基于改进粒子群算法的多传感器探测联盟模型

Multi-sensor Detection Alliance Model Based on Improved Particle Swarm Optimization Algorithm

针对传统多传感器联盟在进行目标分配时考虑要素不全面、算法收敛慢、求解质量低等问题,提出了一种基于改进粒子群算法的多传感器探测联盟模型。通过增加目标威胁度的因素构建多传感器多目标分配模型,同时在改进粒子群算法中,赋予粒子负强化因子和碰撞因子,使粒子能够进行负向学习并具有能够跳出局部最优的能力。仿真结果表明,与基本粒子群算法和其他算法相比,改进后的算法有着更快的收敛速度,且得到的探测联盟的解的质量也更高。

Aiming at the problems of such traditional multi-sensor alliance in target allocation,as incomplete consideration of elements,slow convergence rate of algorithm and low quality of solution,a multi-sensor detection alliance model based on improved particle swarm algorithm is proposed.The multi-sensor and multi-target allocation model is established by adding target threat factor.At the same time,in the improved particle swarm optimization algorithm,negative reinforcement factor and collision factor are assigned to particles in the improved particle swarm algorithm,so that particles can learn from mistakes and have the ability to jump out of local optimum.The simulation results show that the improved algorithm has faster convergence speed and higher solution quality than the basic particle swarm algorithm and other algorithms.