Gas-insulated switch-gear mechanical fault detection based on acoustic feature analysis using a multi-state pre-trained neural network

Zhihua Wang, Zipeng Zhang, Yuying Shao, Kun Qian*, Houguang Liu*, Bin Hu, Björn W. Schuller

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

摘要

The acoustic-based approach is a prevalent way for non-contact fault diagnosis on gas-insulated switch-gear (GIS). GIS always works under different voltages causing great diversity in acoustic frequency. However, based on the frequency principle, neural networks always focus on a specific frequency, which challenges robust fault detection on GIS. This paper introduces a novel multi-stage training method to improve the robustness of fault detection on GIS. The proposed method consists of three components: a multi-channel based frequency regressor (MCBFR), an audio spectrogram transformer auto-encoder (AST-AE), and a feature interaction module (FIM). MCBFR and AST-AE are optimised to extract specific features from acoustics during the pre-training stage. The FIM fuses components extracted by MCBFR and AST when training the model that can indicate the final result. Also, we apply a multi-stage training strategy during the training stage to reduce the cost of potential model retraining. The efficacy of the proposed method was validated using experimental data from a real GIS, and it shows competitive performance in fault detection compared to existing methods.

源语言英语
文章编号076121
期刊Measurement Science and Technology
35
7
DOI
出版状态已出版 - 7月 2024

指纹

探究 'Gas-insulated switch-gear mechanical fault detection based on acoustic feature analysis using a multi-state pre-trained neural network' 的科研主题。它们共同构成独一无二的指纹。

引用此

Wang, Z., Zhang, Z., Shao, Y., Qian, K., Liu, H., Hu, B., & Schuller, B. W. (2024). Gas-insulated switch-gear mechanical fault detection based on acoustic feature analysis using a multi-state pre-trained neural network. Measurement Science and Technology, 35(7), 文章 076121. https://doi.org/10.1088/1361-6501/ad3d78