基于模糊粗糙神经网络的发酵过程建模  

Modeling of Fermentation Process Based on Fuzzy Rough Neural Network

作　　者：李海波[1] 潘丰[2] 

机构地区：[1]无锡商业职业技术学院电子工程系,江苏无锡214153 [2]江南大学控制科学与工程研究中心,江苏无锡214122

出　　处：《计算机测量与控制》2006年第12期1638-1640,1659,共4页Computer Measurement &Control

摘　　要：对于发酵这样一个非线性的动态过程,由于其复杂性和在线传感器的缺乏,使得过程中的一些重要状态变量难以在线测量,从而给发酵过程的优化控制带来了极大的困难,为此,结合模糊粗糙集和智能控制的理论,充分利用模糊粗糙集和神经网络两者的优点,提出了一种新型的网络—模糊粗糙神经网络实现对发酵过程的建模和状态估计,结果表明该网络模型的结构简单,可解释性强,收敛速度快,能够较为准确地拟合过程的动态特性,预估能力较强。Because of the complexity of the process and the lack of biosensor for the fermentation process, some important variables can ＇t be measured on line. The optimization control of the process is difficult. So a new neural network- fuzzy rough neural network is proposed. It is applied to model and predict the variables of the mycetozoan fed batch process. The result has shown that the structure of this kind of neural network model is simple, explicable and the convergent speed is much quicker. It can approximate the dynamic characteristics of the process perfectly. And the predictive precision is high.

关 键 词：模糊粗糙神经网络 建模 发酵过程 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]