Research On The Supply Chain Performance Evaluation Based On Conversion Of Membership Degree

The supply chain management, in order to make the supply chain and healthy development of a comprehensive scientific analysis and evaluation of the supply chain operating performance, operation and supply chain management is crucial. Supply Chain Performance with a strong orientation effect, is driving enterprises to conduct various activities to rationalize the internal dynamic.This paper introduces the supply chain performance evaluation of the features and content firstly; and from the supply chain strategy marching ability, logistics ability, supply chain operation, green competitiveness, coordination of supply chain, developing ability of supply chain, constitutes a multi-storey supply chain performance evaluation system. Supply chain performance evaluation system hierarchy structure of the lowest indicators can be measured or quantified; index and the ranking of index value is fuzzy, so based on the Analytic Hierarchy Process multi-level fuzzy comprehensive evaluation model from the Mechanism is the most reasonable, with the most application to performance evaluation of the supply chain.Construction tree structure evaluation index system, access the membership of bottom index and the importance weight of index in layers, multi-level fuzzy comprehensive evaluation have to solve the issues: to achieve the conversion of membership degree; which seems to be a problem has been resolved, but is an unresolved in fact, at least not yet good to solve the problems. For example, ever, existing converse algorithms of membership degrees in Fuzzy comprehensive evaluation are questionable because they can't distinguish the useful or useless part of membership degrees of indexes based on the contribution values to objective classification. As a result, redundant data, which are useless to objective classification, are involved in calculation of membership degrees of the objective.In fact, the conversion of membership degree is a kind of information fusion technology, mining the hidden knowledge information from the membership of index is the core step. Therefore, through mining this kind of hidden knowledge information, a filtering algorithm, which can removes the redundant data in the index membership function, is proposed to extract no redundancy date to converse membership degrees. A membership transformation method based on "filtering, comparison and composition" from single-index measure to multi-index comprehensive measure is also proposed, and the algorithm suitable for multi-level, more indicators, the large data volume computing problem, the algorithm at the same time solve the large data volume calculation of the complex supply chain evaluation.