Fault diagnosis method of automation equipment in independent and controllable substation based on deep reinforcement learning

Abstract

Fast and accurate fault diagnosis is the key to ensure the safe and stable operation of the substation after the fault occurs to the automation equipment in the independent and controllable intelligent substation. Firstly, different types of faults that may occur in intelligent substation automation equipment are analyzed, and the electrical characteristic information of corresponding fault types is characterized respectively. Then, the basic structure of enhanced deep convolutional neural network (EDCNN) and the applicability and superiority of EDCNN in automatic equipment fault diagnosis are analyzed, and the model and algorithm of automatic equipment fault diagnosis based on EDCNN are built on the basis of data preprocessing. Finally, the proposed algorithm and other three algorithms are compared and analyzed under the same conditions based on actual cases. The results show that for different types of faults, the proposed algorithm has higher fault diagnosis accuracy and faster convergence speed.