Recurrent neuro-fuzzy model of pneumatic artificial muscle position

다국어 초록 (Multilingual Abstract)

In this paper, a dynamic neuro-fuzzy system is proposed toward modeling the pneumatic artificial muscle, which are widely used in robotics and rehabilitation. To benefit from the outstanding advantages of the pneumatic actuators such as high softness and low weightto-force ratio, efficient control of the actuator force as well as its displacement is essential. Attaining a comprehensive model with a satisfactory accuracy in the entire course of the muscle is the most important challenge regarding utilization of the pneumatic artificial muscle in a wide range of the applications. Therefore, an adaptive neuro-fuzzy inference system has been developed for pneumatic artificial muscle modeling. The subtractive clustering method is applied to reduce the number of fuzzy rules without loss of accuracy. To verify the effectiveness of the proposed modeling approach, an experimental setup has been constructed using a vertically suited pneumatic artificial muscle which holds a mass. Input-output data are collected for training and testing the recurrent neuro-fuzzy model. The experimental results demonstrate the desirable performance of the proposed adaptive neuro-fuzzy inference system method in modeling the pneumatic artificial muscle as well as its superiority compared to the mathematical model.

참고문헌 (Reference)

1 A. V. Hill, "The heat of shortening and the dynamic constants of muscle" 136-195, 1938

2 H. F. Schulte, "The application of external power in prosthetics and orthotics, The Characteristics of the McKibben Artificial Muscle" National Research Council 874-, 1961

3 B. Tondu, "The McKibben muscle and its use in actuating robot-arms showing similarities with human arm behavior" 24 (24): 432-439, 1997

4 X. Jiang, "Static and dynamic characteristics of rehabilitation joint powered by pneumatic muscles" 38 (38): 486-491, 2011

5 C. P. Chou, "Static and dynamic characteristics of McKibben pneumatic artificial muscles" 281-286, 1994

6 V. Z. Antonopoulos, "Solar radiation estimation methods using ANN and empirical models" 160 : 160-167, 2019

7 E. Nazem, "Proposing an intelligent approach for measuring the thickness of metal sheets independent of alloy type" 2019

8 A. Khosravi, "Prediction of wind speed and wind direction using artificial neural network, support vector regression and adaptive neuro-fuzzy inference system" 25 : 146-160, 2018

9 G. Andrikopoulos, "Piecewise affine modeling and constrained optimal control for a pneumatic artificial muscle" 61 (61): 904-916, 2014

10 S. Rajab, "Performance evaluation of ANN and neuro-fuzzy system in business forecasting" 749-754, 2015

11 J. F. De Canete, "Object-oriented approach applied to ANFIS modeling and control of a distillation column" 40 (40): 5648-5660, 2013

12 D. Bruder, "Nonlinear system identification of soft robot dynamics using koopman operator theory"

13 X. Shen, "Nonlinear model-based control of pneumatic artificial muscle servo systems" 18 (18): 311-317, 2010

14 B. Kalita, "Nonlinear dynamics of a parametrically excited pneumatic artificial muscle(PAM)actuator with simultaneous resonance condition" 135 : 281-297, 2019

15 J. S. Jang, "Neuro-fuzzy modeling and control" 83 (83): 378-406, 1995

16 A. H. Kishore, "Neuro-fuzzy based medical decision support system for coronary artery disease diagnosis and risk level prediction" 15 (15): 1027-1037, 2018

17 D. B. Reynolds, "Modeling the dynamic characteristics of pneumatic muscle" 31 (31): 310-317, 2003

18 C. Song, "Modeling of pneumatic artificial muscle using a hybrid artificial neural network approach" 31 : 124-131, 2015

19 K. Xing, "Modeling and control of McKibben artificial muscle enhanced with echo state networks" 20 (20): 477-488, 2012

20 H. P. H. Anh, "Hybrid control of a pneumatic artificial muscle(PAM)robot arm using an inverse NARX fuzzy model" 24 (24): 697-716, 2011

21 A. Hosovsky, "Hill's muscle modelbased modeling of pneumatic artificial muscle" 1005-1007, 2011

22 S. Rajab, "Handling interpretability issues in ANFIS using rule base simplification and constrained learning" 2018

23 Y. Yang, "Fuzzy neural network model for assessing credit risk in commercial banks" 678-681, 2011

24 S. L. Chiu, "Fuzzy model identification based on cluster estimation" 2 (2): 267-278, 1994

25 T. Kerscher, "Evaluation of the dynamic model of fluidic muscles using quickrelease" 637-642, 2006

26 H. P. H. Anh, "Dynamic model identification of the 2-Axes PAM robot arm using Neural MIMO NARX model" 18-23, 2008

27 K. L. Hall, "Dynamic Control for a Pneumatic Muscle Actuator to Achieve Isokinetic Muscle Strengthening" Wright State University 2011

28 S. Kurumaya, "Design of thin McKibben muscle and multifilament structure" 261 : 66-74, 2017

29 S. H. Sumit, "C-means clustering and deepneuro-fuzzy classification for road weight measurement in traffic management system" 1-12, 2018

30 S. Abbas, "Bio-inspired neuro-fuzzy based dynamic route selection to avoid traffic congestion" 2 (2): 284-289, 2011

31 Y. L. Park, "Bio-inspired active soft orthotic device for ankle foot pathologies" 4488-4495, 2011

32 J. M. Lee, "Application of artificial neural networks for optimized AHU discharge air temperature set-point and minimized cooling energy in conventional VAV system" 153 (153): 726-738, 2019

33 N. Z. Meymian, "An optimization method for flexural bearing design for high-stroke high-frequency applications" 95 : 82-94, 2018

34 E. P. Ephzibah, "An expert system for heart disease diagnosis using neuro-fuzzy technique" 1 (1): 9-18, 2012

35 P. Naphon, "ANN, numerical and experimental analysis on the jet impingement nanofluids flow and heat transfer characteristics in the micro-channel heat sink" 131 : 329-340, 2019

36 J. S. Jang, "ANFIS: Adaptive-network-based fuzzy inference system" 23 (23): 665-685, 1993

37 H. Ahmadian H, "ANFIS modeling of vibration transmissibility of a power tiller to operator" 138 : 39-51, 2018

38 S. Rajab, "A review on the applications of neuro-fuzzy systems in business" 49 (49): 481-510, 2018