Call for Paper - March 2023 Edition
IJCA solicits original research papers for the March 2023 Edition. Last date of manuscript submission is February 20, 2023. Read More

Neural Network - based Control Strategies Applied to a Chemical Reactor Process

Print
PDF
IJCA Proceedings on National Conference on Recent Trends in Computing
© 2012 by IJCA Journal
NCRTC - Number 7
Year of Publication: 2012
Authors:
Swapnaja Chidrawar
Sadhana Chidrawar

Swapnaja Chidrawar and Sadhana Chidrawar. Article: Neural Network - based Control Strategies Applied to a Chemical Reactor Process. IJCA Proceedings on National Conference on Recent Trends in Computing NCRTC(7):32-34, May 2012. Full text available. BibTeX

@article{key:article,
	author = {Swapnaja Chidrawar and Sadhana Chidrawar},
	title = {Article: Neural Network - based Control Strategies Applied to a Chemical Reactor Process},
	journal = {IJCA Proceedings on National Conference on Recent Trends in Computing},
	year = {2012},
	volume = {NCRTC},
	number = {7},
	pages = {32-34},
	month = {May},
	note = {Full text available}
}

Abstract

This paper is focused on issues of process modeling and model based control strategy of chemical reactor process applying the concept of artificial neural networks (ANNs). The control objective is to force the operation into optimal supersaturating trajectory. It is achieved by; manipulating coolant flow rate, the influent concentration of compound is control. Model predictive control (MPC) alternative is considered. Adequate ANN process models are first built as part of the controller structures. MPC algorithm outperforms satisfactory reference tracking and smooth control action while for the IMC an analytical control solution was determined.

References

  • M. A. Hussain, Marwan Shamel Malik,M. Z. Sulaiman and A. K. Abdul Wahab. "Design and control of an experimental partially simulated exothermic reactor system" Regional symposium of chemical engineering 1999 Proceeding, volume II, Nov 1999.
  • S. Haykin S. (1994), Neural networks: A comprehensive foundation, Prentice Hall, UK.
  • Zorzetto L. F. M. ,R. Maciel Filho and M. R. Wolf-Maciel(2000), Process modeling development through ANN and hybrid models, Computers and chemical engineering,24,1355-1360.
  • Mayne D. Q. , J. B. Rawlings, C. V. Rao, P. O. M. Scokaert (2000), constrained model predictive control: stability and optimality, Automatica, 36789—814.
  • Cabera J. B. D. , K. S. Narendra (1999), Issues in the applicatin of neural networks for training based on inverse control, IEEE Transaction on automatic control special issue on neural networks for control identification and decision making, 44(11), 2007-2027
  • Lingiji Ch. , K. S. Narendra (2001) Nonlinear adaptive control using neural networks and multiple models, Automatica, special issue on neural network feedback control, 37(8), 1245-1255.
  • Rumelhart,D. E. &MccClelland,J. L. ,(1986). Parallel distributed processing,Cambridge,MA:MIT press.
  • Fu-Chuang Chen and Hassank K. Khalil, (1992) Adaptive control of nonlinear systems using neural networks, International journal of control, vol. 55, No. 6, pp. 1299-1317.
  • Hunt K. J. and Gawthrop P. J. ; (1994) Neural network for control – A survey, Automatics vol. 28 no. 6, pp. 1183-1112.
  • Lawrynczuk. M. ,(2007) An efficient nonlinear predictive control algorithm with neural models based on multipoint online linearization. EUROCON 2007. The international conference on computer asa ool ,Warsaw. pp. 777-784.