Rigid cage guide diagnosisbased on deep auto-encoder network

In order to solve the problem of difficulty for fault diagnosis of rigid cage guide of the hoist in fault feature extraction.Combining the advantages of feature extraction, a new fault diagnosis method of rigid cage guide is proposed based on deep auto-encoder.The reconstruction error is used as evaluation criterion for deep auto-encoder network.The weight and offset of auto-encoder network is optimized layer by layer with back propagation.The network model for feature extraction is constructed by optimal weight and offset.Then fault features of rigid cage guide are extracted based on this network.The rigid cage guide fault classification is realized by SVM used as classifier.The experimental results show that the fault feature extracted by the method is recognizable, and has higher recognition rate.