Semisupervised Deep Sparse Auto-Encoder With Local and Nonlocal Information for Intelligent Fault Diagnosis of Rotating Machinery

Authors:
Publisher website
Google Scholar
Abstract
Nowadays, the measuring and monitoring data collected from rotating machinery exists a high-dimensional and massive status in quo, but the acquisition of the valuable labeled information is difficult. To address this challenge, an intelligent fault diagnosis method of rotating machinery based on semi-supervised deep sparse auto-encoder (SSDSAE) with local and non-local information is presented in this paper. Primarily, the collected vibration spectrum signals are fed into the constructed SSDSAE algorithm to implement fault feature extraction, after that the extracted sparse discriminant features are fed into back-propagation (BP) classifier for fault diagnosis. Accordingly, the unlabeled samples in SSDSAE are employed to define local and non-local structural information for the original deep sparse auto-encoder (DSAE), then the topological regularization terms are obtained by minimizing intra-class compactness (locality) and maximizing inter-class separability (non-locality). Moreover, the weighted cross-entropy (WCE) techniques in SSDSAE are employed to improve the generalization performance of the fault diagnosis model for labeled data. Eventually, the availability of the proposed method is validated with the data from experimental bearing fault and industrial rotor fault, respectively.
Funding Information
  • National Natural Science Foundation of China (51675098)
  • Postgraduate Research & Practice innovation program of Jiangsu province, China (SJKY19_0064/KYCX19_0063)
  • China Scholarship Council

This publication has 33 references indexed in Scilit: