Fault Diagnosis Method for Secondary System of Intelligent Substation Based on Patrol Robot and Deep Learning

A F-D method based on patrol robots and deep learning for ISSS is proposed to address the issue of traditional Fault Diagnosis (F-D) methods for Secondary Systems (SS) in Intelligent Substations (IS) that are not suitable for situations with large and complex data volumes, and have low diagnostic accuracy. Firstly, statistical analysis was conducted on the possible faulty equipment and types of ISSS, and based on this, a fault information database was constructed. Then, based on the inspection robot, 24-hour data collection and processing of SS within IS were achieved. Finally, by introducing GA algorithm into the Backpropagation neural network (BP-N) model, an F-D model based on improved BP-N ISSS was proposed, and the corresponding F-D process was provided. A comparative analysis was conducted between the proposed method and the other three methods under the same conditions through simulation experiments. The results show that under the same experimental conditions, the accuracy and CAP obtained by the proposed method are both the highest, reaching 98.35% and 95.67%, respectively. Its performance is superior to the other three comparative methods.