Soft Fault Diagnosis of DC-DC Circuit Based on IAO-ELM
Aiming at the problem of poor accuracy of soft fault diagnosis in DC-DC circuit,a fault diagnosis method based on improved aquila optimizer and optimized extreme learning machine(IAO-ELM)is proposed.The original fault signal is decomposed and reconstructed by the VMD method,and the features in the time-frequency domain are extracted as the feature vector.SPM chaotic mapping,lens reverse learning,adaptive weight and Cauchy mutation strategy are used to improve the aquila optimizer and improve its optimization performance.The input weights and im-plicit layer bias of ELM are optimized by IAO,and the IAO-ELM diagnostic model is obtained to improve the classifi-cation accuracy.The results show that the accuracy of IAO-ELM diagnosis model is 99.375%,which can effectively realize the soft fault diagnosis of DC-DC circuit.
万方数据
维普
