Condition multi-classification and evaluation of system degradation process using an improved support vector machine. (August 2017)

• Record Type: Journal Article
• Authors: Miao, Qiang; Zhang, Xin; Liu, Zhiwen; Zhang, Heng
• Is Part Of: Microelectronics and reliability. Volume 75(2017)
• Page Start: 223
• Page End: 232
• Publication Date: 2017-08
• Subjects: Degradation process -- Multi-classification -- Support vector machine -- System state transition -- Degradation index; Electronic apparatus and appliances -- Reliability -- Periodicals; Miniature electronic equipment -- Periodicals; Appareils électroniques -- Fiabilité -- Périodiques; Équipement électronique miniaturisé -- Périodiques; Electronic apparatus and appliances -- Reliability; Miniature electronic equipment; Periodicals; 621.3815
• DOI: 10.1016/j.microrel.2017.03.020
• Languages: English
• ISSNs: 0026-2714

Abstract

Abstract: Degradation process is a non-negligible phenomenon in system condition monitoring and reliability practices. Traditional binary-state characterization (i.e., normal and failure) on system health condition may not provide accurate information for maintenance scheduling, and the multi-state classification for degradation process is a necessary step to realize cost-effective condition based maintenance. Support vector machine (SVM) is a useful technique for system condition monitoring and fault diagnosis. However, the SVM classification accuracy of deteriorating system is usually poor, because characteristics of different degradation states may not be very distinctive. This paper presented an improved support vector machine for system degradation classification and evaluation. The core of the proposed method can be summarized as: an improved voting scheme in one-against-one SVM, and an optimization of classification process by utilizing inherent physical property of system state transition. A case study of cooling fan bearing accelerated life time test is conducted to obtain the experimental data, and a comparison before and after optimization shows that the proposed method improves the classification accuracy. Highlights: An improved OAOSVM with a new voting scheme is proposed. By utilizing system state transition property, a SVM classification process is optimized. A case study of cooling fan bearings is used to validate the multi-classification performance of the proposed method.