Application of orthogonal neighborhood preserving projections and two dimensional hidden Markov model for the degradation evaluation of rolling elements bearings

• Main Authors: Yongxiang Zhang, Yujie Xiao, Shuai Zhang, Shengjie Wang
• Format: Article
• Language: English
• Published: JVE International 2017-06-01
• Series: Journal of Vibroengineering
• Subjects: data mining; diagnostics; Markov modeling; reliability engineering; process monitoring; rolling elements bearings; incipient defects
• Online Access: https://www.jvejournals.com/article/17084
• ISSN: 1392-8716; 2538-8460

An effective degradation indicator created from the general features is still a hotspot for the condition monitoring of bearing. To cover the shortage of the general features based indicator, some new indicators are built using multiple general features extracted from the original vibration signal without considering the internal relevancy among the features. To address that problem, a new indicator is proposed using the Orthogonal Neighborhood Preserving Projections (ONPP) and 2-Dimensional Hidden Markov Model (2-D HMM). With the ability of keeping the local structure of data set, Orthogonal Neighborhood Preserving Projections is used to obtain the low dimensional features with the main information remained. Unlike 1-Dimensional data-processing algorithm that commonly converts the multiple features into a vector to deal with the high-dimensional data with the integral property of the multiple features considered only, 2-Dimensional Hidden Markov Model not only take the relevance between the individuals of fault features into consideration but also capture the global characteristics of the multiple features. Then a likelihood probability based health assessment indication can be constructed by combing 2-D HMM with the data pre-processed by ONPP. The experiment results indicate that the proposed indicator show great abilities to make degradation performance of the bearing and is sensitive to incipient defects.