Gas-insulated switch-gear mechanical fault detection based on acoustic using feature fused neural network

The acoustic-based method is a prevalent way for non-contact fault diagnosis on gas-insulated switchgear. Gas-insulated switchgear always work under different voltages causing great diversity in acoustic frequency, which challenges robust fault detection. This paper proposed a novel feature-fused method to improve the robustness of fault detection on gas-insulated switchgear. The proposed method consists of four components: wave reduction module, spectrogram reduction module, fusion module and classifier. Wave reduction module extracts operating voltage information from acoustic emissions in the gas-insulated switchgear; spectrogram reduction module uses auto-encoder training schedule for feature extraction on spectrogram; fusion module fuses extracted features; classifier makes final classification. Also, we proposed an objective function for thoroughly utilizing spectrogram information. The efficacy of the proposed method was validated using experimental data from a real gas-insulated switchgear, and it shows competitive performance in fault detection compared to existing methods.

Recommended citation: Zhang, Z., Liu, H., Yuan, G., Yang, J., Liu, S., Shao, Y., & Zhang, Y. (2024). Gas-insulated switch-gear mechanical fault detection based on acoustic using feature fused neural network. Electric Power Systems Research, 230, 110226.
Download Paper | Download Slides | Download Bibtex