Fault Identification Method of T-Connection Transmission Line Built on Backward Traveling Wave Energy Cross Entropy

In order to solve the problems of low accuracy and poor robustness of traditional fault diagnosis for T -connected transmission lines, a fault diagnosis algorithm for T -connected transmission lines based on backward traveling wave energy cross entropy was proposed. Based on S-transform, the cross entropy of the sum of the backward traveling wave current energy of the short time sequence corresponding to 10 frequencies at the two measuring points of the T-connected transmission line is calculated, and the cross entropy calculated from the 6 short time sequences is taken as the sample set to characterize the fault characteristics. Combined with random forest neural network, the characteristic samples are trained and tested to diagnose the fault of T -connected transmission lines. After extensive simulation experiments and analysis, it was found that the proposed method not only accurately identifies the branch where the fault is located, but also has certain anti-interference capabilities.