利用结构逼近式混合神经网络实现间歇反应器建模.pdfVIP

59 4 Vol59 No4 2008 4 Journal of Chemical Industry and Engineering ( China) pril 2008 曹柳林, 李晓光, 王 晶 (, 100029) : , ! , , ; , , : ; ; ; : TQ 3162 : : 0438- 1157 (2008) 04- 0958- 06 Modelingof batchreactor based onstructureapproaching hybrid neural networks approach CAO Liulin, LIXiaoguang, WAN Jing ( I ns titute of A utomation , S chool of I nf o rmation S cience and Technology , B eij ing Univ er s ity of Chem ical T echnolog y , B e ij ing 100029, Ch ina) Abstract: new hybrid neural networks modeling approach, named structure approaching hybrid neural network ( S HNN) is presented in this paperThe characteristics and structure of this approach are introducedT he approach which combines firstprinciples model with neural networks fully utilizes structural information of known nonlinear system, makes neural networks a greybox!, describes and explains the consequence relation of system variables in a better way detailed analysis of S HNN modeling was performedConsidering delayed measurement of outputs, simulation of a chemical batch reactor was performed and comparison of two types of hybrid neural network ( HNN) was madeThe results of simulation and comparison showed that the approach was a promising tool to model complicated nonlinear system effectively and could be utilized as a vehicle to control and optimize chemical reactors. Key words: S HNN; batch reactor; modeling; HNN , , 2007- 05- 09 , 2007- 09- 16 Received date: 2007-