An EHV Transformer Fault Diagnosis Method Based on Acoustic Perception and Sparse Autoencoder-BNCNN

Abstract

The EHV transformer is one of the core transmission equipment of China’s EHV/UHV transmission system, and its reliability directly affects the operational stability of the power grid. In the long-term operation process, affected by sudden short-circuit, resonance, and aging, it will produce faults such as loose winding, loose iron core, inverted discharge, and shim block shedding. Most of the methods for transformer fault diagnosis need off-line monitoring and cause some damage to transformer equipment. At present, the use of transformer acoustic signal for diagnosis and identification is in the initial stage, and there is still room for improvement in the accuracy of fault diagnosis, and how to classify the unbalanced data samples also deserves attention. Therefore, an EHV transformer fault diagnosis method based on acoustic perception and sparse autoencoder-BNCNN is proposed in this paper. Firstly, the sparse autoencoder is trained to ensure the processing ability of the network on imbalanced data. Then, the high-step CNN network is optimized using the BN layer, the data is fed into the improved CNN network for feature extraction, and the classifier outputs the fault diagnosis results. Finally, the transformer acoustic data are processed, and the dataset is formed to evaluate the performance of the proposed method. The experimental results show that the proposed method not only improves the accuracy substantially compared with other methods but also has the ability to handle imbalanced data.