Prediction of firing accuracy of self-propelled antiaircraft gun in marching fire based on GA-BP neural network

Abstract

The firing efficiency during the marching fire is an important indicator to measure the combat efficiency of self-propelled antiaircraft gun, and it is very important to improve the firing accuracy during the marching fire. In order to understand the coupling mechanism between the firing density and various influencing factors of the self-propelled anti-aircraft guns, this paper combines different driving and shooting conditions to study the factors such as driving speed, road grade, shooting load, the angle of fire and other factors. A method of predicting the firing density of self-propelled anti-aircraft guns during marching is proposed based on the GA-BP neural network. This method not only provides a theoretical basis and indirect measurement for the quantification of the firing density of the self-propelled anti-aircraft guns during the marching, but also has important significance for the distribution and design of the firing accuracy of the self-propelled anti-aircraft guns.