An online training algorithm based on the fusion of sliding mode control theory and fuzzy neural networks with triangular membership functions

This paper proposes an online tuning method for the parameters of a fuzzy neural network using variable structure systems theory. The proposed learning algorithm establishes a sliding motion in terms of the fuzzy neuro controller parameters, and it leads the error towards zero. The Lyapunov function approach is used to analyze the convergence of the weights for the case of triangular membership functions. Sufficient conditions to guarantee the convergence of the weights are derived. In the simulation studies, the approach presented has been tested on the velocity control of an electro hydraulic servo system in presence of flow nonlinearities and internal friction.

[1]  M. Kawato,et al.  Hierarchical neural network model for voluntary movement with application to robotics , 1988, IEEE Control Systems Magazine.

[2]  Antônio de Pádua Braga,et al.  Sliding mode algorithm for training multilayer artificial neural networks , 1998 .

[3]  Vadim I. Utkin,et al.  Sliding Modes in Control and Optimization , 1992, Communications and Control Engineering Series.

[4]  Ingersoll-Rand.  Fluid Power Systems , 2006 .

[5]  Okyay Kaynak,et al.  Adaptive neuro-fuzzy control with sliding mode learning algorithm: Application to Antilock Braking System , 2009, 2009 7th Asian Control Conference.

[6]  Zhihong Man,et al.  A fuzzy neural network approximator with fast terminal sliding mode and its applications , 2004, Fuzzy Sets Syst..

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

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