弱连接多子群分子动理论优化算法
A weak linked multi-subpopulation kinetic-molecular theory optimization algorithm

针对分子动理论优化算法拓扑结构与“群集”现象的不足, 提出了一种弱连接多子群分子动理论优化算法. 该 算法分为上下两层, 下层由一系列分子子群执行启发式快速搜索, 以提高算法的收敛速度; 上层中的混沌扰动子群基于 混沌扰动机制, 以便停滞状态的分子子群能跳出局部极值; 上层中的免疫局部学习子群选取下层中的部分优秀个体进行 局部学习, 以实现精细化搜索而提高算法的收敛精度. 仿真结果表明, 该算法在寻优精度、收敛速度以及求解偏移函数 等方面均有良好的性能.
For overcoming the shortcomings of the topology and the ‘cluster’ phenomenon in the kinetic-molecular theory optimization algorithm (KMTOA), based on chaotic mapping and elite learning strategy, a weak linked multisubpopulation kinetic-molecular theory optimization algorithm (WLMS–KMTOA) is proposed in this paper. WLMS– KMTOA includes two layers. In the lower layer, some subgroups perform heuristic search to improve the convergence rate of WLMS–KMTOA. In the upper layer, WLMS–KMTOA uses the chaotic sequence subpopulation to avoid falling into local optimum, and uses immune local learning subgroup to perform a refined search to improve the convergence accuracy. The simulation results show that WLMS–KMTOA has good performance in solution precision and convergence speed, and can be well applied to the functions with different shift values