High-voltage cable partial discharge mode identification method based on particle swarm algorithm and DBN

The invention provides a high-voltage cable partial discharge mode identification method based on a particle swarm algorithm and a DBN. The method comprises the following steps: S1, obtaining a high-voltage cable partial discharge pulse signal, and carrying out the preprocessing; S2, dividing the signal into a training sample and a test sample; S3, establishing a DBN, and optimizing the initial weight of the DBN by adopting a particle swarm algorithm to obtain an optimal initial weight; S4, inputting a training sample to perform offline training on the DBN to obtain a trained DBN model; S5, inputting a test sample into the trained DBN model for testing to obtain an identification result of high-voltage cable multi-source partial discharge. According to the high-voltage cable partial discharge mode identification method based on the particle swarm algorithm and the DBN, the identification precision and the identification accuracy of the partial discharge mode are effectively improved byutilizing the good featu