Credibility Evaluation Method of Simulation System Based on Improved Evidence Theory

In order to solve the problem that it is difficult to evaluate the reliability of complex simulation system accurately, this paper proposes a credibility evaluation method of simulation system based on improved evidence theory. The method combines the advantages of the D-S (Dempster-Shafer) evidence theory and the fuzzy theory. Firstly, for dealing seriously with conflicting evidence when the Dempster combination result can not identify the actual conditions, the Jousselme distance is used to modify the conflicting evidence, and the reliability of evidence is taken as discount factor to correct the fusion rules. Then, the membership function is used to transform the experts' fuzzy comments into the belief function of evidence theory. Finally, all the evidences are fused by the modified evidence fusion rules to get the final credibility evaluation result of simulation system. The application example shows that this method can well reflect the credibility of complex simulation system, and the decision is more reliable and the uncertainty is small, which is a good supplement to the existing research and the method has certain theoretical and practical value.