DocumentCode :
2490027
Title :
A new multi-model internal model control scheme based on neural network
Author :
Zhao, Zhicheng ; Liu, Zhiyuan ; Wen, Xinyu ; Zhang, Jianggang
Author_Institution :
Dept. of Control Sci. & Eng., Harbin Inst. of Technol., Harbin
fYear :
2008
fDate :
25-27 June 2008
Firstpage :
4719
Lastpage :
4722
Abstract :
Aiming at the practical plants with strong nonlinear characteristics, a new multi-model internal model control (MIMC) strategy based on Gaussian potential function networks (GPFN) is proposed in this paper. The internal model is represented by GPFN and the corresponding controller can be got directly, which simplifies the control law design and analyses greatly. Meanwhile, the way of model switch is developed based on fuzzy decision. This MIMC scheme avoids the complex calculation when adjusting the controller parameter and overcomes the switch vibration. Simulation results demonstrate that the strategy has advantage of internal model control (IMC) and multi-model control and could achieve better system performance than the conventional IMC (CIMC).
Keywords :
control system analysis; control system synthesis; neurocontrollers; nonlinear control systems; Gaussian potential function networks; fuzzy decision; multimodel internal model control scheme; neural network; Automatic control; Automation; Control system synthesis; Inverse problems; Neural networks; Nonlinear control systems; Open loop systems; Process control; Switches; System performance; GPFN; Multi-model control; internal model control; nonlinear system;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
Type :
conf
DOI :
10.1109/WCICA.2008.4593686
Filename :
4593686
Link To Document :
بازگشت