Fault diagnosis of hydroelectric units based on GASF and parallel CNN-GRU-MSA

Abstract

Abstract Diagnosing the vibration signals of hydropower units is crucial for safe and stable operation. This paper proposes a fault diagnosis method for hydropower units based on Gramian Angular Summation Fields (GASF) and parallel convolutional neural networks-gated recurrent unit-multi-headed self-attention (CNN-GRU-MSA). The original data forms a double branch, and the first branch selects the original timing signal for feature extraction using GRU. The second branch converts the timing signal into a 2D image using GASF for feature extraction using CNN, and the merged signal is enhanced with MSA for feature values. The experimental results show that the accuracy of the method reaches 97.2%. In order to explore the generalization and practicability of the proposed model, the public dataset of Jiangnan University is introduced for re-analysis. The diagnostic result of 600 rpm is 98.5%, and the diagnostic result of 800 rpm and 1000 rpm is 100%, significantly better than the other comparative models. This study can be valuable to the hydropower unit’s fault diagnosis methods.