Research on Double-Deck Traceability Identification Method of Commutation Failure in HVDC System

Abstract

In AC/DC hybrid power system, AC system failures and commutation valve trigger pulse disorder will lead to commutation failure, which may lead to DC voltage fluctuations, power transmission interruption and other serious consequences. In order to accurately and effectively identify the specific causes of commutation failures, a double deck traceability identification method is proposed in this paper. The surface identification based on wavelet entropy and affinity propagation (AP) algorithm can distinguish internal and external faults. The deep identification uses convolution neural network which can further lock the specific cause of commutation failures. In this paper, 1) the various factors leading to commutation failures are analyzed; 2) the fault feature space consists of the wavelet analysis components of DC voltage signal, and the AP algorithm is used to identify the surface source; 3) the DC current, AC voltage and current signals are added into the sample matrix of fault time-space, and the convolution neural network is used to identify the deep traceability. Finally, the accuracy of the method is verified by using the typical HVDC model.

Keywords

• Commutation failures
• AP clustering algorithm
• deep learning
• fault cases identification
• double-deck method