MS#06.8 Next-Generation Condition Monitoring and Maintenance Decision-Making: A Multi-Scale Digital Twin Perspective
M. LI¹, M. GALAGEDARAGE DON², X. JIANG³, M. NARAYANA⁴, J. CARROLL⁵, T. WANASINGHE⁶
¹ The University of Tokyo|² Aalto University, Finland|³ Delft University of Technology|⁴ University of Moratuwa, Sri Lanka|⁵ University of Strathclyde|⁶ Memorial University of Newfoundland, Canada
Reliability, monitoring and sensing, O&M
Digital Twin (DT) technology is emerging as a powerful tool for enhancing condition monitoring capabilities and maintenance decision-making of wind turbines. DTs can be characterised across various abstractions, including nanoscopic, microscopic, macroscopic, component, asset, system, and process levels. This mini-symposium brings together multidisciplinary researchers, including but not limited to computer, electrical, materials, and mechanical engineers, artificial intelligence (AI) experts, and data scientists, to explore DTs at various scales and discuss their role in condition monitoring and maintenance decision making in the wind energy sector.
The finer-scale DTs, at the nano and micro levels, offer improved accuracy in predicting the material behaviour of wind turbines. By modelling the wear, fatigue, and microstructural changes in critical components like blades and bearings, these DTs enable early detection of potential failures. Real-time data from embedded nanosensors and analytics enhances maintenance decision-making, reducing downtime and operational risks. Moreover, these DTs allow engineers to optimize material selection and component design, enhancing wind turbines' efficiency, durability, and environmental compatibility.
At the component and asset levels, DTs deliver insights into critical parts such as blades, gearboxes, and generator windings. They monitor temperature, torque, vibrations, and wear, enabling predictive maintenance that extends the lifespan of these components. By simulating a series of what-if scenarios on different environmental and operational conditions, DTs can identify potential performance issues before they lead to downtime, enhancing overall reliability, availability, and efficiency.
At the system level, DTs provide a comprehensive view of an entire wind turbine. They integrate data from various components, such as blades, gearboxes, and generators, to frequently monitor overall performance. By analysing factors like energy output, operational efficiency, and environmental conditions, DTs enable operators to optimize turbine performance and adjust settings proactively. This holistic approach helps identify potential issues before they lead to failures, ensuring maximum uptime and efficiency.
At the process level, DTs may represent an entire wind farm, enabling comprehensive monitoring and optimization of all operational aspects. By integrating data from multiple wind turbines, DTs provide insights into collective performance metrics such as energy production, operational efficiency, and resource allocation.
Sample topics of interest include, but are not limited to:
- Digital twin-enabled operation and maintenance (multi-scale)
- Innovative designs for real-time health monitoring platforms (multi-scale)
- Artificial intelligence approaches for fault detection, diagnosis, and prognosis
- Condition-based/predictive/prescriptive maintenance decision-making
- Reliability and risk analysis models integrating digital techniques