基于海洋捕食者算法的武器-目标分配问题研究

Research on weapons-target assignment problem for marine predator algorithm

为了提高武器-目标分配问题的求解效率和质量,给出一种基于改进海洋捕食者算法的求解策略。首先,给出基于反向学习策略的种群初始化改进方案,初始种群中一半的个体随机生成,另一半个体基于反向学习策略给出,提高了算法的收敛速度;其次,应用基于自适应参数的轮盘赌法对猎物更新方式进行了改进以增强其随机性,以及协调算法全局与局部搜索能力。最后,将其与遗传算法、粒子群算法、蜻蜓算法与鲸鱼优化算法之仿真值进行对比,结果表明:改进海洋捕食者算法具有更快收敛速度、更强的全局搜索能力及更高的稳定性,有望应用于未来战争的指挥决策中。

A solving strategy based on the improved marine predator algorithm was proposed for better efficiency and quality.We proposed a modified population initialization scheme,where half of the individuals in initial population were randomly generated and the other half were given based on reverse learning strategy.This scheme improved the convergence speed of the algorithm.And we applied the adaptive parameter-based roulette wheel method to enhance the randomness of prey updating and balance the capability between global searching and local searching.Finally,we simulated and compared the proposed strategy with genetic algorithm,particle swarm optimization,dragonfly algorithm and whale optimization algorithm.The result showed that the improved marine predator algorithm had faster convergence speed,stronger global searching ability and higher stability,which is expected to be applied in command decision of future war.