一种DEA-PSO混合算法及其在丙烯腈收率软测量中的应用  

A Hybrid Algorithm of DEA and PSO and Its Application to Soft Sensing of Acrylonitrile Yield

作　　者：林晨[1] 俞金寿[1] 

机构地区：[1]华东理工大学自动化研究所,上海200237

出　　处：《华东理工大学学报（自然科学版）》2009年第2期298-301,共4页Journal of East China University of Science and Technology

摘　　要：提出了一种DEA与PSO相结合的混合算法,即用DEA算法对PSO中适应值较差的粒子群进行重组和优化。将此混合算法与PSO算法同时用于一些常见测试函数的优化问题,通过对比表明:与PSO算法相比,DEA-PSO混合算法的优化效果更佳。用DEA-PSO混合算法训练神经网络,并将其用于丙烯腈收率软测量建模,结果显示了该混合算法在丙烯腈软测量建模中的可行性与有效性。A hybrid algorithm of DEA and PSO is proposed, in which the DEA is utilized to improve the bad sub-swarms of PSO. By resolving the optimization problems of several widely used test functions, it is showed that the proposed algorithm has better optimization performance than the standard PSO. Finally, the hybrid algorithm is employed to train the artificial neural network that is applied to soft-sensing of acrylonitrile yield. The results show that the hybrid algorithm is feasible and effective in soft-sensing of acrylonitrile yield.

关 键 词：DNA进化算法(DEA) PSO 丙烯腈 软测量 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]