Research on the Failure Mechanism and Fault Prediction Method of High Voltage DC Relays

As an important switching component, studying the fault prediction model of high-voltage direct current relays is of great significance for improving the power supply safety in the field of new energy. With the goal of analyzing the failure mechanism of high-voltage direct current relays and predicting their faults, a high-voltage direct current relay experimental system was built, and a large number of on-off experiments were conducted on multiple relays. BP and PSO-BP neural network prediction models were constructed using MATLAB, and arc energy was selected as the input feature quantity for the prediction model. The accuracy of the prediction model was evaluated using R2, MAE, MSE, and the results showed that the PSO- BP neural network prediction model is more suitable for fault prediction of high-voltage DC relays.