基于VMD-ESA和IPOA-XGBOOST相结合的异步电机故障诊断OACSTPCD

In order to improve the accuracy of fault diagnosis of asynchronous motor,an intelligent diagnostic method is proposed that combines variational mode decomposition(VMD),envelope spectrum analysis(ESA),and improved Pelican optimization algorithm to optimize the limit gradient lifting model(IPOA-XGBOOST).VMD decomposition on the measured vibration signals of asynchronous motors is conducted,and ESA is used to calculate the instantaneous energy matrix of the intrinsic mode components(IMFs)obtained from VMD decomposition.Then,singular value decomposition(SVD)is used to extract features from the obtained instantaneous energy matrix.The extracted feature vectors are used to train the IPOA-XGBOOST model and obtain the accuracy of fault diagnosis of asynchronous motor.In order to solve the problems that the pelican optimization algorithm is easy to fall into the local optimal solution and the optimization speed is slow,the Circle mapping is used to improve the pelican optimization algorithm.The optimization analysis of improved pelican optimization algorithm,genetic algorithm(GA)and pelican optimization algorithm are conducted.The experimental results show that the improved pelican optimization algorithm has the best optimization effect.