Wind Turbine Gearbox Fault Detection Based on Sparse Filtering and Graph Neural Networks
This addresses gearbox failures in wind turbines, which cause high downtime and costs, but the approach is incremental as it applies existing GNN and sparse filtering methods to this specific domain.
The paper tackles wind turbine gearbox fault detection by combining graph neural networks (GNNs) with sparse filtering on high-frequency vibration data, achieving verification on practical experimental data.
The wind energy industry has been experiencing tremendous growth and confronting the failures of wind turbine components. Wind turbine gearbox malfunctions are particularly prevalent and lead to the most prolonged downtime and highest cost. This paper presents a data-driven gearbox fault detection algorithm base on high frequency vibration data using graph neural network (GNN) models and sparse filtering (SF). The approach can take advantage of the comprehensive data sources and the complicated sensing networks. The GNN models, including basic graph neural networks, gated graph neural networks, and gated graph sequential neural networks, are used to detect gearbox condition from knowledge-based graphs formed using wind turbine information. Sparse filtering is used as an unsupervised feature learning method to accelerate the training of the GNN models. The effectiveness of the proposed method was verified on practical experimental data.