Distribution Network Equipment Fault Prediction and Maintenance Path Optimization Strategy Based on Deep Learning and Knowledge Map Comprehensive Analysis

摘要

In view of the dynamic real-time nature of the distribution network faults, the difficulty of forecasting, and the difficulty of fault inspection path planning, this paper proposes a strategy for fault prediction and maintenance path optimization of distribution network equipment based on deep learning-knowledge graph comprehensive analysis. First, use the comprehensive analysis strategy based on deep learning-knowledge map to predict the failure of the distribution network equipment, and perform statistical analysis according to the size of the prediction result. Then, according to the predicted health status of the equipment, the quantum genetic algorithm is used to optimize the inspection path of the distribution net-work inspector. According to the optimization result, the optimal inspection path of the distribution network inspector is finally obtained. The results of the calculation example show that based on the deep learning-knowledge map comprehensive analysis method, the model loss value is reduced to about 0.2, which meets the prediction accuracy. And the use of quantum genetic algorithm to optimize the inspection path compared with the traditional genetic algorithm, the objective function value is reduced by about 50%, thereby reducing the path length of the inspector and saving inspection time.