混沌粒子群混合优化算法的研究与应用

为使粒子群优化算法(PSO)初始粒子均匀分布在解空间,分析了混沌运动的遍历性并根据粒子间欧式距离大小改进了PSO初始种群提取方法。提出了一种混沌粒子群混合优化算法,该算法将优化过程分成两阶段,两分群分别采用PSO算法和混沌优化算法同时进行。对四个高维复杂函数寻优测试表明算法的鲁棒性、收敛速度和精度,全局搜索能力均优于常规PSO。将提出的改进算法用于乙烯收率软测量建模,应用结果表明模型精度较高、泛化性能好。

Study and Application of Chaos- Particle Swarm Optimization-based Hybrid Optimization Algorithm

To make the particles distribute in the problem search space evenly, the ergodicity of chaos was analyzed and the initial population extracting method for particle swarm optimization (PSO) was improved according to their Euclidian distances. A chaos-PSO based hybrid optimization algorithm was proposed. The procedure of optimization was divided into two phases and the particles were divided into two sub-swarms, one sub-swarm searches via PSO and the other searches via chaos algorithm at the same time. Experiments on four complex functions with high dimension show that the improved algorithm outperforms traditional PSO in robustness, converging speed and precision, global searching ability. The improved algorithm was applied to construct a soft sensor model for real-time measuring the ethylene yield. Application results show that this model has high prediction precision as well as good generalization ability.