Integrated neuro-fuzzy model and dynamic R-parameter based quadratic criterion-iterative learning control for batch process

  • Authors:

  • Li Jia;Jiping Shi;Min-Sen Chiu

  • Affiliations:

  • Shanghai Key Laboratory of Power Station Automation Technology, Department of Automation, College of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, China;Shanghai Key Laboratory of Power Station Automation Technology, Department of Automation, College of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, China;Department of Chemical and Biomolecular Engineering, National University of Singapore, Singapore

  • Venue:
  • Neurocomputing
  • Year:
  • 2012

Quantified Score

Hi-index 0.01

Visualization

Abstract

Considering the potentials of iterative learning control as a framework for industrial batch process control and optimization, an integrated neuro-fuzzy model and dynamic R-parameter based quadratic criterion-iterative learning control is proposed in this paper. Firstly, a novel integrated neuro-fuzzy model is used to obtain more accurate model of batch processes, which is not only along the time axle but also along batch axle. Next, quadratic criterion-iterative learning control with dynamic parameters is used to improve the performance of iterative learning control. As a result, the proposed method can avoid the problem of initialization of the optimization controller parameters, which are usually resorted to trial and error procedure in the existing iterative algorithms. Moreover, we make the first attempt to give rigorous description and proof to verify that a perfect tracking performance can be obtained, which are normally obtained only on the basis of the simulation results in the previous works. Lastly, examples are used to illustrate the performance and applicability of the proposed method.