Radar-aircraft system adversarial simulation confidence evaluation method

Abstract

The invention discloses a radar aircraft system adversarial simulation confidence evaluation method. The method comprises the following steps of automatically encoding index vectors of subsystems of two complex and diverse adversarial parties into low-dimensional feature vectors with fixed dimensions by using a self-encoding model, simplifying index input of a flight target, and inputting the index vectors into a confidence prediction model in a stable form; and based on an attention mechanism of a deep network, guiding training of a confidence evaluation model, using a small amount of radar-aircraft system confrontation actual measurement data as a verification reference, and predicting the confidence of a simulation confrontation system according to the similarity degree of a simulationsystem and an actual measurement system. Therefore, the correlation and influence coefficients generated by the indexes of the input subsystems in the confrontation process are indirectly learned, a weighting matrix does not need to be set manually, and the objectivity of simulation confidence evaluation is improved.

Description

technical field [0001] The invention relates to the technical field of simulation system credibility evaluation, in particular to a radar-aircraft system countermeasure simulation confidence evaluation method. Background technique [0002] When simulating large and complex application systems, it usually involves joint simulation, interaction, and even confrontation between systems of multiple platforms, multi-systems, and multi-functional structures, such as radar system confrontation simulation. The system confrontation simulation system is characterized by multiple levels of structure, a wide range of fields involved, and many related factors. Under the combined effects of multiple factors on both sides of the offense and defense, the uncertainty of the simulation experiment is large. Accurate and objective simulation confidence evaluation is related to the failure of simulation experiments. Objective quantitative evaluation methods include similarity method, confidence ...

AI Technical Summary

Problems solved by technology

[0005] Conventional methods face the problems of poor model versatility, difficulty in objective weighting of the interaction between indicators, difficulty in calculation and difficulty in weighting in the confidence evaluation of system confrontation simulation, and it is difficult to objectively evaluate complex system-level / sub-system-level simulation systems , including:

[0006] (1) The adversarial system contains a large number of subsystems, resulting in complex and diverse indicators for each subsystem. The input format of indicators and the indicator weight matrix need to be adjusted according to the specific system, and the generality of the confidence evaluation model is poor.

When the simulation scene is fine-tuned, the evaluation model needs to be readjusted, which requires a large amount of calculation and high implementation cost

[0007] (2) It is difficult to objectively and accurately assign weights to the influence of indicators caused by confrontation

The confrontation system contains a large number of subsystem indicators, and the influence coefficient between indicators is the square of the number of indicators. The difficulty of weighting increases exponentially with the increase of indicators, and the mechanism of confrontation between indicators is complicated. Conventional weighting methods based on expert knowledge are difficult to be effective. , Objectively construct the weight matrix

Images