The article presents mathematical models, numerical algorithms and a software package for an intelligent system for artillery mount autonomous guidance and adjustment of firing. The software package includes the following components: a module for solving the direct problem of external ballistics, a neural network training module, and a firing guidance and adjustment module. The first module is designed to form a database of computational experiments by repeatedly solving the direct problem of external ballistics under varying firing conditions. In the second module, a neural network is trained to solve the inverse problem of external ballistics using the database generated from computational experiments. The third module implements algorithms for calculating the artillery mount launching angles on a target using a trained neural network and calculating corrections to launching angles based on data on the projectile impact point deviation from the target. Having received data on the artillery mount readiness to fire, the coordinates of the target position and projectile’s impact point received from a digital observer, the software package calculates the necessary launching angles or corrections to them. Launching angles are transferred via text files to the control system of the artillery mount drives, then a shot is fired and the conditions for hitting the target are assessed. The algorithm is then repeated for the next shot or new target. Testing of the developed algorithms for autonomous guidance and shooting correction was carried out using modeling of external ballistics processes in the software package, as well as carrying out experimental testing on a working simulation device of an artillery mount. The developed software package allows visualization of the obtained results and saving the history of the performed operations.
Read full abstract