DocumentCode :
3007586
Title :
Feedforward Decoupling Intelligent Algorithm for Multivariable Based on FNN and Its Application in Biology Fermentation Control
Author :
Liu, Yefei ; Zhao, Dean ; Zhu, Xianglin ; Wang, Yuejun
Author_Institution :
Sch. of Electr. & Inf. Eng., JiangSu Univ., Zhenjiang, China
fYear :
2010
fDate :
25-27 June 2010
Firstpage :
1010
Lastpage :
1013
Abstract :
The coupling relations of all variables during fermentation process with fermentation are discussed. Since the parameters are always changing as time-varying, nonlinearity and randomicity during biology fermentation control process. the scheme for biology fermentation control process using feed forward decoupling intelligent algorithm for multivariable based on FNN is presented. Fuzzy-Neural controller and decoupling units were designed independently, where the Fuzzy controller combined with neural network and the radial basis function neural network was employed for decoupling. The optimized training algorithm based on the system output error was used for online adjustment of network weights, thus realizing dynamic decoupling, which eliminated the need of identifying the plants. This method, with a simple architecture and a small amount of computation is proved to be effective by simulation and application results.
Keywords :
biology; fermentation; fuzzy neural nets; neurocontrollers; radial basis function networks; biology fermentation control process; decoupling units; dynamic decoupling; feed forward decoupling intelligent algorithm; feedforward decoupling intelligent algorithm; fuzzy neural network; fuzzy-neural controller; optimized training algorithm; radial basis function neural network; Algorithm design and analysis; Artificial neural networks; Biology; Control systems; Fuzzy control; Fuzzy neural networks; Heuristic algorithms; Agitation Speed; Coupling; Decoupling Control; Dissolved Oxygen; Fermentation; Fuzzy Neural Network;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electrical and Control Engineering (ICECE), 2010 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-6880-5
Type :
conf
DOI :
10.1109/iCECE.2010.256
Filename :
5631279
Link To Document :
بازگشت