Research on Intelligence evaluation method of American defense industry capability

The U.S. defense industry involves nuclear, aerospace, aviation, shipping, weapons and electronics in six industries, is a comprehensive equipment research and production system. Scientific research on the process and method of defense industry capability evaluation in the United States has important reference value for perfecting the defense industry capability evaluation system in China. Based on this, this study puts forward the intelligent evaluation model of American defense industry capability. Principal component analysis is used to extract the key factors that affect the capability of the defense industry, so as to avoid the interference of irrelevant factors on the accuracy of the evaluation results. First of all, in order to avoid the contradiction between the calculated results and the objective facts when combining high-conflict evidence sources with DS evidence theory synthesis rules, interpolation method and outlier detection are adopted to correct the monitoring data with large conflict measurement values, and the data set collected by the defense industry capability index system is fused with the improved D-S evidence theory. By calculating the evidence chain conflict measurement value, credibility and weight of evidence, the purpose of correcting conflicting evidence is achieved. The modified evidence chain is fused with Dumpster's rule, and the result of multi-source heterogeneous data fusion is obtained. On this basis, the defense industry capability evaluation system based on TOPSIS method is constructed. Finally, the self-organizing neural network is used for training, and then the American defense industry capability intelligent evaluation model is obtained, and the evaluation results are analyzed. The purpose of this study is to provide technical support for improving and perfecting our national defense industry system in the future.