Dynamic Recurrent Neural Network Based Indirect Adaptive Control for Nonlinear Systems

Hussien, Mohamed A.; Mahmoud, Tarek A.; Mahmoud, Mohamed I.

doi:10.21608/mjeer.2017.63423

Dynamic Recurrent Neural Network Based Indirect Adaptive Control for Nonlinear Systems

Document Type : Original Article

Authors

Dept. of Industrial Electronics and Control Eng., Faculty of Electronic Engineering, Menoufia University, Egypt

10.21608/mjeer.2017.63423

Abstract

In this study, an indirect adaptive controller based on dynamic recurrent neural network (DRNN) is developed in the form of the internal model control structure. This control method includes two learning phases, i.e., off-line and on-line learning. In the offline learning, the DRNN is learned by the epoch wise back propagation through time (BPTT) method to represent the forward dynamics of the system to be controlled. In the online phase, the DRNN is used as the internal model of the controlled system and its parameters can be trained by the Truncated BPTT to cope with the possible change in the system dynamics. Hence, the mathematical inversion of the DRNN internal model is computed online to act as the forward controller. Finally, the controller is then obtained by cascading this inverse model with a robust filter and a linear compensator to improve the closed loop performance. The proposed method is applied to a continuous stirred tank reactor (CSTR) with time varying behavior to evaluate the performance of controller.

References

to; -webkit-text-stroke-width: 0px; ">[1] S. Kalogirou, “Artificial intelligence for the modeling and control of
combustion processes: A Review” Progress in Energy and Combustion
Science, vol. 29, pp. 515–566,2003.
[2] D. C. Psichogios and L. H. Ungar, “Direct and indirect model-based
control using artificial neural networks,” Ind. Eng. Chem. Res., vol. 30, pp.
25–64, 1991.
[3] Cabrera, J., Narendra, K., “Issues in the application of neural networks for
tracking based on inverse control, ”IEEE Transaction on Automatic
Control, vol. 44, pp. 2007–2027, 1999.
[4] Hussain, M.A., Kershenbau, L.S., “Implementation of neural networkbased inverse-model control strategies on an exothermic
reactor,”ScienceAsia, vol. 27, pp. 41–50, 2001.
[5] Awais, M.,“Application of internal model control methods to industrial
combustion”. Applied Soft Computing, vol. 5, pp. 223–233, 2005.
[6] Chidrawar, S., Patre, B., “Implementation of neural network for internal
model control and adaptive control,”Proceedings of the International
Conference on Computer and Communication Engineering, Kuala Lumpur,
Malaysia, 2008.
[7] Hua Deng, Zhen Xu, Han-Xiong Li." A novel neural internal model control
for multi-input multi-output nonlinear discrete-time processes”.Journal of
Process Control, vol. 19, 1392–1400, 2009

px; -webkit-text-size-adjust: auto; -w[8] J. Suykens, “Nonlinear modeling and support vector machines,” IEEE
Instrumentation and Measurement Technology Conference, (Budapest
Hungary), 21-23 May 2001.
[9] J. Suykens, J. Vandewalle, and B. D. Moor, “Optimal control by least
squares support vector machines,” Neural Networks, vol. 14, pp. 23–35,
2001.
[10] L. Bin, S. Hong-ye, and C. Jian , “New predictive control algorithms based
on least squares support machines,” Journal of Zhejiang University
Science, vol. 6 , no. 5, pp. 440–446, 2005.
[11] L. Li-Juan, S. Hong-Ye, and C. Jian, “Generalized predictive control with
online least squares support machines,” ActaAutomaticaSinica, vol. 33, no.
11, pp. 1182–1188, 2007.
[12] W. Yao-Nan and Y. Xiao-Fang, “SVM approximate-based internal model
control strategy,” ActaAutomaticaSinica, vol. 34, no. 2, pp. 696–702,2008.
[13] Tarek. A. Mahmoud, “Multi resolution wavelet least squares support
vector machine network for nonlinear system modeling,” Proceedings of
15th International Conference in Automation and Robotics MMAR2010,
Miedzyzdroje, Poland, 23-26 August 2010.
[14] Tarek. A. Mahmoud, “Adaptive control scheme based on the least squares
support vector machine network,” International Journal of Applied
Mathematics and Computer Science, vol. 21, no. 4, pp. 685–696, 2011.
[15] Tarek A. Mahmoud, Lamiaa M. Elshenawy“ Direct Adaptive Control
Based on LS-SVM Inverse Model For Nonlinear Systems ,” Proceedings
of 19th International Conference in Automation and Robotics
MMAR2014, Miedzyzdroje, Poland, 2- 5 September 2014.
[16] Chun-Fei H. , Chin-Min L. , Ang-Bung T., and Chao-Ming C., “Adaptive
control for MIMO uncertain nonlinear systems using recurrent wavelet
neural network,” International Journal of Neural Systems vol. 22, no.1,
2012.
[17] Williams R. J., Zisper D., “An efficient gradient-based algorithm for online training of recurrent networks”. Neural Computation, vol .2, no. 4, pp:
490–50, 1990
[18] B. A. Pearlmutter, “Gradient calculations for dynamic recurrent neural
networks: A survey,” IEEE Trans. Neural Networks, vol. 6, no. 5, pp.
1212–1227, 1995.
[19] Zamarreno J. M., Vega P., "State-Space Neural Network, Properties and
Application", Neural Networks, vol. 11, pp. 1099 - 1112, 1998.
[20] Ku CC and Lee KY, “Diagonal recurrent development neural networks for
dynamic systems control,”IEEE Transactions on Neural Networks vol. 6 ,
No .1, pp. 144–156, 1995.
[21] Levin A. and Narendra K., “Control of nonlinear dynamical systems using
neural networks. ii. observability, identification, and control,” IEEE
Transactions on Neural Networks vol. 7, no. 1, pp. 30–42, 1996.