spare-parts inventories, delivering measurable improvements without reliance on complex algorithms.

This approach provides a roadmap for maintenance and asset management professionals to transform fragmented datasets into actionable decision support, strengthening maintenance planning and asset performance management across industrial environments.

Presentation content

• Unified O&M data model for cross-asset comparability
• Maintenance job clustering to identify redundant tasks
• Automated work-order configuration and planning
• Spare-parts inventory alignment with critical equipment
• Translating maintenance history into strategy differentiation

Practical takeaways

Participants learn how to leverage harmonised O&M and CMMS data to support systematic maintenance strategy differentiation and enable asset comparability across sites and functions. The session highlights conditions for successful data integration, techniques to identify redundant maintenance tasks, methods to automate and accelerate work-order planning, and approaches to optimise spare-parts stock while maintaining supply reliability. Attendees gain insight into converting historical maintenance data into actionable decision support that enhances maintenance efficiency and informs long-term asset management.

Unexpected failures of electric motors often lead to unplanned downtime and maintenance inefficiencies in industrial operations. Managing the large volumes of motor voltage and current data while accurately detecting faults early remains a critical challenge for maintenance and reliability teams. Ensuring timely and reliable diagnostics is necessary to optimise asset availability, reduce safety risks, and manage operational costs effectively.

To address these issues, Enging - Make Solutions has developed an AI-driven predictive maintenance platform that integrates real-time electrical measurements with machine learning models. This system extracts detailed features such as harmonics, phase imbalances, and symmetrical components from continuous motor signal acquisition. Through a combination of supervised learning and adaptive anomaly detection, it classifies fault types, predicts degradation trends, and supports prescriptive maintenance planning. The platform also offers digital dashboards, automated reports, and seamless integration with enterprise asset management systems to deliver actionable insights for maintenance engineers and plant operators.

Presentation content

• Automated fault diagnosis using AI and machine learning
• Real-time acquisition and analysis of motor electrical signals
• Feature extraction including harmonics and phase unbalances
• Fault classification and degradation trend prediction
• Combining supervised learning with adaptive anomaly detection
• Integration with digital dashboards and asset management systems
• Industrial case study demonstrating operational impact

Practical takeaways

Participants learn how AI and machine learning facilitate automated detection and classification of motor faults using real-time electrical data. The session highlights the technical and operational requirements for deploying scalable diagnostic platforms, including handling data quality and integrating with existing asset management processes. Participants gain insights into translating AI-driven outputs into actionable maintenance interventions that can anticipate faults well in advance, thereby supporting improved reliability and maintenance efficiency in industrial environments.

Effective condition monitoring (CM) programs are crucial for improving the efficiency and reliability of maintenance operations across various industries, including power generation and marine sectors. Many organisations face challenges in deploying CM initiatives that genuinely influence maintenance decision-making and generate sustainable value. The key issue lies in transforming vast amounts of condition data into actionable maintenance steps that reduce failure risks and optimise resource allocation.

This session draws on seven years of operational experience involving over 3,000 monitored machines and more than 45,000 completed CM analyses. It identifies critical success factors for CM program deployment and demonstrates how well-integrated CM and condition-based maintenance (CBM) initiatives can shift maintenance culture towards proactive, data-driven practices. Insights from practical case studies illustrate how these strategies contribute to improved machine reliability and long-term operational benefits beyond financial return on investment.

Presentation content

• Fundamentals of condition monitoring and condition-based maintenance
• Evaluating return on investment in CM programs
• Critical success factors for CM program implementation
• Case studies from power generation and marine industries
• Methods to integrate CBM information into maintenance decisions
• Strategies to maximise ROI from condition-based maintenance

Practical takeaways

Participants learn how to design and deploy condition monitoring programs that effectively support maintenance decisions. They gain insight into the conditions required for sustained ROI, common pitfalls to avoid in CM initiatives, and how to translate condition data into actionable maintenance activities. The session also offers lessons on driving a cultural shift toward proactive, data-driven maintenance practices applicable across various industrial contexts.

De Watergroep manages an extensive drinking water distribution network challenged by ageing infrastructure and large District Metered Areas (DMAs) which hinder timely and precise leak detection. Fragmented IoT sensor data further complicates network-wide visibility and rapid validation of leak repairs, impacting operational costs and environmental footprint.

To address these challenges, De Watergroep integrates asset management priorities with harmonised operational and financial data using the Delphi platform, establishing a single source of truth. By deploying a denser sensor network and leveraging AI-driven analytics, the organisation enhances detection, localisation, and proactive prioritisation of leaks. This approach links pipe investment decisions to end-to-end performance monitoring, enabling targeted interventions based on asset condition, operational impact, and business value.

The case illustrates how combining strategic asset management, IoT data integration, and advanced analytics supports a shift from reactive leak management towards proactive, data-driven water network performance management.

Presentation content

• Transitioning from reactive to proactive water leakage management
• Integrating asset, operational, IoT and financial data via Delphi platform
• Expanding sensor coverage to improve leak detection and localisation
• Applying AI analytics for prioritisation of potential leak interventions
• Connecting pipe investment decisions with operational and financial metrics
• Implementing near-real-time data for intervention management and repair validation

Practical takeaways

Participants learn how a business-driven asset strategy combined with harmonised data enhances proactive leakage reduction. They gain insight into deploying denser sensor networks and AI analytics to improve leak detection and prioritisation. The session clarifies how integrated operational and financial monitoring guides economically justified investments and supports near-real-time intervention validation. Lessons from De Watergroep’s approach highlight conditions for successful implementation and its applicability to water utilities seeking to optimise asset performance and reduce operational costs.

Maintaining operational safety during technical interventions is critical in industrial environments such as those at Friesland Campina. The complexity of modern maintenance tasks, combined with stringent safety requirements, creates a challenge to ensure both worker safety and asset reliability. Digital tools can enhance safety practices by providing structured workflows and real-time information, reducing human error and exposure to hazards.

Friesland Campina is exploring the integration of digital solutions to support safe maintenance activities. These tools aim to improve safety compliance, facilitate communication between teams, and ensure that safety protocols are consistently followed. By strengthening the connection between safety processes and maintenance execution through digitalisation, the organisation seeks to mitigate risks and improve overall operational performance.

Presentation content

• Current safety challenges in maintenance operations
• Role of digital tools in supporting safety compliance
• Integration of safety protocols into maintenance workflows
• Practical application of digital safety solutions at Friesland Campina
• Collaboration between asset owners and service providers
• Lessons learned from implementing digital safety measures

Practical takeaways

Participants learn how digital tools can be effectively integrated into maintenance processes to enhance safety and reduce risk. The session provides insight into operational challenges related to safety during maintenance and demonstrates practical approaches for using digital workflows to enforce safety standards. Attendees gain understanding of key success factors and potential barriers when adopting digital safety enhancements in industrial environments.

For professionals with maintenance, reliability or asset management responsibility across multiple sites. Participation is subject to approval. Participation details

Managing maintenance and contractors across multiple industrial sites requires balancing central governance with local operational and regulatory realities. Large organisations, such as TotalEnergies and OQ, face the challenge of establishing consistent maintenance and contractor management standards while ensuring flexibility for site-specific conditions. Achieving this balance is critical for maintaining reliability, optimising contractor performance, and controlling administrative burden.

This session explores how centrally defined maintenance methodologies, contract principles and digital tools are implemented across diverse sites. It highlights the use of multi-site, multi-year maintenance contracts with common performance measurement, continuous improvement frameworks and incentive mechanisms to sustain long-term contractor relationships. Scaling contractor management also involves addressing fragmented onboarding, certification and compliance processes through centralised information and AI-driven automation, improving visibility and reducing manual workload without compromising local judgement.

Together, these approaches illustrate how combining centralised governance, standardised methodology and digitalisation supports consistent asset performance while respecting necessary site-level autonomy and regulatory variation.

Presentation content

• Balancing central governance with site-specific flexibility
• Implementing multi-site and multi-year maintenance contracts
• Translating common maintenance methodologies into contracts
• Monitoring contractor performance and continuous improvement
• Centralising contractor information, certification and compliance
• Applying AI-driven automation for scalable contractor management
• Integrating digital tools with local decision-making

Practical takeaways

Participants learn how central maintenance frameworks can enforce consistency across multiple sites while preserving local autonomy. They gain insight into structuring multi-site maintenance contracts with clear governance and continuous performance improvement mechanisms. The session demonstrates how digitalisation and AI-driven workflows reduce administrative workload in contractor management without compromising regulatory compliance. Attendees understand the importance of differentiating between standardisable processes and those requiring local judgement, and how to maintain long-term contractor relationships through performance monitoring and incentives.

Many asset-intensive organisations seek to implement predictive maintenance (PdM) programs to reduce unplanned downtime and optimise asset performance. However, one critical challenge is the common assumption that existing data is complete and of sufficient quality to support accurate predictions. Inaccurate or incomplete sensor data, inconsistent readings, and missing presets often compromise the reliability of PdM models, leading to misguided maintenance decisions and inefficient resource use.

To address these issues, the session explores practical methods for auditing and assessing data readiness before deploying predictive models. It focuses on data cleaning, normalisation, and adapting predictive algorithms to handle gaps and inconsistencies. Real-world case studies demonstrate how systematic data preparation improves prediction accuracy, reduces operational risk, and enhances maintenance resource allocation in practice.

Presentation content

• Common data quality and completeness issues in predictive maintenance
• Risks of overestimating data availability and making false assumptions
• Auditing and assessing asset and sensor data readiness
• Methods for cleaning and normalising historical datasets
• Adjusting predictive models to accommodate data gaps
• Case studies showing improvements in prediction accuracy and downtime

Practical takeaways

Participants learn to recognise typical data-related pitfalls affecting predictive maintenance accuracy and how incomplete or low-quality data undermines reliability. They gain practical strategies for auditing, cleaning, and preparing data before PdM implementation. The session also provides insights from real-world cases on achieving measurable improvements in prediction quality and operational efficiency through robust data preparation, enabling more reliable maintenance decision-making in asset-intensive environments.

OQ RPI faced unpredictability in asset performance that directly impacted both production stability and financial results, highlighting the critical need to move beyond reactive maintenance approaches. This challenge was compounded by high operational risks due to limited proactive risk management, fragmented asset management practices, and insufficient integration of digital tools and condition monitoring into decision-making processes. Achieving a balance between cost optimization, reliability, and long-term asset integrity was essential to sustain operational and financial performance.

To address these issues, OQ RPI embarked on a structured transformation, evolving from a Reliability Improvement Program focused on stabilizing assets to a comprehensive Asset Management system. This approach integrates risk-based and predictive maintenance practices, enhanced reliability engineering, and improved work execution. Cross-functional alignment, leadership engagement, and digital solutions underpin this strategy, enabling the organization to embed asset management as a core business capability that delivers measurable EBITDA improvements alongside operational stability and risk reduction.

Presentation content

• Transition from reactive to proactive asset management maturity
• Linking reliability performance to EBITDA and operational risk
• Leveraging digital tools for predictive and condition-based maintenance
• Developing and executing a structured reliability improvement program
• Building organizational capability and a reliability-focused culture
• Integrating asset condition management with maintenance execution

Practical takeaways

Participants learn how to develop and implement a comprehensive asset management strategy that directly connects reliability improvements with EBITDA impact. They gain insight into digital simulation of key performance indicators for forward-looking decision-making, establishing structured reliability programs, and fostering organizational capability and culture aligned with asset performance goals. The session offers practical understanding of balancing cost optimization with long-term asset integrity while advancing from reactive maintenance towards risk-based and predictive maintenance practices.

Aging chemical production assets, often operating beyond their original 20 to 30-year design life, pose increasing risks due to the deterioration of critical components like coatings, electrical systems, and internal parts. For industrial sites such as those managed by Ineos Styrolution, effectively assessing and managing these risks is essential to maintaining reliability and minimizing unplanned downtime. Understanding the true health status of aging equipment enables more informed decision-making about maintenance priorities and investment strategies.

This session presents a practical, structured framework used at Ineos to assess asset health, interpret diagnostic outcomes, and benchmark results across multiple production sites. The approach translates assessments into actionable maintenance and asset management decisions, helping to prioritize interventions that reduce failure risks and support operational excellence in aging facilities.

Presentation content

• Framework for assessing health of aging chemical assets
• Interpreting and benchmarking asset health assessment results
• Identifying risk exposure related to component deterioration
• Translating assessment outcomes into maintenance actions
• Prioritizing and managing interventions to maximize impact
• Leveraging assessments as decision-support tools for reliability

Practical takeaways

Participants learn to analyze asset health assessment data to identify reliability risks in aging equipment and translate these insights into prioritized maintenance and investment decisions. The session demonstrates how structured assessment processes support risk management, improve reliability, and guide maintenance strategies tailored to assets operating beyond their design life. Attendees gain practical understanding of benchmarking across sites and managing actions to optimize asset performance in aging chemical production environments.

Industrial organisations managing complex asset lifecycles face the challenge of integrating vast operational data with efficient decision-making processes. In environments such as utilities and nuclear power, closing the gap between insight generation and maintenance execution is crucial to enhance performance and ensure sustainability. Traditional asset management approaches often struggle to link condition monitoring, performance analytics, and maintenance workflows into a seamless, adaptive process.

This session highlights the deployment of AI-driven Intelligent Asset Management solutions to create a continuous cycle of insight and action. By connecting each decision to the next, the approach enables more adaptive and self-optimising asset operations. These capabilities support maintaining asset health through timely, data-informed interventions while addressing evolving operational demands and sustainability goals.

Presentation content

• Integration of AI in asset lifecycle decision-making
• Creating continuous feedback loops for operational learning
• Linking asset performance insights with maintenance execution
• Implementing self-optimising maintenance strategies
• Enabling sustainable and adaptive asset management practices

Practical takeaways

Participants learn how AI can be applied to connect data-driven insights with maintenance actions, establishing a closed-loop asset management process. The session provides an understanding of the technical and organisational steps required to build an adaptive, self-optimising operational framework. Attendees gain insights into leveraging intelligent systems to enhance decision quality, balance operational sustainability, and advance maintenance execution within complex industrial environments.

When Christian Texter became plant manager at Liqui Moly in 2022, the maintenance team operated reactively, managing breakdowns under intense pressure with scattered documentation and disorganized spare parts. This environment led to unplanned downtime, slow fault diagnosis, and the risk of losing critical expert knowledge as experienced technicians approached retirement.

Liqui Moly addressed these challenges through a phased digitalisation of their maintenance workflows, using remberg maintenance software without halting production. Key steps included cleaning asset master data and introducing QR codes, digitalising maintenance scheduling and workflows, cataloguing thousands of spare parts, and deploying an AI copilot that reduced fault information retrieval from 15 minutes to 15 seconds. This approach balanced the need to increase equipment availability under staffing constraints with maintaining uninterrupted plant operations.

The case illustrates how structured digitalisation combined with AI support can significantly improve maintenance responsiveness and asset availability while setting the stage for advanced predictive maintenance using live sensor data.

Presentation content

• Phased digitalisation from master data cleanup to AI copilot
• Implementing asset QR codes for streamlined data access
• Digitalising workflows, work orders, and spare parts management
• AI copilot reducing fault diagnosis time to 15 seconds
• Achieving 20% higher equipment availability and 70 extra production days annually
• Maintaining uninterrupted production during digital transformation
• Preparing for predictive maintenance with live sensor integration

Practical takeaways

Participants learn how a stepwise maintenance digitalisation delivers tangible improvements without disrupting production, why clean master data is fundamental to AI success, and how AI can reduce fault diagnosis time to enhance equipment availability. The session offers insights into transitioning from reactive to predictive maintenance by integrating AI with live sensor data and automating maintenance planning, providing practical guidance applicable to other industrial settings facing similar challenges.

Maintenance teams in complex industrial environments face challenges due to fragmented information sources, growing system complexity, and the gradual loss of expert knowledge. Technicians often juggle multiple tools, documents, and data systems to conduct diagnostics and record their work, which leads to inefficiencies and variable quality in maintenance execution.

To address these issues, the presented case integrates automated generation of inspection and maintenance reports with immediate access to technical documentation. This approach structures field interventions, supports decision-making, and enhances knowledge transfer across maintenance teams. It highlights how these solutions were embedded within existing workflows, their adoption by field personnel, and the resulting improvements in intervention consistency and report quality.

The session further examines practical challenges such as system integration and user acceptance, providing insights and recommendations for organizations seeking to deploy similar solutions to improve standardization and reduce dependency on individual expertise.

Presentation content

• Challenges of fragmented data and expert knowledge loss
• Industrial use case context and initial maintenance pain points
• Implementation of automated inspection and maintenance reporting
• Integration of instant technical documentation access in workflows
• Adoption by technicians and change management strategies
• Impact on intervention consistency and quality of reporting
• Lessons learned and deployment recommendations

Practical takeaways

Participants learn how combining automated reporting with instant technical documentation access can organize maintenance activities more effectively. The session provides insight into key factors for successful implementation of AI copilots in real-world settings, emphasizing adoption challenges and strategies. Attendees gain understanding of ways to improve knowledge transfer, reduce reliance on expert individuals, and ensure consistent, high-quality maintenance execution across teams.

Industrial asset management is evolving rapidly as organisations seek to move beyond traditional predictive maintenance towards more autonomous operational models. This transition addresses the challenge of effectively managing complex assets by leveraging the increased data availability provided through sensors, digital twins and advanced analytics. The tension lies in integrating AI-driven insights into existing maintenance and asset management workflows while preserving engineering expertise and ensuring reliability.

Enging - Make Solutions explores how combining artificial intelligence and predictive analytics can drive this evolution. Their approach focuses on enabling organisations to use data and models not only to predict failures but to support autonomous decision-making that enhances asset performance, sustainability and operational excellence. This workshop presents an interactive platform to consider challenges and practical approaches for implementing AI and autonomous systems in asset management environments.

Presentation content

• Overview of AI and digital twins in asset performance
• Transitioning from predictive maintenance to autonomous operations
• Integration of AI insights into maintenance workflows
• Data challenges in industrial asset management
• Addressing organisational and technical implementation barriers
• Future outlook for autonomous asset management

Practical takeaways

Participants learn how AI and digital twins can extend predictive maintenance towards autonomous asset operations. The session provides insights on integrating intelligent analytics with existing asset management systems while balancing AI support and human engineering judgement. Attendees gain an understanding of operational and organisational challenges involved, practical steps for implementation, and considerations for scaling autonomous asset performance strategies.

For professionals with maintenance, reliability or asset management responsibility across multiple sites. Participation is subject to approval. Participation details

Operating multiple sites often leads to diverse maintenance practices influenced by site-specific cultures, asset types, and maturity levels. This diversity can hinder consistency, efficiency, and the ability to apply lessons learned across the organisation. Establishing a uniform maintenance methodology addresses these challenges by standardising processes, improving comparability of performance data, and facilitating better allocation of resources.

Achieving a coherent approach across sites requires balancing corporate standards with local operational realities, ensuring that the methodology is adaptable yet maintains core principles. This session explores the organisational and technical factors involved in developing and implementing a standardised maintenance framework that supports asset reliability and operational excellence across diverse locations.

The methodology focuses on harmonising maintenance strategies, workflow integration, and consistent performance measurement, enabling more effective collaboration between sites and central functions. This approach helps maintenance and asset performance professionals to align their efforts and leverage shared insights for continuous improvement.

Presentation content

• Key challenges in multi-site maintenance standardisation
• Developing core maintenance methodology principles
• Aligning site-specific practices with corporate standards
• Integrating maintenance workflows across locations
• Establishing consistent performance indicators and reporting
• Addressing organisational change and training needs
• Leveraging data to monitor and improve maintenance practices

Practical takeaways

Participants learn how to create and implement a uniform maintenance methodology that balances standardisation with site-specific conditions. They understand prerequisites for successful roll-out, including organisational alignment and training. The session provides insights into harmonising workflows and performance metrics, enabling clearer decision-making and enhanced collaboration across multiple sites. Attendees gain practical knowledge on overcoming common barriers and applying best practices to achieve operational consistency and improved asset reliability.

Mars Snacking has been advancing its predictive maintenance strategy since 2006, evolving from traditional time-based and periodic condition monitoring toward automated, continuous asset monitoring. The initial PdM program addressed the limitations of scheduled inspections by introducing vibration analysis at fixed intervals, but rapid failure developments often escaped detection between measurements. This created significant blind spots along the P-F curve that risked unplanned downtime and operational disruption.

To overcome these challenges, Mars Snacking is transitioning to a digital PdM approach that automates data collection and increases monitoring frequency through continuous condition monitoring combined with advanced analytics. This enhanced approach enables earlier detection of emerging failure modes, extending maintenance planning windows and improving proactive intervention. Through collaboration and case studies, the session highlights how the integration of automated sensor data and analytic tools supports operational risk reduction and more informed maintenance decision-making in a complex manufacturing environment.

Presentation content

• Evolution from periodic to continuous predictive maintenance
• Limitations of manual condition monitoring and inspection intervals
• Implementing automated data acquisition and sensor integration
• Applying advanced analytics for early failure mode identification
• Extending maintenance response time via continuous monitoring
• Impact on operational risk and maintenance planning
• Industrial case study of Mars Snacking’s PdM program

Practical takeaways

Participants learn how continuous, automated condition monitoring closes gaps inherent in periodic inspections and provides earlier visibility of developing asset issues. The session demonstrates how increasing data frequency along the P-F curve allows maintenance teams to plan interventions with greater lead time, reducing operational risk. Attendees gain insight into practical implementation challenges, the role of advanced analytics in predictive maintenance, and how these digital evolutions enhance decision-making and asset performance in a manufacturing setting.

Aquafin manages a broad range of machinery and equipment in the construction of new wastewater treatment facilities. Each installed asset requires accurate recording of critical technical parameters such as flow rates, electrical specifications, and maintenance intervals, which are currently extracted manually from complex PDF technical manuals. This manual process is time-consuming, inefficient, and prone to human error, especially given the variety and volume of technical data involved in large projects.

The challenge significantly impacts operational reliability by introducing data inaccuracies and delays in asset registration within Aquafin’s systems. To address this, Aquafin is exploring automated workflows that leverage AI-driven extraction techniques to transform unstructured PDF data into high-quality, structured asset data. This approach aims to reduce lead times and enhance data integrity, supporting more reliable asset management and operational decision-making.

Presentation content

• Managing diverse machinery during facility construction
• Critical technical data requirements for asset records
• Limitations and risks of manual data extraction from PDFs
• Automation of parameter extraction from unstructured documents
• Reducing human error and improving data accuracy
• Shortening project lead times through workflow transformation
• Integrating structured data into asset management systems

Practical takeaways

Participants learn how AI-driven extraction can replace manual data entry to improve accuracy and efficiency when recording complex technical parameters from asset documentation. They gain insight into identifying workflow bottlenecks, implementing automation technologies suitable for large-scale asset data management, and ensuring data quality that supports reliable operational processes. The session also highlights practical considerations for integrating automated data workflows within existing asset management systems and reducing the risks associated with human error.

Heineken’s C15 production line faced the common challenge of moving AI and prescriptive maintenance initiatives beyond isolated pilots to achieve tangible operational improvements. Identifying the right use case within a complex production environment is difficult, as is validating anomaly detection in real-world conditions and translating technical insights into convincing business cases. The tension between advanced AI techniques and established maintenance practices requires careful alignment of technology with existing workflows and human expertise.

To address these challenges, the project applied anomaly detection to operational data streams including current, voltage, and vibration. The approach systematically defined the problem, set up and validated a proof of concept (POC), and linked detected anomalies to preventive maintenance actions. The case demonstrates practical methods to build a credible business case with measurable results and shows how to scale and embed prescriptive maintenance in daily operations through process integration, training, and risk management tools like FMEA.

Presentation content

• Selecting a high-impact use case on the C15 production line
• Setting up and validating anomaly detection with operational data
• Translating anomalies into preventive and prescriptive maintenance actions
• Developing a business case with downtime reduction and cost benefits
• Creating an implementation roadmap for scaling across production lines
• Embedding solutions through process integration, training, and FMEA

Practical takeaways

Participants learn how to identify appropriate starting points for AI-driven prescriptive maintenance and build a validated POC that produces measurable operational benefits. The session highlights translating technical anomaly detection results into actionable maintenance procedures and a credible business case. It also explains key factors for scaling solutions beyond pilots, including embedding them into existing processes, training teams, and managing risks through established frameworks such as FMEA.

Industrial organisations face increasing pressure to optimise maintenance strategies amid growing asset complexity and digital transformation. The adoption of smart maintenance applications—leveraging IoT, data analytics, and predictive tools—presents opportunities to enhance operational efficiency, asset availability, and failure prevention. Yet, understanding how these technologies are integrated and their evolving market dynamics remains a challenge for maintenance and asset management professionals.

IoT Analytics provides a detailed analysis based on the latest market research, revealing how different industries adopt smart maintenance solutions and the emerging trends shaping this sector. This insight enables organisations to benchmark their approaches against industry developments and anticipate future directions in asset performance enhancement through data-driven maintenance strategies.

Presentation content

• Market research insights on smart maintenance adoption
• Emerging trends in maintenance technology implementation
• Forecasting developments in smart maintenance solutions
• Implications of digital transformation on maintenance strategies

Practical takeaways

Participants learn to interpret current market data on smart maintenance adoption and identify how emerging trends influence asset performance and operational efficiency. They gain a clearer understanding of the evolving landscape of maintenance technologies, enabling more informed decisions on integrating data-driven approaches within their asset management and reliability programs.

Asset owners face growing pressure to enhance equipment performance, reliability and output in increasingly complex manufacturing environments. Although Overall Equipment Effectiveness (OEE) is widely used to measure equipment productivity quantitatively, it often overlooks valuable qualitative insights generated daily by operators, technicians and engineers on the shop floor. This information typically remains fragmented across emails, paper logbooks and informal conversations, limiting root cause analysis, team alignment and timely issue escalation.

To address this challenge, a manufacturing ecosystem can integrate MES data with active shop floor dialogues, involving equipment owners, technicians, engineers and leadership. This approach transforms OEE from a static management KPI into a dynamic operational tool that fosters collaboration, innovation and bottom-up engagement. Operational excellence acts as an orchestrator, streamlining communication, enabling insights to flow back to end users and facilitating smooth escalation into shift handovers and daily meetings.

Presented through a practical case study with Alpro, this session demonstrates how connecting data, people and workflows in real time improves factory performance and the quality of working life on the shop floor.

Presentation content

• Limitations of OEE as solely a quantitative management metric
• Capturing qualitative shop floor knowledge alongside MES data
• Replacing fragmented communication with a connected operational dialogue
• Roles of equipment owners, technicians, engineers and leadership in shared improvements
• Designing a manufacturing ecosystem to connect data, people and workflows
• Using operational excellence to link performance measurement and daily problem-solving
• Feeding insights back to end users and escalating issues during shift handovers

Practical takeaways

Participants learn how to expand OEE beyond quantitative measurement to include qualitative shop floor input, enabling a comprehensive view of performance. They gain insight into integrating frontline team communications with MES data within a manufacturing ecosystem, fostering collaboration and bottom-up engagement. The session clarifies how to replace disconnected communication channels with aligned operational dialogues that improve issue escalation and daily workflows. Attendees discover how this methodology enhances factory output, reliability and workforce collaboration by connecting data, people and operational processes.

ATEX inspections during commissioning are critical for maintaining compliance and operational safety in hazardous environments. At Ebert Hera, these inspections traditionally rely on paper or Excel-based reporting, resulting in time-consuming processes, inconsistent documentation, and a higher risk of overlooking crucial details. These challenges hinder effective communication and decision-making across maintenance and compliance teams.

To address this, Ebert Hera developed a prototype AI-assisted inspection application that replaces manual forms with a guided digital workflow. The app supports inspectors in the field by ensuring completeness and consistency, while generating standardized reports that simplify review and follow-up actions. The system operates fully on-premises for data confidentiality and is built on a custom AI infrastructure specifically trained on ATEX-related requirements, enabling real-time interpretation and risk identification. This approach balances the need for technological assistance with the rigour required for safety-critical inspections.

Presentation content

• Limitations of manual ATEX inspection reporting
• Development of AI-assisted digital inspection app
• Structured workflows for field inspection guidance
• On-premises AI infrastructure for data security
• AI support in requirements interpretation and risk detection
• Generation of standardized and actionable reports

Practical takeaways

Participants learn how integrating AI into ATEX inspection workflows can reduce inspection complexity and time, improve reporting accuracy and consistency, and enhance communication among stakeholders. The session highlights the implementation of an on-premises AI solution that maintains data confidentiality while supporting inspectors with real-time guidance and risk recognition. Attendees gain insight into practical conditions for deploying AI in safety-critical environments and how such tools can aid compliance and operational safety management.

Process industries extensively deploy predictive maintenance technologies, using sensors, vibration monitoring, thermal analytics, and AI platforms to detect anomalies and forecast equipment failures. Despite these advances, a critical challenge remains in converting these digital diagnostics into effective and safe maintenance actions in the field.

Technicians often face delays locating relevant documentation, validating procedures, and seeking expert advice, which is exacerbated by the retirement of experienced personnel. This creates an operational gap between AI-driven insights and hands-on execution, known as the 'last mile of predictive maintenance.' Chenext Technologies addresses this gap by integrating immersive Mixed Reality (XR) as a human 3D-interface, delivering interactive, contextual maintenance guidance directly linked to the equipment.

This approach connects AI diagnostics with technician actions, aiming to reduce repair time, errors, and reliance on senior experts while supporting knowledge transfer during workforce transitions.

Presentation content

• Challenges bridging AI diagnostics and maintenance execution
• Concept of the last mile in predictive maintenance
• Prescriptive Maintenance Execution Platform by Chenext Technologies
• Immersive XR for interactive 3D maintenance guidance
• Integration of XR with sensor and AI monitoring systems
• Enhancing maintenance accuracy, safety, and knowledge retention
• Supporting technician performance amid workforce changes

Practical takeaways

Participants learn why predictive maintenance must be complemented by effective execution tools and how immersive XR technologies serve as an essential interface linking AI diagnostics with maintenance tasks. The session explains how XR-driven prescriptive workflows can enable faster, safer, and more accurate interventions, reduce dependence on retiring experts, and improve knowledge management. Attendees gain insights into practical integration with monitoring systems and how such approaches can address the persistent execution challenges in asset performance management.

Industrial asset owners face increasing challenges in maintaining high-quality inspections amid resource constraints and rising safety and compliance demands. Traditional inspection processes are labour-intensive and often struggle to keep pace with growing workloads, while cautious adoption of AI tools reflects concerns about losing control over critical safety assessments.

Airvision and Smart AIS address this by integrating a human in the loop AI workflow that accelerates corrosion and insulation damage detection without compromising control or compliance. Certified inspectors actively train, guide, and validate every AI-generated finding, ensuring expert judgement remains central. Adjustable sensitivity settings and transparent validation processes reduce false positives, shorten inspection cycles, and maintain trust while delivering evidence-based reports rapidly. This method supports asset owners in managing risks effectively while augmenting inspection resources with AI assistance rather than replacement.

Presentation content

• Industry caution and challenges in applying AI to inspections
• Combining drones with panoramic 3D laser scanners for data capture
• Leveraging certified inspectors to train and validate AI models
• Implementing a human in the loop workflow with inspector control
• Using adjustable sensitivity settings to optimize detection
• Reducing false positives through continuous expert feedback
• Supporting faster, evidence-based inspection reporting and decisions

Practical takeaways

Participants learn how integrating drones and panoramic imaging with human-guided AI accelerates corrosion and insulation damage detection while ensuring compliance and inspector control. They gain insight into how expert feedback trains AI models, how adjustable sensitivity settings affect detection outcomes, and how this approach helps manage resource shortages. Attendees understand practical implementation details, including workflow integration and maintaining trust in AI-augmented inspections, applicable to various asset-intensive industries.