A fuzzy AHP-based performance evaluation model for implementing SPC in the Taiwanese LCD industry

Statistical process control (SPC) is one of the most practical and widely used tools to enhance product quality and reduce costs. However, the implementation of SPC has often resulted in unsatisfactory performance; moreover, there is no well-established standard for evaluation of the results of introducing the system. The present study addresses this problem by proposing an effective and convenient performance-evaluation model for implementing SPC. The proposed model draws on the DMAIC methodology of Six Sigma, the performance-evaluation model of Lin et al. (Lin, W.T., Liu, C.H., Hsu, I.C., and Lai, C.T., 2004. An empirical study of QS 9000 in the automobile and related industries in Taiwan. Total Quality Management, 15 (3), 335–378), and the fuzzy mathematical programming of Kaufmann and Gupta (Kaufmann, A. and Gupta, M.M., 1991. Introduction to fuzzy arithmetic: theory and application. New York: Van Nostrand Reinhold) to define the fuzzy indices and control values of importance, action, and performance in developing the proposed performance-evaluation model. The model is then applied in a case study of a Taiwanese liquid crystal display manufacturer. A questionnaire is designed to establish fuzzy indices of importance, action, and performance values for assessment by analytic hierarchy process methodology. Various critical factors and feasible improvement strategies are then compared (using computed weights) to determine the priority of the improvement strategies. To verify improvement, the same model is used to re-evaluate system control performance after implementing the improvement strategies for some time. The study demonstrates that the proposed model is an effective and convenient tool that can be used to analyse and improve the performance of an existing SPC system or to enhance success in implementing a new SPC system while working within constraints of time and costs.