化工过程建模中的一类复合型模糊神经网络

A Type of Compound Fuzzy Neural Network in Modeling of Chemical Process

针对化工非线性过程建模问题 ,本文提出了一类由函数逼近和规则推理网络构成的复合型模糊神经网络 ,其规则网络基于过程先验知识用于对操作区间的划分 ,而函数网络采用改进型模糊神经网络结构完成非线性函数逼近。该技术已成功地用于某工业尿素CO2 汽提塔液位建模。

A type of compound fuzzy neural network that has a rule network and a function network is proposed in this paper to build model for chemical nonlinear process. Base on process knowledge, the process operation is partitioned into a number of local operating regions by the rule network, and the local behavior of process is approximated by the function network, with its improved fuzzy neural network structure. The techniques have been successfully applied to the modeling of level process of carbon dioxide stripping tower in an industrial urea production.