Forward-backward Analysis Of Supply Chain Using Fuzzy Cognitive Map

Since supply chain is an uncertain system containing numerous variables and complex causal-effect relationships, therefore it is really a hard problem to realize the optimization efficiency of the whole system and the high effect coordination between all factors. In a supply chain system, uncontrollable external states with probabilistic behaviors (e.g., machine failure rate) influence on internal states (e.g., inventory level) significantly through complex causal relationships. Through doing the research on former research, this paper find out the problems widely existed in the modeling supply chain system, such as lacking immediate information connection inside the system, without universality, hard to establish the accurate model and the evaluation index. The goal of this research is to mine bidirectional cause-effect knowledge from the state data.In detail, in order to model the three-stage supply chain system, fuzzy cognitive map (FCM) which has a really good characterize in describing complex causal relationship, is developed. Through asking a group of experts'idea to create the basic structure of FCM, which means the states of system and direction of the system is determined. Furthermore, the developed. By using genetic algorithm, the weight matrix of the FCM model is discovered with the past state data. The outlier state node are some statistical nodes(such as machine failure rate),they influence the inside state node through complex causal relationship. At the beginning of simulation step, the outliner state value is generated by random number methods. Thanks to Radio frequency identification (RFID) technology, real time monitoring of the states is now possible rather than the traditional "human plus bar code" technology. When there is a sudden change of the internal states, a forward (what-if) analysis is performed through calculation of FCM. Also, when sudden change in a certain state is detected, its cause is sought from the past state data throughout backward analysis. Simulation based experiments are provided to show the performance of the proposed forward-backward analysis methodology.At the final experiment stage, this paper constructs a expended supply chain FCM which combines the manufacturer operation. Through the simulation of forward-backward analysis, the results show that the error of forward analysis is 0.19, the backward analysis error is 0.11. therefore the conclusion is clear to get that the constructed supply chain system has a good logical expression, generality and the predication ability satisfies our need.