Applying DEA to enhance assessment capability of FMEA

Abstract

Purpose

The purpose of this study is to propose a state‐of‐the‐art new approach to enhance FMEA assessment capabilities.

Design/methodology/approach

Through data envelopment analysis (DEA) technique and its extension, the proposed approach evolves the current rankings for failure modes by exclusively investigating SOD in lieu of RPN and to furnish improving scales for SOD.

Findings

Through an illustrative example the proposed approach supports the proposition that DEA can not only complement traditional FMEA for improving assessment capability but also, especially, provide corrective information regarding the failure factors – severity, occurrence and detection. Further application of DEA Stratification also reveals that this methodology is useful for managing resource allocation and risk management.

Practical implications

It is shown that the proposed approach enables manager/designers to prevent system or product failures at an early stage of design. Moreover, the approach is able to provide managerial insight of SOD more effectively than justifying the efforts on RPN alone. Projection of each SOD is determined to help managers examine the scale of efforts. Finally, the stratification analysis offers the economical allocation of failure modes with respect to the incurred costs and the efficiency.

Originality/value

The paper proposes a unique new approach, robust, structured and useful in practice, for failure analysis. The methodology, within a firmed methodology, overcomes some of the largely known shortfalls of traditional FMEA: it takes into account multiple criteria and restricted weighted; and it analyses the failure modes' ranking considering not only the direct impacts of failure indices, but also the contribution of these indices.

Citation

Chang, D. and Paul Sun, K. (2009), "Applying DEA to enhance assessment capability of FMEA", International Journal of Quality & Reliability Management, Vol. 26 No. 6, pp. 629-643. https://doi.org/10.1108/02656710910966165