| 混沌混合粒子群算法应用于优化酯化反应神经网络模型 |
| |
| 引用本文： | 张立庆,程志刚,吴晓华,李小林,盛煜翔. 混沌混合粒子群算法应用于优化酯化反应神经网络模型[J]. 计算机与应用化学, 2007, 24(8): 1073-1077 |
| |
| 作者姓名： | 张立庆 程志刚 吴晓华 李小林 盛煜翔 |
| |
| 作者单位： | 浙江科技学院生物与化学工程学院,浙江,杭州,310012;浙江科技学院信息与电子工程学院,浙江,杭州,310012;浙江大学材料与化学工程学院,浙江,杭州,310027 |
| |
| 基金项目： | 浙江省自然科学基金项目(Y404082)，浙江省教育厅重点科研计划项目(20030836) |
| |
| 摘 要： | 利用混沌映射的随机性和遍历性,将其引入粒子群优化算法,以提高算法的全局寻优能力,同时引入优进策略,以改善其局部寻优效率,在此基础上构建了混沌混合粒子群优化算法(CHPSO)。高维复杂函数的仿真优化试验表明,CHPSO全局寻优能力强、优化效率高。针对常规算法训练神经网络容易早熟收敛和陷入局部极值点的不足,采用CHPSO训练人工神经网络,由此构建CHPSO-NN模型,并应用于乙酸己酯催化酯化反应条件的建模,与BP-NN相比,其预测能力和稳健性都有较大提高,效果良好,与传统方法相比有明显的优越性。
|
| 关 键 词： | 混沌 优进 粒子群优化 神经网络 酯化 |
| 文章编号： | 1001-4160（2007）08-1073-1077 |
| 修稿时间： | 2006-10-13 |
Chaotic hybrid particle swarm optimization algorithm and its application in optimization of ANN model of esterification |
| |
| Zhang Liqing,Cheng Zhigang,Wu Xiaohua,Li Xiaolin,Sheng Yuxiang. Chaotic hybrid particle swarm optimization algorithm and its application in optimization of ANN model of esterification[J]. Computers and Applied Chemistry, 2007, 24(8): 1073-1077 |
| |
| Authors: | Zhang Liqing Cheng Zhigang Wu Xiaohua Li Xiaolin Sheng Yuxiang |
| |
| Affiliation: | 1. School of Biological and Chemical Engineering, Zhejiang University of Science and Technology, Hangzhou, 310012, Zhejiang, China; 2. School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, 310012, Zhejiang, China; 3. College of Materials Science and Chemical Engineering, Zhejiang University, Hangzhou, 310027, Zhejiang, China |
| |
| Abstract: | a new algorithm,which is named as chaotic hybrid particle swarm optimization algorithm (CHPSO),is proposed.CHPSO integrates chaotic mechanism for its ergodicity,stochastic property,and regularity,whieh enhance the global exploitation.And also in- tegrates the eugenic strategy to improve the local exploration.Simulation results on high dimensional eomphx functions shows that CHP- SO has powerful global optimization ability and high optimization efficiency.Then CHPSO was proposed to training Neural Networks, named CHPSO-ANN,to establish reaction model for esterification of hexyl acetate,the predict ability and stability of results have a quite increase compared with the traditional BP-ANN method. |
| |
| Keywords: | chaotic eugenic particle swarm optimization neural networks esterification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
