A Supplier Evaluation Model Based on ANP and Fuzzy Integral with Application to LED Sapphire Substrate Industry

• Main Authors: Yi-Ting Chen, 陳怡婷
• Other Authors: Chiuh-Cheng Chyu
• Format: Others
• Language: zh-TW
• Online Access: http://ndltd.ncl.edu.tw/handle/c39vaa

碩士 === 元智大學 === 工業工程與管理學系 === 103 === This study presents a new multiple criteria decision model (MCDM) combining the techniques of analytic network process (ANP) and fuzzy integral for supplier selection problems. This model was applied to a LED producer company, where a group of relevant decision makers and experts were invited to participate in the evaluation process. In the beginning, a structure of hierarchical evaluation criteria was established using the fuzzy Delphi method based on data from the expert group. Afterwards, the DEMATEL was applied to construct the ANP model and assess the criteria weights. The ANP model assumes that the inter-influence factors are considered only for criteria within the same aspect, but not between two different aspects. At the final evaluation phase, fuzzy integrals with synergy effect were used to evaluate the total score of each candidate supplier. This MCDM model is characterized by rating the suppliers in consideration of inter-influence relationships and the supper-additive effects among criteria of the same aspect. The presented model was applied to a LED producer for selecting outsourcing provider of pattern sapphire substrate (PPS), which has been extensively used in manufacturing LED lighting products, palmtop computers, and smart phones. Selecting a quality PPS supplier will promote the product quality of the sapphire wafer manufacturer and increase market competition. The conclusion of the MCDM model in the empirical example coincides with the case company’s choice. The outcome supports that the proposed two ANP models are useful in practice.