A fuzzy multi attribute decision framework with integration of QFD and grey relational analysis

Abstract

ObjectiveThis paper proposes a multi attribute decision support model in a supply chain in order to solve complex decision problems. The paper provides a platform to ease decision process through the integration of quality function deployment (QFD) and grey relational analysis (GRA) in demonstrating main supply chain drivers under fuzzy environment. MethodologyThe proposed method is important because of several points: First of all, in a supply chain system, evaluation factors are not really independent and must be addressed in relation to the external factors such as customer requirements. Hence, we have applied QFD tool. Second, due to the constant uncertainty in the supply chain environment, fuzziness among the factors has to be considered. So, an interval valued fuzzy model was implemented. Third, to examine the proposed decision system in reality, it was applied in Risk and Uncertain Conditions for Agriculture Production Systems (RUC-APS) project. ContributionAn integrated version of QFD and GRA is presented. It is assumed that QFD can act to measure optimal solutions based on the distance to ideal solutions. In an interval-valued fuzzy environment the enormous volume of computation by Euclidean distance doesn't allow decision makers to obtain the results easily. This drawback is addressed using gray relational analysis. The gray relational coefficient is integrated to the fuzzy QFD to measure the distance of potential solutions from ideal solutions. This integration facilitates decision making process in further problems once big data are available. ResultsTo obtain the importance degrees of logistic indicators in the supply chain, expert team considered the environmental, social & cultural, and economic factors as external dimension of the QFD. The other dimension of QFD includes supply chain drivers such as quality, environmental management system, supply chain flexibility, corporate social responsibility, transportation service condition, and financial stability. The decision model is solved and the ranking of indicators is achieved. A sensitivity analysis helps to test and check the performance of the decision model.