Implementation of Fuzzy NARX IMC PID control of PAM robot arm using Modified Genetic Algorithms

In this paper, a proposed Fuzzy Nonlinear ARX (NARX) model is applied to model, identify and control the highly nonlinear pneumatic artificial muscle (PAM) robot arm. The Fuzzy NARX models are then applied as inverse and forward Fuzzy NARX models in the novel Fuzzy NARX IMC-PID controller for adaptively tracking the joint angle position of the nonlinear PAM robot arm. The performance of the proposed controller is due to the combination between the robust internal model control (IMC) structure with the approximating and predictive potentiality of the Fuzzy NARX model. The experimental testings are carried out and the effectiveness of the proposed control algorithm is demonstrated with two different conditions of payload and two kinds of control methods. These results can also be applied to control the other highly nonlinear and time-varying parametric industrial robot systems.

[1]  R. Babuska,et al.  Internal model control with a fuzzy model: application to an air-conditioning system , 1997, Proceedings of 6th International Fuzzy Systems Conference.

[2]  Meng Joo Er,et al.  A fast learning algorithm for parsimonious fuzzy neural systems , 1999, 1999 European Control Conference (ECC).

[3]  Kuldip S. Rattan,et al.  Feedforward control of a non-linear pneumatic muscle system using fuzzy logic , 2003, The 12th IEEE International Conference on Fuzzy Systems, 2003. FUZZ '03..

[4]  Pablo Carbonell,et al.  Nonlinear control of a pneumatic muscle actuator: backstepping vs. sliding-mode , 2001, Proceedings of the 2001 IEEE International Conference on Control Applications (CCA'01) (Cat. No.01CH37204).

[5]  Jihong Zhu,et al.  Nonlinear adaptive internal model control using neural networks for tilt rotor aircraft platform , 2005, Proceedings of the 2005 IEEE Midnight-Summer Workshop on Soft Computing in Industrial Applications, 2005. SMCia/05..

[6]  Aniruddha Datta Adaptive Internal Model Control , 1998 .

[7]  Zhi-Cheng Zhao,et al.  Multi-model neural network IMC , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[8]  K.S. Rattan,et al.  Fuzzy logic control of a pneumatic muscle system using a linearing control scheme , 2003, 22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003.

[9]  Léon Personnaz,et al.  Nonlinear internal model control using neural networks: application to processes with delay and design issues , 2000, IEEE Trans. Neural Networks Learn. Syst..

[10]  Ahmad B. Rad,et al.  Fuzzy adaptive internal model control , 2000, IEEE Trans. Ind. Electron..

[11]  Aniruddha Datta,et al.  Adaptive internal model control: Design and stability analysis , 1996, Autom..

[12]  Kyoung Kwan Ahn,et al.  A new approach for modelling and identification of the pneumatic artificial muscle manipulator based on recurrent neural networks , 2007 .

[13]  Marek Perkowski,et al.  Adaptive Reflex Control for an Artificial Hand , 2003 .