Authors: Guoxi Sun; Qinghua Zhang; Longqiu Shao; Qin Hu; Aisong Qin
Addresses: College of Computer and Electronic Information, Guangdong University of Petrochemical Technology, Maoming, China ' College of Computer and Electronic Information, Guangdong University of Petrochemical Technology, Maoming, China ' College of Computer and Electronic Information, Guangdong University of Petrochemical Technology, Maoming, China ' School of Automation, Guangdong University of Technology, Guangzhou, China ' College of Information Engineering, Taiyuan University of Technology, Taiyuan, China
Abstract: In order to ensure the safety in petrochemical production, it is of great importance for key equipment in petrochemical production unit to maintain, monitor and diagnose fault. Non-dimensional indicator is insensitive to the change of working condition so it is applicable to fault diagnosis technology, yet it is not satisfactory for complex concurrent fault diagnosis in rotating machinery and the number of conventional non-dimensional indicators is small. Building new non-dimensional indicator, which especially possesses the features of integrated diagnosis, is very significant to improve capability to diagnose fault. In the paper, the method of building new non-dimensional indicator is presented. Based on the previous research findings about 3MGCA to search arithmetical combination of conventional non-dimensional indicator, new non-dimensional indicator is acquired using optimisation algorithm of measured fault data. Experiments show that the proposed method is practical and efficient for building new non-dimensional indicator in rotating machinery, and it has good potential application in the engineering practice.
Keywords: fault diagnosis; non-dimensional indicator; rotating machinery; 3MGCA; occupational safety; petrochemical production.
International Journal of Wireless and Mobile Computing, 2013 Vol.6 No.3, pp.271 - 276
Received: 26 Oct 2012
Accepted: 08 Nov 2012
Published online: 06 Aug 2013 *