基于PSA的CNN电缆接头局部放电识别应用OA

At present,the partial discharge identification of power cable connectors requires to measure voltage signals,and there are problems such as insufficient generalization ability and low identification accuracy.Based on this,a convolutional neu-ral network(CNN)cable connector partial discharge defect identification algorithm based on pulse sequence analysis(PSA)is proposed.Three partial discharge models of power cable connectors are designed,and a partial discharge experimental platform is built.The data are processed,and the phase resolved partial discharge(PRPD)spectrum and PSA image of the partial dis-charge of cable connector defects are obtained.The PSA image helps to improve the identification accuracy.The CNN is used to identify the partial discharge of the cable connector defects,and the algorithm is verified through practical examples.The re-sults show that in the absence of partial discharge voltage signals,the identification accuracy rate of the proposed algorithm is 95.3％,and the identification accuracy rate of the PRPD-based CNN algorithm is 90.6％,proving the feasibility and effective-ness of the proposed method.