Application of GA-LSTM model in cable Joint temperature prediction

Abstract

The safety of the power cable running system directly affects the safety and reliability of the power supply. Due to most of the cable fault occurred in the cable joint parts, it's necessary to improve the security of power cable running system. This paper shows an algorithm based on GA - LSTM to predict the cable joint temperature. That's genetic algorithm optimizes the network structure of LSTM model, gets the best LSTM prediction model, and uses the collected data set of cable joint temperature on the established model for training. The training results show that the GA-LSTM algorithm can get a more accurate temperature prediction value and less error than the LSTM network under the condition of large samples, and it has a good application for the prediction of cable temperature.