Method of inter-turn fault detection for next-generation smart transformers based on deep learning algorithm

• Published in: High voltage 2019-12, Vol.4 (4), p.282-291
• Main Authors: Duan, Lian, Hu, Jun, Zhao, Gen, Chen, Kunjin, Wang, Shan X, He, Jinliang
• Format: Article
• Language: English
• Subjects: 12-channel data; channel selection; comprehensive fault waveforms; current waveforms; deep learning algorithm; deep learning framework; fault diagnosis; fault tags; fault type; fault waveforms; feature extraction; feature selection; input signal; inter-turn fault detection; inter-turn fault diagnosis method; learning (artificial intelligence); learning model; MATLAB/Simulink; multichannel waveforms; next-generation smart transformers; power engineering computing; power transformers; secondary voltage; signal classification; signal sampling; signal sampling frequency; sparse auto-encoder; Special Issue: Advanced Sensing Technology for High Voltage Applications; time-domain monitoring signals; transformer fault diagnosis; two-dimension data matrix
• ISSN: 2397-7264; 2397-7264
• DOI: 10.1049/hve.2019.0067

In this study, an inter-turn fault diagnosis method is proposed based on deep learning algorithm. 12-channel data is obtained in MATLAB/Simulink as the time-domain monitoring signals and labelled with 16 different fault tags, including both primary and secondary voltage and current waveforms. An auto-encoder is presented to classify the fault type of the abundant and comprehensive fault waveforms. The overall waveforms compose a two-dimension data matrix and the auto-encoder is trained to extract the features in the multi-channel waveforms. The selected features are convoluted with the original data, generating a one-dimensional vector as the input to the softmax classifier. Variables such as type, activation function and depth of auto-encoder, sparsity of sparse auto-encoder, number of features and pooling strategies are studied, which gives an intuitive process to train a proper learning model. The overall recognition accuracy reaches 99.5%. Signal characteristics such as channel selection, time span of the input signal and signal sampling frequency are studied to find the best solution for the inter-turn fault detection of the three-phase transformer. The proposed method under deep learning framework increases the accuracy and robustness in transformer fault diagnosis, indicating its potential and prospect in the next-generation smart transformers.