【作者】 周伟； 卜艳萍；

【Author】 ZHOU Wei 1,BU Yanping 2 1.School of Business,East China University of Science and Technology,Shanghai 200237,P.R.China2.School of Technology,Shanghai Jiaotong University,Shanghai 201101,P.R.China

【机构】 华东理工大学商学院； 上海交通大学技术学院；

【摘要】 本文分析了微粒群优化(PSO)算法这一新兴的群智能优化算法,重点研究了PSO算法与人工神经网络及模拟退火算法的结合。提出了一种基于模拟退火与PSO算法的协同进化方法(SAPSO)。用SAPSO算法训练神经网络,并将其用于高压聚乙烯熔融指数的软测量建模。仿真结果表明,所建模型的泛化性较好,模型具有较高的精度。更多还原

【Abstract】 In this paper,particle swarm optimization(PSO)algorithm is analyzed,which is a new kind of swarm intelligent optimal algorithm.The studies on PSO algorithm concentrate on the combination of artificial neural network and simulated annealing algorithm.A cooperative evolutionary algorithm(SAPSO)based on PSO and simulated annealing algorithm is proposed.The SAPSO algorithm is employed to train artificial neural network and applied to soft-sensing of melt-index of High Pressure Low-Density Polyethylene yield.The simulation results show that these models have higher measuring precision as well as better generalization ability.更多还原