Model Reference Adaptive Control based on a Simplified Recurrent Neural Network Trained by Gbest-Guided Gravitational Search Algorithm to Control Nonlinear Systems

  • Omar Farouq Lutfy Assistant Prof. Dr., University of Technology, Baghdad, Iraq
  • Ahmed Lateef Jassim Engineer, University of Technology, Baghdad, Iraq
Keywords: Modified Elman neural network, modified recurrent neural network, artificial neural network, gbest-guided gravitational search algorithm, model reference adaptive control.


This paper presents an intelligent Model Reference Adaptive Control (MRAC) strategy based on a Simplified Recurrent Neural Network (SRNN) for nonlinear dynamical systems. This network is an enhanced version of a previously reported modified recurrent network (MRN). More precisely, the enhancement in the SRNN structure was realized by employing unity weight values between the context and the hidden layers in the original MRN structure. The newly developed Gbest-guided Gravitational Search Algorithm (GGSA) was adopted for optimizing the parameters of the SRNN structure. To show the efficiency of the proposed SRNN-based MRAC, three different nonlinear systems were considered as case studies, including complex difference equations and the water bath temperature control system. From an extensive set of evaluation tests, which includes a control performance test, a disturbance rejection test, and a generalization test, the proposed SRNN-based MRAC system demonstrated its effectiveness with regards to precise control and good robustness and generalization abilities. Furthermore, compared to other Neural Network (NN) structures, including the original MRN and the Multilayer Perceptron (MLP) NN, the SRNN structure attained superior results due to the utilization of a reduced set of parameters. From another study, the GGSA accomplished the best optimization results in terms of control precision and convergence speed compared to the original Gravitational Search Algorithm (GSA).


Y.-C. Cheng, W.-M. Qi, and W.-Y. Cai, “Dynamic properties of Elman and modified Elman neural network,” Proceedings of the 1st Int. Conference on Machine Learning and Cybernetics, Beijing, PP. 637-640, 2002.

A. I. Abdulkareem, “Identification of Dynamical Systems using Recurrent Neural networks with Structure Optimization Utilizing Genetic Algorithms,” Engineering and Technology Journal, Vol.24, Part A, No.2, PP.129–139, 2005.

L.C. Jain, and L.R. Medsker, “Recurrent Neural Networks: Design and Applications,” CRC Press, 1st ed., London, 1999.

N.A. Shiltagh, “A training algorithm for partial recurrent neural networks and its applications for system identification and control,” Ph.D. Thesis, Control and Computer Eng. Dept., Univ. of Technology, Baghdad, Iraq, 2001.

J.L. Elman, “Finding structure in time,” Cognitive science, Vol. 14, PP. 179-211, 1990.

D.T. Pham, and X. Liu, “Neural Networks for Identification, Prediction and Control,” Springer-Verlag, 1st ed., London, Ch. 3, PP. 47-61, 1995.

K.-K. Shyu, and H.-J. Shieh, S.-S. Fu, “Model Reference Adaptive Speed Control for Induction Motor Drive Using Neural Networks,” IEEE Trans Ind Electron, Vol. 45, PP. 180-182. 1998.

H.-W. Ge, et al., “Identification and control of nonlinear systems by a dissimilation particle swarm optimization-based Elman neural network,” Nonlinear Analysis: Real World Applications, Vol. 9, PP. 1345-1360, 2008.

A.Thammano, and P. Ruxpakawong, “Nonlinear dynamic system identification using recurrent neural network with multi-segment piecewise-linear connection weight,” Memetic Computing, Vol. 2, PP. 273-282, 2010.

J. Ma, and R. Zhang, “Model Reference Adaptive Neural Sliding Mode control for Aero-engine,” AASRI Procedia, Vol. 3, PP. 508-514. 2012.

C. Zhou, L.Y. Ding, and R. He,, “PSO-based Elman neural network model for predictive control of air chamber pressure in slurry shield tunneling under Yangtze River,” Automation in Construction, Vol. 36, PP. 208-217, 2013.

C.-H. Huang, “Modified neural network for dynamic control and operation of a hybrid generation systems,” Journal of applied research and technology, Vol. 12, PP. 1154-1164. 2014.

Y. Fang, J. Fei, and K. Ma, “Model reference adaptive sliding mode control using RBF neural network for active power filter,” Electrical Power and Energy Systems, Vol. 73, PP. 249-258. 2015.

M. Bahita, and K. Belarbi, “Model Reference Neural-Fuzzy Adaptive Control of the Concentration in a Chemical Reactor (CSTR),” IFAC-PapersOnLine, Vol. 49, PP. 158-162. 2016.

O. F. Lutfy, and M. H. Dawood, “Model Reference Adaptive Control based on a Self-Recurrent Wavelet Neural Network Utilizing Micro Artificial Immune Systems,” Al-Khwarizmi Engineering Journal, Vol. 13, PP. 107-122. 2017.

X. Gao, X. Gao, and S. Ovaska, “A modified Elman neural network model with application to dynamical systems identification,” IEEE International Conference in Systems, Man, and Cybernetics. Information Intelligence and Systems, Beijing, China, PP. 1376-1381, 1996.

G. Ren, Y. Caoa, S. Wena, T. Huangc, and Z. Zeng, “A modified Elman neural network with a new learning rate scheme,” Neurocomputing, Vol. 286, PP. 11-18, 2018.

E. Rashedi, H. N. pour, and S. Saryazdi, “GSA: a gravitational search algorithm,” Information sciences, Vol. 179, PP. 2232-2248, 2009.

C. Li, N. Zhang, X. Lai, J. Zhou, and Y. Xu, “Design of a fractional-order PID controller for a pumped storage unit using a gravitational search algorithm based on the Cauchy and Gaussian mutation,” Information Sciences, Vol. 396, PP. 162-181, 2017.

S. Yazdani, H. N. pour, and S. Kamyab, “A gravitational search algorithm for multimodal optimization,” Swarm and Evolutionary Computation, Vol.1, PP. 1-14, 2014.

F. M. Ham, and I. Kostanic, “Principles of Neurocomputing for Science and Engineering,” McGraw Hill, New York, NY, 2001.

S. Li, J. Li, J. Qiu, H. Ji, and K. Zhu “Control design for arbitrary complex nonlinear discrete-time systems based on direct NNMRAC strategy,” J Process Control, Vol. 21, No. 1, pp. 103-110, 2011.

Y. Oussar, and G. Dreyfus,“ Initialization by selection for wavelet network training ” Neurocomputing, Vol. 34, pp. 131-143, 2000.

O. F. Lutfy, “Wavelet neural network model reference adaptive control trained by a modified artificial immune algorithm to control nonlinear systems,” Arab. J. Sci. Eng., Vol. 39, pp. 4737-4751, 2014.

S. Chong, S. Rui, L. Jie, Z. Xiaoming, T. Jun, S. Yunbo, L. Jun , and C. Huiliang, “Temperature drift modeling of MEMS gyroscope based on genetic-Elman neural network,” Mechanical Systems And Signal Processing, Vol. 72, PP. 897-905, 2016.

F.-J. Lin, L.-T. Teng, and H. Chu, “Modified Elman neural network controller with improved particle swarm optimisation for linear synchronous motor drive,” IET Electric Power Applications, Vol. 2, PP. 201-214, 2008.

S. Mirjalili, and A. Lewis, “Adaptive gbest-guided gravitational search algorithm,” Neural Computing and Applications, Vol. 25, PP. 1569-1584, 2014.

B. Yin, Z. Guo, Z. Liang, and X. Yue, “Improved gravitational search algorithm with crossover,” Computers & Electrical Engineering, Vol. 66, PP. 505-516, 2017.

S. Jiang, Y. Wang, and Z. Ji, “Convergence analysis and performance of an improved gravitational search algorithm,” Applied Soft Computing, Vol. 24, PP. 363-384. 2014.

A. Errachdi, and M. Benrejeb, “Model reference adaptive control based-on neural networks for nonlinear time-varying system,” Proceedings of the International Conference on Systems, Control and Informatics, Italy, pp. 73-77, 2013.

C. -F. Juang, and C. Lo, “Zero-order TSK-type fuzzy system learning using a two-phase swarm intelligence algorithm,” Fuzzy Sets and Systems, Vol. 159, No. 21, pp. 2910-2926, 2008.

C. -T. Lin, C. –H. Chen, and C. -J. Lin, “Nonlinear system control using functional-link-based neuro-fuzzy networks,” In: Yu, W. (editor) Recent Advances in Intelligent Control Systems. Springer-Verlag London Limited, 2009.

H. Husain, M. Khalid, and R. Yusof, “Direct model reference adaptive controller based-on neural-fuzzy techniques for nonlinear dynamical systems,” American Journal of Applied Sciences, Vol. 5, No. 7, pp. 769-776, 2008.