New machine prognostics approach based on health state probability estimation

Abstract

This paper presents an innovative prognostic model based on health state probability estimation embedded in the closed loop diagnostic and prognostic system to provide comprehensive timely analysis for effective decision making in industrial asset management. To apply an appropriate classifier in health state probability estimation for prediction of machine remnant life, a comparative study on intelligent fault classification for four fault conditions with five different fault progressed data from high pressure cryogenic pumps were conducted. Five different classifiers, such as support vector machines (SVMs), radial basis function neural networks, random forest and linear regression, were used to evaluate their effectiveness for the health state estimation process. Two sets of impeller-rub data were employed for the prediction of pump remnant life based on estimation of discrete health state probability with feature selection technique using the outstanding capability of SVM. The results obtained were very encouraging and showed that the proposed prognosis system has the potential to be used as an estimation tool for machine remnant life prediction in real life industrial applications.

Keywords:

• High pressure cryogenic pump
• diagnostics
• prognostics
• remaining useful life (RUL)

Additional information

Notes on contributors

H -E Kim

Dr Hack-Eun Kim is the senior manager of Korea Gas Technology Corporation, located Daejeon, Korea. He received his PhD degree at the School of Engineering Systems, Faculty of BEE, Queensland University of Technology, Brisbane, Australia. He also received his master of engineering in mechanical from Gyeongsang National University, Gyeongnam, Korea. He was recipient of “Award of Best Achievement in Faculty of Engineering” and Full Scholarship for four years during his undergraduate course. He has worked as a mechanical engineer, project engineer and maintenance manager in oil and gas industry for 13 years. His research interests include vibration condition monitoring, diagnostics and prognostics for effective asset management in real industry.

A C C Tan

Andy CC Tan received his BSc (Eng) and PhD degrees in mechanical engineering from the University of Westminster, London. His research interests include noise and vibration condition monitoring, and sensors for active vibration control. He applied adaptive signal processing and the blind deconvolution algorithms to enhance the desired signals corrupted by noise for the detection of incipient faults. These algorithms together acoustic emission sensors are currently being used in low speed machinery condition monitoring. He is expanding his research into diesel engine diagnostics/prognostics and study of electrical properties of carbon nanotube composite sensors for bridge structure monitoring. He is a pioneer of artificial heart pump project in Queensland, Australia and a professor of mechanical engineering at the Faculty of Built Environment and Engineering of the Queensland University of Technology. His academic interests include dynamics of mechanical systems, noise and vibrations and mechanism design. In engineering education, he receives international recognition for pioneering the first joint degrees program. He is a Fellow of the Institution of Engineers Australia.

J Mathew

Professor Joseph Mathew is the Chief Executive Officer of the Cooperative Research Centre in Infrastructure and Engineering Asset Management, located Brisbane, Australia. He was previously Queensland University of Technology’s Head of School in the School of Mechanical, Manufacturing and Medical Engineering. Prior to arriving in Brisbane in 2000, Joe was Monash University’s Professor of Manufacturing and Industrial Engineering in Melbourne. He has also served as Executive Director of Monash’s Centre for Machine Condition Monitoring from 1993–1997. He has presented numerous invited lectures and addresses to professional societies and industrial organisations on engineering asset management, machine condition monitoring, and vibrations and noise control. Prior to academia, Joe was a noise and vibrations consultant having begun his career with Vipac and Partners and subsequently ran JAM Solutions, providing solutions in noise and vibrations control. He serves as Chairman of the Board of the International Society of Engineering Asset Management, Chairman of the ISO’s subcommittee ISO/TC 108/SC 5 on Condition Monitoring and Diagnostics of Machines and as General Chair for the World Congress on Engineering Asset Management.