As a necessary component in rotating machinery,any fault of rolling bearings may lead to mechanical or even system failures,resulting in huge economic loss and time wastage,therefore,it is necessary to promptly and accurately diagnose the rolling bearing fault.In response to the problem that there is the large influence of the model parameters on the fault diagnosis accuracy of rolling bearings,a rolling bearing fault diagnosis method based on deep kernel extreme learning machine with Bayesian optimization is proposed.Firstly,the deep kernel extreme learning machine(DKELM)model is constructed by combining the auto encoder(AE)with the kernel extreme learning machine(KELM).Secondly,the Bayesian optimization algorithm is used to search the optimal hy-perparameters in the DKELM,and minimize the classification error rates of the training and validation datasets in the DKELM model.Then,the test dataset is then input to the trained BO-DKELM for the fault diagnosis.Finally,the proposed method is validated on the bearing fault dataset of the Case Western Reserve University,the result shows that the final fault diagnosis accuracy is 99.6％,compared with traditional intelligent algorithms such as deep belief networks and convolutional neural networks,the proposed method has a higher fault diagnosis accuracy.
rolling bearingfault diagnosisdeep kernel extreme learning machineBayesian optimizationdeep learning
万方数据
维普
