The Application of Self-learning Controller in Fermentation Process
In fermentation process, conventional control algorithm usually cannot produce an efficient control and it is difficult to realize a stable control. Although some advance control algorithm can raise the production e±ciency, they usually need much more prior knowledge and depend heavily on the accuracy of process modelling. This paper presents an introduc- tion to use fuzzy-neural network method in fermentation process. Fuzzy logic can be used in the control processes with properties of fuzzy, uncertainty, highorder and heavy lag and these control processes without accurate mathematics model. The neural network method has the advantage of self-learning, memory ability, fault-tolerant and parallel processing. It takes the counter propagation network (CPN) as framework, combining an improved fuzzy control algorithm, to realize the fuzzy-neural control of fermentation process. The method has the ability of self-organizing and self-learning from control knowledge needed in fermentation process. The rule database initially is empty and then it is gradually self-constructed to meet the performance index. Simulation results proved the proposed method can realize the ability of self-learning.
Gui-cheng Wang Min Zhang Yong Wang Xinhe Xu
College of Information Engineering Shenyang Institute of Chemical Technology Shenyang 110142, China; College of Information Engineering Shenyang Institute of Chemical Technology Shenyang 110142, China College of Information Science and Engineering Northeastern University Shenyang 110004, China
国际会议
青岛
英文
2006-07-21（万方平台首次上网日期，不代表论文的发表时间）