Optimal aiming point selection method for multi-projectile strikes on complex area targets

To address the optimal aiming point selection problem for multi-projectile strikes on complex-shaped area targets, a multi-head attention particle swarm optimization (MHAPSO) algorithm is proposed to optimize the best aiming points for multiple projectiles. In developing the aiming point selection model, multiple complex factors affecting the damage effectiveness against area targets are comprehensively considered. These include the target area’s shape, area correlation, ammunition power area, ammunition hit accuracy, and cumulative damage. The PSO algorithm is improved by dividing different attention groups and designing an inter-group particle flow mechanism, which enhances its convergence speed without compromising global search capability. The performance of the algorithm is verified through typical test cases of complex area targets. The research results show that compared to the Monte Carlo algorithm, PSO algorithm, and the improved grey wolf optimizer (IGWO) algorithm, the MHAPSO algorithm demonstrates superior aiming point selection capability. It achieves an average increase of 6.7% in damage yield, while requiring only 20%∼40% of the average computation time and 60%∼80% of the average ammunition expenditure required by other methods. Thus, the MHAPSO algorithm holds significant advantages in both damage yield and computational efficiency. Furthermore, the proposed MHAPSO framework is not confined to military applications; it represents a generalized model for polygon-region coverage and resource allocation optimization that is broadly transferable across multiple domains, including wildfire suppression target selection, industrial facility protection layout planning, wireless communication coverage optimization, and UAV-based disaster relief logistics distribution.