A BRB Based Fault Prediction Method of Complex Electromechanical Systems. (8th June 2015)

• Record Type: Journal Article
• Authors: Zhang, Bangcheng; Yin, Xiaojing; Wang, Zhanli; Han, Xiaoxia; Gao, Zhi
• Other Names: Li Gang Academic Editor.
• Is Part Of: Mathematical problems in engineering. Volume 2015(2015)
• Publication Date: 2015-06-08
• Subjects: Engineering mathematics -- Periodicals; 510.2462
• DOI: 10.1155/2015/708616
• Languages: English
• ISSNs: 1024-123X

Abstract

Abstract : Fault prediction is an effective and important approach to improve the reliability and reduce the risk of accidents for complex electromechanical systems. In order to use the quantitative information and qualitative knowledge efficiently to predict the fault, a new model is proposed on the basis of belief rule base (BRB). Moreover, an evidential reasoning (ER) based optimal algorithm is developed to train the fault prediction model. The screw failure in computer numerical control (CNC) milling machine servo system is taken as an example and the fault prediction results show that the proposed method can predict the behavior of the system accurately with combining qualitative knowledge and some quantitative information.