Design of an intelligent exponential-reaching sliding-mode control via recurrent fuzzy neural network

In the presence of modeling inaccuracy, which may have strong adverse effects upon system performance, the sliding-mode control (SMC) can provide a closed-loop system dynamics with an invariance property to uncertainties. This study proposes an intelligent exponential-reaching sliding-mode control (IERSMC) system which provides faster convergence and higher tracking precision. The proposed IERSMC system is composed of a linearization controller and an exponential compensator. The linearization controller including a recurrent fuzzy neural network (RFNN) approximator is the main controller and the exponential compensator is designed to eliminate the effect of the approximation error introduced by the RFNN approximator upon system stability. Finally, the proposed IERSMC system is applied to an inverted pendulum to show its effectiveness. The simulation results demonstrate that the proposed IERSMC system can achieve favorable performance for tracking control problem.

[1]  Yih-Guang Leu,et al.  Observer-based direct adaptive fuzzy-neural control for nonaffine nonlinear systems , 2005, IEEE Trans. Neural Networks.

[2]  Chun-Fei Hsu,et al.  Fuzzy-identification-based adaptive controller design via backstepping approach , 2005, Fuzzy Sets Syst..

[3]  Chun-Fei Hsu.  Adaptive neural complementary sliding-mode control via functional-linked wavelet neural network , 2013, Eng. Appl. Artif. Intell..

[4]  Chin-Teng Lin,et al.  Using an Efficient Immune Symbiotic Evolution Learning for Compensatory Neuro-Fuzzy Controller , 2009, IEEE Transactions on Fuzzy Systems.

[5]  Vadim I. Utkin,et al.  Sliding Modes and their Application in Variable Structure Systems , 1978 .

[6]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control - design and stability analysis , 1994 .

[7]  Faa-Jeng Lin,et al.  Recurrent-Fuzzy-Neural-Network-Controlled Linear Induction Motor Servo Drive Using Genetic Algorithms , 2007, IEEE Transactions on Industrial Electronics.

[8]  Chun-Fei Hsu.  Nonlinear system control using a self-organizing functional-linked neuro-fuzzy network , 2013 .

[9]  Weiping Li,et al.  Applied Nonlinear Control , 1991 .

[10]  Syuan-Yi Chen,et al.  Recurrent Functional-Link-Based Fuzzy Neural Network Controller With Improved Particle Swarm Optimization for a Linear Synchronous Motor Drive , 2009, IEEE Transactions on Magnetics.

[11]  Chih-Min Lin,et al.  Supervisory adaptive dynamic RBF-based neural-fuzzy control system design for unknown nonlinear systems , 2013, Appl. Soft Comput..

[12]  Cheng-Jian Lin,et al.  An Efficient Symbiotic Particle Swarm Optimization for Recurrent Func- tional Neural Fuzzy Network Design , 2009 .

[13]  Chia-Feng Juang,et al.  Recurrent type-2 fuzzy neural network using Haar wavelet energy and entropy features for speech detection in noisy environments , 2012, Expert Syst. Appl..

[14]  Chun-Fei Hsu.  Intelligent tracking control of a DC motor driver using self-organizing TSK-type fuzzy neural networks , 2012 .

[15]  Chia-Feng Juang,et al.  Speedup of Implementing Fuzzy Neural Networks With High-Dimensional Inputs Through Parallel Processing on Graphic Processing Units , 2011, IEEE Transactions on Fuzzy Systems.

[16]  Yang-Yin Lin,et al.  Dynamic system modeling using a recurrent interval-valued fuzzy neural network and its hardware implementation , 2011, Fuzzy Sets Syst..

[17]  Chin-Teng Lin,et al.  A recurrent self-organizing neural fuzzy inference network , 1999, IEEE Trans. Neural Networks.