Call for Paper - November 2022 Edition
IJCA solicits original research papers for the November 2022 Edition. Last date of manuscript submission is October 20, 2022. Read More

System Identification of Thermal Process using Elman Neural Networks with No Prior Knowledge of System Dynamics

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2017
Authors:
Ibraheem Kasim Ibraheem
10.5120/ijca2017913316

Ibraheem Kasim Ibraheem. System Identification of Thermal Process using Elman Neural Networks with No Prior Knowledge of System Dynamics. International Journal of Computer Applications 161(11):38-46, March 2017. BibTeX

@article{10.5120/ijca2017913316,
	author = {Ibraheem Kasim Ibraheem},
	title = {System Identification of Thermal Process using Elman Neural Networks with No Prior Knowledge of System Dynamics},
	journal = {International Journal of Computer Applications},
	issue_date = {March 2017},
	volume = {161},
	number = {11},
	month = {Mar},
	year = {2017},
	issn = {0975-8887},
	pages = {38-46},
	numpages = {9},
	url = {http://www.ijcaonline.org/archives/volume161/number11/27194-2017913316},
	doi = {10.5120/ijca2017913316},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

Dynamic Neural networks have been verified as identifiers due to its capability for manipulating processes in parallel and enduring noisy sorts of the input signals. They make them outstanding contenders for system identification applications. This paper presents a method for a black box system identification based on Elman neural network (ENN) for thermal process system to generate a prototype for the dynamical system of the thermal process without any past information about the system dynamics. This identification approach is compared to its counterpart conventional feedforward neural network (CFFNN) based system identification. The comparative simulations show that the ERNN gives an excellent results and outperforms the CFFNN in terms of accuracy with little degradation in the speed of convergence which make this neural network a motivating candidate for adaptive and gain scheduling controllers.

References

  1. Dong, Ze, Pu Han, Dongfeng Wang, and Songming Jiao. "Thermal Process System Identification Using Particle Swarm Optimization." In 2006 IEEE International Symposium on Industrial Electronics, vol. 1, pp. 194-198. IEEE, 2006.
  2. Liu, Tao, Ke Yao, and Furong Gao. "Identification and autotuning of temperature-control system with application to injection molding." IEEE transactions on control systems technology 17, no. 6 (2009): 1282-1294.
  3. Esfandiari, Ramin S., and Bei Lu. Modeling and analysis of dynamic systems. CRC Press, 2014.
  4. Linhares, Leandro LS, Aluisio IR Fontes, Allan M. Martins, Fábio MU Araújo, and Luiz FQ Silveira. "Fuzzy Wavelet Neural Network Using a Correntropy Criterion for Nonlinear System Identification." Mathematical Problems in Engineering 2015 (2015).
  5. Toha, Siti Fauziah, and M. Osman Tokhi. "MLP and Elman recurrent neural network modeling for the TRMS." In Cybernetic Intelligent Systems, 2008. CIS 2008. 7th IEEE International Conference on, pp. 1-6. IEEE, 2008.
  6. Rout, Ajit Kumar, P. K. Dash, Rajashree Dash, and Ranjeeta Bisoi. "Forecasting financial time series using a low complexity recurrent neural network and evolutionary learning approach." Journal of King Saud University-Computer and Information Sciences (2015).
  7. Horvath, Gábor. "Neural networks in system identification." Nato Science Sub-Series III Computer And Systems Sciences 185 (2003): 43-78.
  8. Scarpiniti, Michele, Danilo Comminiello, Raffaele Parisi, and Aurelio Uncini. "Novel cascade spline architectures for the identification of nonlinear systems." IEEE Transactions on Circuits and Systems I: Regular Papers 62, no. 7 (2015): 1825-1835.
  9. Liu, Changliang, and Xiaojiao Sun. "Electromagnetism-like mechanism particle swarm optimization and application in thermal process model identification." In Control and Decision Conference (CCDC), 2010 Chinese, pp. 2966-2970. IEEE, 2010.
  10. Maachou, Asma, Rachid Malti, Pierre Melchior, Jean-Luc Battaglia, Alain Oustaloup, and Bruno Hay. "Nonlinear thermal system identification using fractional Volterra series." Control Engineering Practice 29 (2014): 50-60.
  11. Pan, Wei, Ye Yuan, Jorge Gonçalves, and Guy-Bart Stan. "A sparse Bayesian approach to the identification of nonlinear state-space systems." IEEE Transactions on Automatic Control 61, no. 1 (2016): 182-187.
  12. Scarpiniti, Michele, Danilo Comminiello, Raffaele Parisi, and Aurelio Uncini. "Nonlinear system identification using IIR spline adaptive filters." Signal Processing 108 (2015): 30-35.
  13. Tavakolpour-Saleh, A. R., S. A. R. Nasib, A. Sepasyan, and S. M. Hashemi. "Parametric and nonparametric system identification of an experimental turbojet engine." Aerospace Science and Technology 43 (2015): 21-29.
  14. Li, Zongjian, Yuling Chen, Weichao Fang, Zhengjiang Zhang, Guoqiang Zeng, and Yuxing Dai. "Research on parameter identification method based on finite measurement information for photovoltaic array model." In Control Conference (CCC), 2014 33rd Chinese, pp. 6465-6470. IEEE, 2014.
  15. Shobana, R., C. Sreepradha, S. Sobana, and Rames C. Panda. "Identification and Estimation of temperature in Nitration process." In Technological Innovation in ICT for Agriculture and Rural Development (TIAR), 2015 IEEE, pp. 165-170. IEEE, 2015.
  16. Wang, Jeen-Shing, and Yen-Ping Chen. "A fully automated recurrent neural network for unknown dynamic system identification and control." IEEE Transactions on Circuits and Systems I: Regular Papers 53, no. 6 (2006): 1363-1372.
  17. Sebakhy, O. A., H. M. A. Kader, W. A. Youssef, and S. Deghiedi. "Identification of linear discrete time systems using linear recurrent neural networks." In Industrial Electronics, 1996. ISIE'96., Proceedings of the IEEE International Symposium on, vol. 1, pp. 374-379. IEEE, 1996.
  18. Nouri, Khaled, Rached Dhaouadi, and N. Benhadj Braiek. "Identification of a nonlinear dynamic systems using recurrent multilayer neural networks." In Systems, Man and Cybernetics, 2002 IEEE International Conference on, vol. 5, pp. 5-pp. IEEE, 2002.
  19. Fan, Bo, Xing Li, Guanghui Shi, and Weigang Zhao. "Motor rotor resistance identification based on Elman neural network." In 2012 IEEE International Conference on Automation and Logistics, pp. 196-200. IEEE, 2012.
  20. Zhang, Wenjun, Zhengjiang Liu, Jinshan Zhu, and Xiaoka Xu. "Identification and control of time-delay system with recurrent wavelet neural networks." In Intelligent Control and Information Processing (ICICIP), 2012 Third International Conference on, pp. 211-216. IEEE, 2012.
  21. Khalil, Rafid Ahmed. "Comparison of Four Neural Network Learning Methods Based on Genetic Algorithm for Non-linear Dynamic Systems Identification." Al-Rafadain Engineering Journal 20, no. 1 (2012).
  22. array, Fakhreddine O., and Clarence W. De Silva. Soft computing and intelligent systems design: theory, tools, and applications. Pearson Education, 2004.
  23. Nguyen, Hung T., Nadipuram R. Prasad, Carol L. Walker, and Elbert A. Walker. A first course in fuzzy and neural control. CRC press, 2002.
  24. Narendra, Kumpati S., and Kannan Parthasarathy. "Identification and control of dynamical systems using neural networks." IEEE Transactions on neural networks 1, no. 1 (1990): 4-27.
  25. Gao, X. Z., X. M. Gao, and S. J. Ovaska. "A modified Elman neural network model with application to dynamical systems identification." In Systems, Man, and Cybernetics, 1996., IEEE International Conference on, vol. 2, pp. 1376-1381. IEEE, 1996.
  26. Kalinli, Adem, and Seref Sagiroglu. " Elman Network with Embedded Memory for System Identification " Journal of Information Science and Engineering 22 (2006): 1555-1568.
  27. Pham, D. T., and X. Liu. "Training of Elman networks and dynamic system modelling." International Journal of Systems Science 27, no. 2 (1996): 221-226.
  28. Ogata, Katanhiko. "Modern Control Engineering,(1997)." ISBN: 0-13-227307-1: 299-231.

Keywords

Backpropagation algorithm, Elman neural networks, black box modeling, online training, offline training