最小rbf网设计的进化优选算法跟其在动力配煤过程状态预测建模中的运用.pdfVIP

21 1 Vol. 21 No. 1 Jan. 2001 2001 1 Proceedings of t he CSEE 2001 Chin. Soc. for Elec. Eng . (2001) 0100 305 RBF 魏海坤, 徐嗣鑫, 宋文忠, 吴福保 ( 东南大学自动化研究所, 江苏 南京21009 ) EVOLUTIONARY SELECTING ALGORITHM FOR DESIGNING MINIMAL RBF NETS AND ITS APPLICATION IN COAL BLENDING WEI Haikun, XU Sixin, SONG Wenzhong, WU Fubao ( Institute of Automation, Southeast University, Nanjing 21009 , China) ABSTRACT: This paper proposes an evolutionary selecting algo , rithm (ESA) to design RBF nets. Given an accuracy limit, ESA can design a RBF net with east hidden units, so the network will , , generalize well. Proposed algorithm can be used to establish models of state estimation process for steam coal blending. One of such modeling problems, softening temperature prediction of coal ash, is , BP illustrated using ESA method. Minimal RBF net designed is com [ 1, 2] , , pared with RBF nets obtainedwith OLS and clustering method, re BP : , sult shows that RBF net designed with ESA method has better gen , , eralization ability. BP KEY WORDS: RBF nets; generalization ability; steam coal blending; modeling , ( RBF ) : RBF , [3] RBF RBF , , Moody , RBF , , , [4]