Retracted: Fault Diagnosis Method Based on EEMD and Multi-Class Logistic Regression

A fault diagnosis method based on EEMD and multi-class Logistic regression was proposed for various types of faults. First, the vibration signal is decomposed by EEMD method, and then the AR model is established based on the decomposition results. The autoregressive parameters and the residual variance of the model are taken as the fault feature vectors, which are used as the input of the fault diagnosis model. Then, on the basis of the binary classification Logistic model, the multi-class Logistic regression model was established, and the model parameters were estimated by the gradient descent method, overcoming the limitations of the binary classification Logistic. Finally, an example is given to verify that the proposed method can effectively classify the normal working state and fault types.