Multi-Objective Firepower Planning Research Based on Dual-Driven Decision Tree Genetic Algorithm

本文构建“射程筛选–智能分类–优化求解”的分层理论框架，融合欧氏距离模型、决策树与改进遗传算法，通过数学建模与智能算法实现目标可打击性评估、威胁分类及火力分配优化。仿真验证表明，该方法在经济代价、弹药利用率与收敛速度上显著优于传统模式，为炮兵智能化指挥决策提供了理论研究思路。Fire planning faces challenges such as data overload, decision-making complexity in modern informatized battlefields. The paper proposes a hierarchical theoretical framework “range screening, intelligent classification, priority ranking, and optimization solving”, integrating Euclidean distance models, decision trees, and an improved genetic algorithm. Through mathematical modeling and intelligent algorithms, the method enables assessable target strike feasibility, threat classification, and optimized firepower allocation. Simulation results demonstrate its significant superiority over traditional approaches in cost efficiency, ammunition utilization, and convergence speed, offering a theoretical foundation for intelligent artillery command and decision-making.