Training fuzzy neural networks using sliding mode theory with adaptive learning rate

This paper proposes an online training method for the parameters of a fuzzy neural network (FNN) using sliding mode systems theory with an adaptive learning rate. The implemented control structure consists of a conventional controller in parallel with a FNN. The former is provided both to guarantee global asymptotic stability in compact space and acts as a sliding surface to guide the states of the system towards zero. The output of the conventional controller is used to update the parameters of the FNN. The output of the FNN gradually replaces the conventional controller. The adaptive learning rate makes it possible to control the system without priori knowledge about the upper bound of the states of the system and their derivatives. An appropriate Lyapunov function approach is used to analyze the stability of the adaptation law of parameters of FNN. Sufficient conditions to guarantee the boundedness of the parameters are derived. The proposed approach is tested on the velocity control of an electro hydraulic servo system in presence of flow nonlinearities and internal friction.

[1]  Jun Nakanishi,et al.  Feedback error learning and nonlinear adaptive control , 2004, Neural Networks.

[2]  Mojtaba Ahmadieh Khanesar,et al.  Extended Kalman Filter Based Learning Algorithm for Type-2 Fuzzy Logic Systems and Its Experimental Evaluation , 2012, IEEE Transactions on Industrial Electronics.

[3]  K. Doya,et al.  Motor Control: Neural Models and Systems Theory , 2001 .

[4]  Mojtaba Ahmadieh Khanesar,et al.  A novel training method based on variable structure systems theory for fuzzy neural networks , 2011, Computational Intelligence in Control and Automation (CICA).

[5]  Okyay Kaynak,et al.  Neuro-fuzzy control of antilock braking system using sliding mode incremental learning algorithm , 2011, Neurocomputing.

[6]  Dragan Antić,et al.  Position control of an electro-hydraulic servo system using sliding mode control enhanced by fuzzy PI controller , 2002 .

[7]  Meng Joo Er,et al.  Control of Adept One SCARA robot using neural networks , 1997, IEEE Trans. Ind. Electron..

[8]  Xiaogang Ruan,et al.  On-line adaptive control for inverted pendulum balancing based on feedback-error-learning , 2007, Neurocomputing.

[9]  Yaochu Jin,et al.  Advanced fuzzy systems design and applications , 2003, Studies in Fuzziness and Soft Computing.

[10]  M. Jovanovic,et al.  Nonlinear control of an electrohydraulic velocity servosystem , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[11]  M. Teshnehlab,et al.  Sliding mode control of Rotary Inverted Pendulm , 2007, 2007 Mediterranean Conference on Control & Automation.

[12]  M. A. Khanesar,et al.  Hybrid Training of Recurrent Fuzzy Neural Network Model , 2007, 2007 International Conference on Mechatronics and Automation.

[13]  Okyay Kaynak,et al.  The fusion of computationally intelligent methodologies and sliding-mode control-a survey , 2001, IEEE Trans. Ind. Electron..

[14]  Okyay Kaynak,et al.  Sliding Mode Control Approach for Online Learning as Applied to Type-2 Fuzzy Neural Networks and Its Experimental Evaluation , 2012, IEEE Transactions on Industrial Electronics.

[15]  Mitsuo Kawato,et al.  A computational model of four regions of the cerebellum based on feedback-error learning , 2004, Biological Cybernetics.

[16]  Lon-Chen Hung,et al.  Decoupled sliding-mode with fuzzy-neural network controller for nonlinear systems , 2007, Int. J. Approx. Reason..

[17]  M. Teshnehlab,et al.  Fuzzy Sliding Mode Control of Rotary Inverted Pendulum , 2007, 2007 IEEE International Conference on Computational Cybernetics.

[18]  John Watton.  Fluid Power Systems: Modeling, Simulation, Analog and Microcomputer Control , 1989 .

[19]  Mojtaba Ahmadieh Khanesar,et al.  An online training algorithm based on the fusion of sliding mode control theory and fuzzy neural networks with triangular membership functions , 2011, 2011 8th Asian Control Conference (ASCC).