Sensors 2013, 13(9), 12663-12686; doi:10.3390/s130912663
Article

A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics

The Smart Engineering Asset Management Laboratory (SEAM), Department of Systems Engineering and Engineering Management (SEEM), City University of Hong Kong, Tat Chee Avenue, Kowloon, 999077 Hong Kong
* Author to whom correspondence should be addressed.
Received: 18 June 2013; in revised form: 10 September 2013 / Accepted: 12 September 2013 / Published: 18 September 2013
(This article belongs to the Section Physical Sensors)
PDF Full-text Download PDF Full-Text [697 KB, Updated Version, uploaded 25 September 2013 09:15 CEST]
The original version is still available [868 KB, uploaded 18 September 2013 13:39 CEST]
Abstract: Oil sand pumps are widely used in the mining industry for the delivery of mixtures of abrasive solids and liquids. Because they operate under highly adverse conditions, these pumps usually experience significant wear. Consequently, equipment owners are quite often forced to invest substantially in system maintenance to avoid unscheduled downtime. In this study, an approach combining relevance vector machines (RVMs) with a sum of two exponential functions was developed to predict the remaining useful life (RUL) of field pump impellers. To handle field vibration data, a novel feature extracting process was proposed to arrive at a feature varying with the development of damage in the pump impellers. A case study involving two field datasets demonstrated the effectiveness of the developed method. Compared with standalone exponential fitting, the proposed RVM-based model was much better able to predict the remaining useful life of pump impellers.
Keywords: pump impeller; remaining useful life (RUL); prognosis; relevance vector machine (RVM); sum of two exponential functions

Article Statistics

Load and display the download statistics.

Citations to this Article

Cite This Article

MDPI and ACS Style

Hu, J.; Tse, P.W. A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics. Sensors 2013, 13, 12663-12686.

AMA Style

Hu J, Tse PW. A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics. Sensors. 2013; 13(9):12663-12686.

Chicago/Turabian Style

Hu, Jinfei; Tse, Peter W. 2013. "A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics." Sensors 13, no. 9: 12663-12686.

Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert