No abstract

Decision fusion is an effective way to resolve the conflict of diagnosis results. Aiming at the problem that Dempster-Shafer (DS) theory deals with the high conflict of evidence and produces wrong results, a decision fusion algorithm for fault diagnosis based on closeness and DS theory is proposed. Firstly, the relevant concepts of DS theory are introduced, and the normal distribution membership function is used as the evidence closeness. Secondly, the harmonic average is introduced, and the weight of each evidence is established according to the product of closeness of each evidence and its harmonic average. Thirdly, the weight of conflicting evidence is regularized, and the final decision fusion result is obtained by using the Dempster’s rule. Lastly, the simulation and application examples are designed. Simulation and application results show that the method can effectively reduce the impact of diagnostic information conflicts and improve the accuracy of decision fusion. What’s more, the method considers the overall average distribution of evidence in the identification framework, it can reduce evidence conflicts while preserving important diagnostic information.

No abstract

Considering the shortcomings of the existing network key node identification methods based on multiattribute fusion, which have single evaluation methods and low decision accuracy, combined with the advantages of the high accuracy of TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) algorithm and the applicability of grey relational analysis method for incomplete information evaluation, the concept of relative closeness is proposed, and nodes are ranked in importance based on the relative closeness; a key node identification method algorithm based on improved multiattribute fusion is designed. First, the identification problem of key nodes is transformed into multiattribute decision-making method, and the decision matrix is obtained. Second, the weighting matrix is obtained by weighting them in both subjective and objective dimensions, the relative closeness is calculated for the weighting matrix. Finally, sort the network nodes by relative closeness, and network performance simulation experiments are designed using various combinations of evaluation methods and key node identification methods. The simulation results show that this method is more adaptable and improves the identification accuracy of the network key nodes.