Title: Proposing a new model of failure mode and effect analysis for clustering and ranking of manufacturing process
Authors: Farshad Faezy Razi; Ehsan Hoseini
Addresses: Department of Industrial Management, Semnan Branch, Islamic Azad University, Semnan, Iran ' Department of Industrial Management, Semnan Branch, Islamic Azad University, Semnan, Iran
Abstract: This article proposes a new framework for the failure mode and effect analysis (FMEA) in the manufacturing process. This paper will argue that how a new approach offers a different analysis of the risk of failure compared with the traditional approach in the FMEA model. Through a case study in the Paper Machine Type: Andritz DC 100, it was tried to examine the effectiveness of the new approach. The method used in this study is descriptive and mathematical modelling. The implementation results of KOHNEN algorithm showed that all failure modes in the studied machine do not fall in one cluster and that is why each cluster of failure modes must be evaluated independently and separately from other clusters. Unlike other FMEA models, the present paper initially clusters failure modes through the KOHNEN neural network. Failure modes classified in each cluster will be evaluated independently of any other cluster through the SBM-DEA model.
Keywords: failure mode and effects analysis; FMEA; KOHNEN neural networks; slack-based measure; SBM; data envelopment analysis; DEA; clustering; ranking; manufacturing processes; case study; mathematical modelling.
International Journal of Productivity and Quality Management, 2017 Vol.21 No.1, pp.45 - 71
Received: 07 Nov 2015
Accepted: 05 Dec 2015
Published online: 23 Mar 2017 *