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

Abstract

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.

Keywords

• learning (artificial intelligence)
• power transformers
• fault diagnosis
• feature extraction
• signal sampling
• power engineering computing
• signal classification
• feature selection
• comprehensive fault waveforms
• two-dimension data matrix
• multichannel waveforms
• sparse auto-encoder
• channel selection
• input signal
• signal sampling frequency
• inter-turn fault detection
• deep learning framework
• transformer fault diagnosis
• next-generation smart transformers
• deep learning algorithm
• inter-turn fault diagnosis method
• 12-channel data
• time-domain monitoring signals
• secondary voltage
• current waveforms
• fault type
• fault waveforms
• learning model
• fault tags
• matlab/simulink