System combination model credibility intelligent evaluation method based on deep learning

Abstract

The invention provides a system combination model credibility intelligent evaluation method based on deep learning. The system combination model credibility intelligent evaluation method comprises thefollowing steps of obtaining a reference learning sample set, obtaining the reference learning sample set, evaluating uncertainty influence degree, evaluating noise influence degree and evaluating credibility. According to the invention, a deep learning method is applied; uncertainty and influence of noise are comprehensively considered; the credibility evaluation of the to-be-inspected model ismore reliable; a reverse mapping relationship from a simulation learning sample (to-be-inspected model) is applied to a reference learning sample (reference model); a fuzzy phenomenon possibly occurring during forward mapping is avoided, credibility evaluation accuracy is improved, through the deep learning method and the optimization model based on the loss function, implementation difficulty ofsystem combat simulation credibility evaluation is reduced, and adaptive intelligent evaluation and model screening are realized.

Description

technical field [0001] The invention relates to a method for intelligently evaluating the credibility of a system combination model based on deep learning, and belongs to the technical field of system combat simulation modeling. Background technique [0002] As the battlefield environment and confrontation game behavior become more and more complex and changeable, modeling and simulation are becoming more and more important in the research of complex large systems and complex systems, but it also makes it difficult to quantitatively analyze, calculate and evaluate the reliability of system combat simulation. Especially in the pre-concept demonstration and development stages of systems and complex systems, in order to meet the rapid iteration of the scheme, most of them adopt coarse-grained and functional-level simulation models that are oriented to combat tasks and mainly focus on design indicators, so that the credibility of the simulation results How to construct a high-re...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned technical problems, the present invention provides an intelligent evaluation method for the credibility of system combination models based on deep learning, which solves the problem of the reliability of functional-level equipment models. For low-level problems, apply deep learning methods and adaptive optimization methods to convert the credibility of the combined model into the associated probability problem of feature representation, and realize the intelligent evaluation of the credibility of the combined model. While improving the evaluation efficiency, reduce the Uncertainty of the combined model and the influence of noise factors

Images