Recurrent Neural Network Based Fuzzy Inference System for Identification and Control of Dynamic Plants

Authors: Rahib Hidayat Abiyev

Abstract:

This paper presents the development of recurrent neural network based fuzzy inference system for identification and control of dynamic nonlinear plant. The structure and algorithms of fuzzy system based on recurrent neural network are described. To train unknown parameters of the system the supervised learning algorithm is used. As a result of learning, the rules of neuro-fuzzy system are formed. The neuro-fuzzy system is used for the identification and control of nonlinear dynamic plant. The simulation results of identification and control systems based on recurrent neuro-fuzzy network are compared with the simulation results of other neural systems. It is found that the recurrent neuro-fuzzy based system has better performance than the others.

Keywords: Fuzzy logic, neural network, neuro-fuzzy system, control system.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1085665

References:

[1] Zadeh L.A.(1975). The concept of linguistic variable and its application to approximate reasoning. Information Sciences, v.8.
[2] Kosko B. (1993). Neural networks and fuzzy systems. A dynamical system approach to machine intelligence. Prentice- Hall International Inc., Englewood Cliffs.
[3] Yager R.R., Zadeh L.A.(Eds). (1994). Fuzzy sets, neural networks and softcomputing, New York, Van Nostrand Reinhold.
[4] Witold Pedryz, editor, (1996) Fuzzy Modelling: Paradigms and Practice, Kluwer Academic Publisher, Boston.
[5] Aliev R.A., Tserkovni A.E., and Mamedova G.A. (1991). Production management at fuzzy initial information. Moscow, Energiatomizdat, (Russian)
[6] J.Reeman and D.Saad.(1997). Online learning in radial basis function networks, Neural Comput., vol.9,no.7,
[7] T.Mheskes and B. Kappen. (1993). Online learning processes in artificial neural networks. Math. Found. Neural Networks, Amsterdam, The Netherlands: Elsevier, pp.199-233.
[8] Diederich J. (1990). Artificial Neural Networks. Consept learning, Los Alamitos CA: IEEE Computer Society Press.
[9] Jyh-Shing Roger Jang. (1993). "ANFIS: Adaptive-Network- Based Fuzzy Inference System". IEEE Transactions on Systems, Man and Cybernetics, Vol.23, No.3, pp.665-683.
[10] Nauck, Detlef and Kruse, Rudolf. (1996). Designing neurofuzzy systems through backpropagation, In Witold Pedryz, editor, Fuzzy Modelling: Paradigms and Practice, Boston, Kluwer Academic Publisher,pp.203-228
[11] Detlef Nauck. (1994). Building neural-fuzzy controllers with NEFCON-I. In Rudolf Kruse, Jorg Gebhardt, and Rainer Palm(Eds), Fuzzy Systems in Computer Science, Artificial Intelligence, Wiesbaden, Vieweg,pp.141-151.
[12] M.Onder Efe, and Okyay Kaynak. (2000). "On stabilization of Gradient-Based Training Strategies for Computationally Intelligent Systems". IEEE Transactions on Fuzzy Systems, Vol.8, No.5, October, pp.564-575.
[13] J.J.Buckley, Y.Hayashi, and E.Czogola.(1993). Fuzzy neural networks with fuzzy signals and weights. International Journal on Intelligent Systems 8, pp.527-537.
[14] J.J.Buckley, and Y.Hayashi. (1993). Fuzzy neural networks. In L.A.Zadeh and R.R.Yager (Eds), Fuzzy Sets, Neural networks and Soft Computing, Van Nostrand Reinhold, pp.233-249.
[15] H.Ishibuchi, K. Morioka, and H.Tanaka. (1994). A fuzzy neural network with trapezoidal fuzzy weights. Proc. FUZZ-IEEE, Orlando, Florida, June 26-29, pp.228-233.
[16] R.A.Aliev, R.H.Abiyev, and R.R.Aliev. (1994). Automatic control system synthesis with the learned neural network based fuzzy controller. Moscow, News of Academy of Sciences, Tech. Cybernetics 2:pp. 192-197.
[17] R.A.Aliev, F.T.Aliev, R.H.Abiev, and R.R.Aliev. (1994). Industrial neural controllers. EUFIT-94, Promenade 9,52076, Aachen, Germany. Elita foundation
[18] R.H.Abiyev, K.W.Bonfig, and F.T.Aliev. (1996). Controller based on fuzzy neural network for control of technological process. ICAFS-96, Siegen, Germany, June 25-27,pp295-298.
[19] J.Zhang, and A.J.Morris, (1999). Recurrent neuro-fuzzy networks for nonlinear process modeling. IEEE Trans. Neural Networks, vol.10,no.2, Mart, pp.313-326,
[20] C.H.Lee, and C.C.Theng. (2000). Identification and control of dynamic systems using recurrent fuzzy neural network. IEEE Trans. Fuzzy Systems, vol. 8, pp.349-366.
[21] Chia-Feng Juang. (2002), A TSK -type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithm, IEEE Trans. Fuzzy Systems, vol.10, pp.155-170.
[22] James Keller, Ronald R.Yager, and Hossein Tahani. (1992). Neural network implementation of fuzzy logic, Fuzzy Sets and Systems, 45:pp.1-12.
[23] Rahib Abiyev. (2001). Controllers based on Softcomputing elements// Electrical, Electronics and Computer Engineering Symposium NEU-CEE2001 & Exhibition. Nicosia, TRNC, Turkey, May 23-25, pp.182-188.
[24] Rahib Abiyev. (2002). Fuzzy inference system based on neural network for technological processes control. Journal of Mathematical and Computational Applications. Turkey, pp.245- 252.
[25] Jaier Nunez-Garcia and Olaf Wolkenhauer. (2002). Random Set System Identification. IEEE Transactions on Fuzzy Systems, Vol.10, No.3, October, pp.287-296.
[26] Rahib Abiyev. (2002). Neuro-Fuzzy system for technological processes control. The 6th World Multi-Conference on SYSTEMICS, cybernetics and informatics. SCI-20002, Orlando, Florida, USA. July 14-18.