- Research area
Operations maintenance and human factors
University of Sheffield
- Research project
Advance condition monitoring solutions for offshore wind generators
- Lead supervisor
- PhD Student
- Supervisory Team
Dr Xiao Chen (Department of Electronic and Electrical Engineering, University of Sheffield)
Reliability and availability are two key requirements in offshore wind generators where a fault can result in catastrophic failures. Furthermore, any downtime caused by faults or maintenance results in significant loss of revenues. With the aim of reducing faults and increasing availability, there has been a recent upsurge of interest in real-time monitoring of machine health during its lifetime. The aims are not only to avoid the risk of catastrophic failures but also to replace costly periodic routine maintenance with condition-based maintenance to be performed only when the remaining useful life (RUL) decreases below a predefined threshold.
Industrial surveys have identified degradation in the electrical insulation in the generators and degradation in the bearings as the two most common causes of failure in high power electrical machines of the type used in offshore wind generators.
This project will investigate novel methodologies for a holistic solution to condition monitoring and prognosis of the remaining life of electrical generators and their bearings.
Based on advanced signal processing methods and emerging methodologies for sensor fusion and machine learning, the project will develop novel detection methods for bearings and electrical faults that combine the available mechanical and electrical signals. It is expected that the approach developed will result in significant improvement in sensitivity to the detection of progressive degradation and incipient faults.