作战仿真中火力分配优化算法研究

Algorithm Research on Fire Distribution Optimization for Combat Simulation

火力分配优化是作战仿真中的一个重要内容,其结果的精确度直接影响到作战仿真的可信度。为提高火力分配的快速性和精准性,将免疫遗传算法和量子遗传算法相结合,利用免疫克隆、免疫记忆、免疫平衡算子改善优化量子遗传算法,引入先验知识和局部最优解来提高算法的收敛精度、收敛速度和稳定性。实验结果证明,在容量各异抗体记忆库的条件下,量子免疫遗传算法可有效解决作战仿真火力分配优化问题,与常用的基本遗传算法、量子遗传算法、免疫遗传算法相比,具有收敛速度快、稳定性好、无明显早熟形象等特点。

Fire distribution optimization which will impact the last reliability is an important part of combat simu- lation. This paper integrated immune genetic algorithm and quantum genetic algorithm an used immune clonal, im- mune memory and immune balance to improve quantum genetic algorithm. Prior knowledge and local information were introduced to enhance algorithm precision, speed and stability. Under the condition of different sizes of antibody memory pool, the test results prove that the quantum immune genetic algorithm can solve fire distribution optimization problem effectively, and has fast speed convergence, better stability and less precocity compared with standard genet- ic algorithm, quantum genetic algorithm and immune genetic algorithm