Research on State Prediction of Gas Insulated Switchgear Based on CNN-GRU Combinatorial Neural Network

Gas Insulated Switchgear is one of the core equipment of the power system. During the operation, its maintenance work is relatively complicated and time-consuming, and the power outage range sometimes involves non-faulty components, which will cause significant economic losses. Therefore, predicting the operation status of GIS can help to perceive the potential threats of GIS in time and grasp the development trend of GIS failures. This paper proposes a GIS operating state prediction method based on the combined neural network of convolutional neural network (CNN) and gated recurrent unit (GRU). Defects, historical test data, and online monitoring data are combined with AHP and multi-level variable weight evaluation ideas to evaluate their status, build equipment status correlation analysis and status prediction models, and organically combine quantitative and qualitative indicators to explore characteristic parameters. Correspondence between GIS states. The feasibility and accuracy of the method are verified by example analysis, compared with long short-term memory (LSTM) model and GRU model, it has better prediction accuracy and efficiency.