Reliability prediction for evolutionary product in the conceptual design phase using neural network-based fuzzy synthetic assessment

Yu Liu, Hong-Zhong Huang and Dan Ling

International Journal of Systems Science, 2013, vol. 44, issue 3, 545-555

Abstract: Reliability prediction plays an important role in product lifecycle management. It has been used to assess various reliability indices (such as reliability, availability and mean time to failure) before a new product is physically built and/or put into use. In this article, a novel approach is proposed to facilitate reliability prediction for evolutionary products during their early design stages. Due to the lack of sufficient data in the conceptual design phase, reliability prediction is not a straightforward task. Taking account of the information from existing similar products and knowledge from domain experts, a neural network-based fuzzy synthetic assessment (FSA) approach is proposed to predict the reliability indices that a new evolutionary product could achieve. The proposed approach takes advantage of the capability of the back-propagation neural network in terms of constructing highly non-linear functional relationship and combines both the data sets from existing similar products and subjective knowledge from domain experts. It is able to reach a more accurate prediction than the conventional FSA method reported in the literature. The effectiveness and advantages of the proposed method are demonstrated via a case study of the fuel injection pump and a comparative study.

Date: 2013
References: Add references at CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://hdl.handle.net/10.1080/00207721.2011.617887 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:tsysxx:v:44:y:2013:i:3:p:545-555

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TSYS20

DOI: 10.1080/00207721.2011.617887

Access Statistics for this article

International Journal of Systems Science is currently edited by Visakan Kadirkamanathan

More articles in International Journal of Systems Science from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().