Desired Impact Time Range Based on BP Neural Network

This paper focuses on the analysis of the desired impact time range under multiple constraints. In order to solve the problem that the precision of the traditional formula method is not high enough to calculate the time range, this paper proposes, for the first time, the application of a BP neural network to address the problem, thereby mitigating the failure of the salvo attack. First, a specific guidance law with multiple constraints was selected, and it was demonstrated that the desired impact time range cannot be accurately solved by the traditional formula method, which leads to miss. Secondly, analyzed the parameters that affected the guidance time range, and carried out sensitivity analysis on them, so as to obtain the influence degree of each parameter on the range, and reduced the sample size while ensuring accuracy. Then, the binary search method was applied to obtain the impact time range, in order to obtain the samples. After obtained the samples, the BP neural network was used to train the samples. Finally, the accuracy of this method was verified by simulation, which provided an important premise for salvo attacks.