Convolutional neural network framework for wind turbine electromechanical fault detection

Stone, Emilie; Giani, Stefano; Zappalá, Donatella; Crabtree, Christopher

Abstract

Effective and timely health monitoring of wind turbine gearboxes and generators is essential to reduce the costs of operations and maintenance activities, especially offshore. This paper presents a scalable and lightweight Convolutional Neural Network (CNN) framework using high-dimensional raw condition monitoring data for the automatic detection of multiple wind turbine electromechanical faults. The proposed approach leverages the potential of combining information from a variety of signals to learn features and to discriminate the types of fault and their severity. As a result of the CNN layers used to extract features from the signals, this architecture works in the time domain and can digest high-resolution multi-sensor data streams in realtime. To overcome the inherent black-box nature of AI models, this research proposes two interpretability techniques, multidimensional scaling and layer-wise relevance propagation, to analyse the proposed model’s inner-working and identify the signal features relevant for fault classification. Experimental results show high performance and classification accuracies above 99.9% for all fault cases tested, demonstrating the efficacy of the proposed fault detection system.

Citation

Stone, E., Giani, S., Zappalá, D., & Crabtree, C. (2023). Convolutional neural network framework for wind turbine electromechanical fault detection. Wind Energy, 26(10), 1082 - 1097. https://doi.org/10.1002/we.2857

• Journal Article Type: Article
• Acceptance Date: Jul 6, 2023
• Online Publication Date: Aug 7, 2023
• Publication Date: 2023-10
• Deposit Date: Jul 7, 2023
• Publicly Available Date: Aug 22, 2023
• Journal: Wind Energy
• Print ISSN: 1095-4244
• Electronic ISSN: 1099-1824
• Publisher: Wiley Open Access
• Peer Reviewed: Peer Reviewed
• Volume: 26
• Issue: 10
• Pages: 1082 - 1097
• DOI: https://doi.org/10.1002/we.2857
• Public URL: https://durham-repository.worktribe.com/output/1170194
• Publisher URL: https://onlinelibrary.wiley.com/journal/10991824