A Study on Artillery Firing Data Solving Method Based on Improved Genetic Algorithm

Abstract

Artillery, as the primary firepower weapon for ground and naval forces, plays a crucial role in modern warfare. However, modern information warfare poses severe challenges to artillery systems. An efficient and accurate artillery firing data resolution algorithm is a crucial component in enabling modern combat capabilities for artillery. In response to these challenges, this paper proposes an improved genetic algorithm (GA-LFPSO) for solving artillery firing data. The proposed algorithm addresses and improves upon issues such as population initialization, local optimum problems, and calculation efficiency. The initialization of the algorithm’s population incorporates initial solutions based on Levy flight to enhance population diversity. Additionally, the genetic algorithm integrates the particle swarm optimization algorithm by guiding the population’s iterative selection with optimal solutions generated during its iterations, further enhancing the convergence speed of the algorithm. In the final phase of the algorithm, new individuals are generated using Levy flight based on a portion of the existing individuals and integrated into the population, thereby improving the algorithm’s global search capability. To validate the algorithm, simulations were conducted using a ballistic model and compared with four other algorithms. The results demonstrate that the proposed GA-LFPSO algorithm exhibits rapid convergence, robust search capabilities, and exceptional performance in solving the firing data.

Keywords

• Firing data
• ballistic model
• genetic algorithm
• Levy flight
• particle swarm optimization