电厂烟气含氧量智能混合预测方法.pdfVIP

31 8 Vol31 No8 2010 8 Ch inese Journal of Scientific Instrum ent Aug. 2010 * 湛腾西, 郭观七 ( 4 14006) : , RBF ; ; , , ; , , , : ; ; RBF ; ; ; : TP273 : A : 510. 8099 Intelligent hybrid prediction method of the flue gas oxygen content in power plant Zhan Tengx,i Guo Guanqi (School of Inf orm ation and Comm unication Eng ineering, H unan Institute of Science and Technology, Yueyang 414006, China) Abstract: A mi ing at the fact that the pow er p lant flue gas oxygen content is har to pre ict effectively, an intelligent hybri pre iction metho is propose . F irstly, RBF neural newt ork an principal component analysismetho are uti lize to re uce the mi ension of the input variables; secon ly, the casebase reasoningmetho is a opte to pre ict the flue gas oxygen content from the above analysis results. Then in or er to reflect the tmi e cumulative effect of the flue gas oxygen conten,t the process neural netw ork m etho isuse to pre ict the current flue gas oxygen content val ue. F inally the final flue gas oxygen content is obtaine using variancecovariancemetho ofw eight combination fore casting. The results of actual operation ata analysis an in ustrial trial operation show that the propose intelligent hybri pre iction mo el has high accuracy an robustness, an can effectively solve the problem of pre icting flue gas oxygen content. Key words: flue gas oxygen content; intelligent hybri pre iction metho ; RBF neural newt ork; principal compo nent analysis; casebase reasoning; process neural network , 1 , , , , ,