摘要
针对基本PSO算法早熟、搜索精度不高与易陷入局部最优的缺点,结合云滴的随机性、稳定倾向性,提出了一种改进粒子群优化算法(ICPSO)。将改进算法用于模糊神经网络的参数优化,并应用于甲醇单程转化率建模中。仿真实验结果表明:该模型具有较高的精度和较好的泛化能力,能够实现甲醇转化率的实时监测。
By integrating the randomness and stable tendency of cloud droplets, this paper proposes an improved particle swarm algorithm （ICPSO） so as to overcome the premature convergence and easily plunging into the local optimization of the PSO algorithm. And then, the improved algorithm is utilized to optimize the parameters of the fuzzy neural network, which is further applied to the modeling of methanol conversion. The experiment results show that the proposed model has higher precision and better generalization ability, and can realize real-time monitoring of the methanol conversion.
出处
《华东理工大学学报（自然科学版）》
CAS
CSCD
北大核心
2013年第6期697-701,共5页
Journal of East China University of Science and Technology
基金
中央高校基本科研业务费专项资金
国家"863"项目(2009AA04Z141)
上海市重点学科项目(B504)
关键词
粒子群优化算法
云模型
模糊神经网络
甲醇
particle swarm optimization（PSO）
cloud model
fuzzy neural network
methanol
