Power equipment partial discharge classification method based on multi-channel sound signal space-time correlation analysis

The invention discloses a power equipment partial discharge classification method based on multi-channel sound signal space-time correlation analysis, which classifies power equipment partial discharge types by respectively mining the space correlation and the time correlation of multi-channel sound signals. The invention provides a one-dimensional convolutional neural network for space-time correlation mining, which comprises the following steps: firstly, carrying out space correlation mining on multichannel sound signals, obtaining space weight information and carrying out space correlation weighting on multichannel sound signal features; then performing time correlation mining on each channel signal on the basis so as to obtain time weight information and performing time correlation weighting on each channel sound signal; and finally, carrying out further feature extraction and partial discharge type classification on the multi-channel sound signals subjected to space and time correlation mining. According