-种用于变压器故障诊断的贝叶斯网络优化方法.

In view of the low efficiency of transformer fault diagnosis, an improved grasshopper optimization algorithm is proposed by combining dissolved gas analysis in oil with artificial intelligence method to optimize the transformer fault diagnosis method of Bayesian network. The differential evolution algorithm and simulated annealing algorithm are used to improve the locust algorithm, which improve the optimization ability of the algorithm. The improved locust algorithm is applied to the Bayesian network structure learning to construct the transformer fault diagnosis model, and the method proposed in this study is used to diagnose the transformer fault. The experimental results show that the diagnosis accuracy of this method is 92.7%, which is higher than that of other algorithms [ABSTRACT FROM AUTHOR]