Rolling Bearing with Isometric Feature Mapping and Fuzzy C means Fault Identification Method

In the fault identification of rolling bearing, the traditional ISOMAP algorithm is met with the problem of large deviation of geodesic distance and aliasing in fault identification. So, this paper presents a fuzzy C means and Isometric Feature Mapping of rolling bearing fault identification met...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG Ya-ping, LI Shi-song, GE Jiang-hua, XU Di, LI Yun-fei
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2019-06-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=1680
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the fault identification of rolling bearing, the traditional ISOMAP algorithm is met with the problem of large deviation of geodesic distance and aliasing in fault identification. So, this paper presents a fuzzy C means and Isometric Feature Mapping of rolling bearing fault identification method. First of all, the neighborhood size k of ISOMAP algorithm is improved with residuals to ensure that the mapping results reflect the global nature well. Second, the index of category divisibility is used to evaluate the effect of feature dimensionality reduction. Then, a fuzzy Cmeans clustering method is adopted to ensure that the data in high dimensional manifolds and the low dimensional smooth manifold in the topological space are still close or the same. Finally, the experimental verification of vibration data of rolling bearing with different damage degrees shows that the combination of fuzzy C means and improved ISOMAP has obvious improvement in both classification and identification accuracy.
ISSN:1007-2683