Fault Cause Identification Method Based on Multi-Source Information Fusion for UHVDC Transmission Lines

This paper proposes a fault cause identification method based on multi-source information for UHVDC transmission lines. The multi-source fault information used in this paper includes voltage, current,weather, season, time period, terrain and historical fault information. Firstly, the method analyzes multi-source fault information to extract fault features. Then, the BP neural network is used to fuse the multi-source fault feature. The output of the BP neural network is the probability of failure causes. This method selects the fault type with the highest probability. The effectiveness and feasibility of the method in identifying different types of fault causes are demonstrated by case tests.