A Support Vector Machine approach based on physical model training for rolling element bearing fault detection in industrial environments

Gryllias, KC; Antoniadis, IA

dc.contributor.author	Gryllias, KC	en
dc.contributor.author	Antoniadis, IA	en
dc.date.accessioned	2014-03-01T02:07:33Z
dc.date.available	2014-03-01T02:07:33Z
dc.date.issued	2012	en
dc.identifier.issn	09521976	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/29573
dc.subject	Condition monitoring	en
dc.subject	Fault detection	en
dc.subject	Rolling element bearings	en
dc.subject	Support Vector Machines	en
dc.subject	Vibration analysis	en
dc.subject.other	Automated diagnosis	en
dc.subject.other	Basic concepts	en
dc.subject.other	Classification procedure	en
dc.subject.other	Data preprocessing	en
dc.subject.other	Demodulated signals	en
dc.subject.other	Experimental data	en
dc.subject.other	Experimental test	en
dc.subject.other	Frequency domains	en
dc.subject.other	Industrial environments	en
dc.subject.other	Industrial Test Case	en
dc.subject.other	Normal condition	en
dc.subject.other	Order analysis	en
dc.subject.other	Physical model	en
dc.subject.other	Raw signals	en
dc.subject.other	Rolling Element Bearing	en
dc.subject.other	Rolling element bearings	en
dc.subject.other	Rotating speed	en
dc.subject.other	Rotation speed	en
dc.subject.other	Simulation data	en
dc.subject.other	Sudden change	en
dc.subject.other	Support vector	en
dc.subject.other	SVM classifiers	en
dc.subject.other	Test case	en
dc.subject.other	Two stage	en
dc.subject.other	Two-stage recognition	en
dc.subject.other	Computer simulation	en
dc.subject.other	Condition monitoring	en
dc.subject.other	Dynamic response	en
dc.subject.other	Fault detection	en
dc.subject.other	Feature extraction	en
dc.subject.other	Frequency domain analysis	en
dc.subject.other	Rotation	en
dc.subject.other	Signal detection	en
dc.subject.other	Vibration analysis	en
dc.subject.other	Support vector machines	en
dc.title	A Support Vector Machine approach based on physical model training for rolling element bearing fault detection in industrial environments	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.engappai.2011.09.010	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.engappai.2011.09.010	en
heal.publicationDate	2012	en
heal.abstract	A hybrid two stage one-against-all Support Vector Machine (SVM) approach is proposed for the automated diagnosis of defective rolling element bearings. The basic concept and major advantage of the method, is that its training can be performed using simulation data, which result from a well established model, describing the dynamic response of defective rolling element bearings. Then, vibration measurements, resulting from the machine under condition monitoring, can be imported and processed directly by the already trained SVM, eliminating thus the need of training the SVM with experimental data of the specific defective bearing. A key aspect of the method is the data preprocessing approach, which among others, includes order analysis, in order to overcome problems related to sudden changes of the shaft rotating speed. Moreover, frequency domain features both from the raw signal as well as from the demodulated signal are used as inputs to the SVM classifiers for a two-stage recognition and classification procedure. At the first stage, a SVM classifier separates the normal condition signals from the faulty signals. At the second stage, a SVM classifier recognizes and categorizes the type of the fault. The effectiveness of the method tested in one literature established experimental test case and in three different industrial test cases, including a total number of 34 measurements. Each test case includes successive measurements from bearings under different types of defects, different loads and different rotation speeds. In all cases, the method presents 100% classification success. © 2011 Elsevier Ltd. All rights reserved.	en
heal.journalName	Engineering Applications of Artificial Intelligence	en
dc.identifier.doi	10.1016/j.engappai.2011.09.010	en
dc.identifier.volume	25	en
dc.identifier.issue	2	en
dc.identifier.spage	326	en
dc.identifier.epage	344	en