基于BA-MKELM的微电网故障识别与定位OACSTPCD

A microgrid fault identification and location method based on Bayesian algorithm optimizing multi-kernel extreme learning machine is proposed.Aiming at the problem of insufficient regression ability caused by the random selection of input parameters and hidden layer nodes of extreme learning machine,the kernel function is introduced,and the polynomial and the Gaussian radial basis kernel function are combined to form a multi-kernel extreme learning machine to establish a fault identification and location model.The Bayesian algorithm is used to optimize the relevant parameters of the multi-kernel extreme learning machine to further improve the approximation ability of the model.In order to verify the fault identification and location performance of the proposed model,extreme learning machine and multi-kernel extreme learning machine are selected to establish fault diagnosis models respectively for comparative analysis.Experimental results show that the proposed method can identify and locate any type of faults in the microgrid with high performance,and has higher recognition and location accuracy.