Rolling element bearing fault detection in industrial environments based on a K-means clustering approach

Yiakopoulos, CT; Gryllias, KC; Antoniadis, IA

dc.contributor.author	Yiakopoulos, CT	en
dc.contributor.author	Gryllias, KC	en
dc.contributor.author	Antoniadis, IA	en
dc.date.accessioned	2014-03-01T01:36:43Z
dc.date.available	2014-03-01T01:36:43Z
dc.date.issued	2011	en
dc.identifier.issn	0957-4174	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/21412
dc.subject	Condition monitoring	en
dc.subject	Fault detection	en
dc.subject	K-means clustering	en
dc.subject	Vibration analysis	en
dc.subject	Rolling element bearings	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.classification	Operations Research & Management Science	en
dc.subject.other	ARTIFICIAL NEURAL-NETWORKS	en
dc.subject.other	SUPPORT VECTOR MACHINES	en
dc.subject.other	CORRELATION DIMENSION	en
dc.subject.other	GENETIC ALGORITHMS	en
dc.subject.other	DIAGNOSIS	en
dc.subject.other	GEAR	en
dc.title	Rolling element bearing fault detection in industrial environments based on a K-means clustering approach	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.eswa.2010.08.083	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.eswa.2010.08.083	en
heal.language	English	en
heal.publicationDate	2011	en
heal.abstract	A K-means clustering approach is proposed for the automated diagnosis of defective rolling element bearings. Since K-means clustering is an unsupervised learning procedure, the method can be directly implemented to measured vibration data. Thus, the need for training the method with data measured on the specific machine under defective bearing conditions is eliminated. This fact consists the major advantage of the method, especially in industrial environments. Critical to the success of the method is the feature set used, which consists of a set of appropriately selected frequency-domain parameters, extracted both from the raw signal, as well as from the signal envelope, as a result of the engineering expertise, gained from the understanding of the physical behavior of defective rolling element bearings. Other advantages of the method are its ease of programming, simplicity and robustness. In order to overcome the sensitivity of the method to the choice of the initial cluster centers, the initial centers are selected using features extracted from simulated signals, resulting from a well established model for the dynamic behavior of defective rolling element bearings. Then, the method is implemented as a two-stage procedure. At the first step, the method decides whether a bearing fault exists or not. At the second step, the type of the defect (e.g. inner or outer race) is identified. The effectiveness of the method is tested in one literature established laboratory test case and in three different industrial test cases. Each test case includes successive measurements from bearings under different types of defects. In all cases, the method presents a 100% classification success. Contrarily, a K-means clustering approach, which is based on typical statistical time domain based features, presents an unstable classification behavior. (C) 2010 Elsevier Ltd. All rights reserved.	en
heal.publisher	PERGAMON-ELSEVIER SCIENCE LTD	en
heal.journalName	EXPERT SYSTEMS WITH APPLICATIONS	en
dc.identifier.doi	10.1016/j.eswa.2010.08.083	en
dc.identifier.isi	ISI:000284863200172	en
dc.identifier.volume	38	en
dc.identifier.issue	3	en
dc.identifier.spage	2888	en
dc.identifier.epage	2911	en