Pneumatic artificial muscles (PAMs) are widely used in the various fields of medical robots and other industrial applications. As a powerful tool of intelligent control, neural networks nowadays are applied effectively to model, identify, and control highly non-linear systems, including the PAM manipulator. In the current paper a prototype PAM manipulator is modelled through recurrent neural networks (NN) modelling and identification based on experimental input-output training data. The proposed incremental back-propagation (INCBP) algorithm, which yields faster convergence than a conventional back-propagation (BP) algorithm, is applied to train the neural networks. The realization of the INCBP algorithm is given. An evaluation is carried out for different non-linear NN auto-regressive with exogenous input (NNARX) models of a PAM manipulator, using recurrent NN with various input nodes as well as various hidden layer nodes. For the first time, the non-linear NNARX model scheme of the prototype PAM manipulator has been investigated. The results show that the non-linear NNARX model trained by INCBP yields better performance and higher accuracy than the traditional linear ARX model. These results can be applied in modelling, identifying, and controlling not only the PAM manipulator, but also other highly non-linear systems.
LillyJ. H.Adaptive tracking for pneumatic muscle actuators in bicep and tricep configurations. IEEE Trans. Neural Syst. Rehabil. Engng, 2003, 11 (3), 333–339.
2.
CaldwellD. G.TsagarakisG. N.Development and control of a soft-actuated exoskeleton for use in physiotherapy and training. J. Autonomous Robots, 2003, 15 (1), 21–33.
3.
KobayashiH.UchimuraA.ShiibaT.Development of muscle suit for upper body. In Proceedings of IEEE International Conference on Intelligent robots and systems, IROS 2003, October 2003, Vol. 4, pp. 3624–3629.
4.
NoritsuguT.SasakiD.TakaiwaM.Rehabilitation robotics: development of active support splint driven by pneumatic soft actuator (ASSIST). In Proceedings of IEEE International Conference on Robotics and automation, Barcelona, Spain, April 2005.
5.
FukudaT.GuoS. X.WangJ. R.Study on actuators of the artificial muscular type. Trans. Jap. Soc. Mech. Engrs, 1993, 59 (3), 203–210.
6.
ChouC. P.HannafordB.Measurement and modeling of McKibben pneumatic artificial muscle. IEEE Trans. Robotics and Automation, 1996, 12 (1), 90–102.
7.
TonduB.LopezP.McKibben muscle and its use in actuating robot-arms showing with human arm behavior. IEE Ind. Robot, 1997, 24 (6), 432–439.
8.
ChouC.-P.HannafordB.A study of pneumatic muscle technology for possible assistance in mobility. In Proceedings of 19th Annual International Conference of the IEEE, Medicine and Biology Society, Chicago, Illinois, 1994, pp. 1884–1887.
9.
ChouC.-P.HannafordB.Static and dynamic characteristics of McKibben pneumatic artificial muscles. In Proceedings of the IEEE Conference on Robotics and automation, 1994, pp. 281–286.
10.
ReppergerD. W.JohnsonK. R.PhillipsC. A.VSC position tracking system involving a large scale pneumatic muscle actuator. In Proceedings of the IEEE Conference on Decision control, Tampa, Florida, December 1998, pp. 4302–4307.
11.
TsagarakisN.DarwinG. C.Improved modeling and assessment of pneumatic muscle actuators. In Proceedings of IEEE International Conference on Robotics and automation, San Francisco, California, April 2000, pp. 3641–3646.
12.
CaldwellD. G.Medrano-CerdaG. A.GoodwinM.Control of pneumatic muscle actuators. IEEE Trans., Control Syst. Mag., 1995, 15 (1), 40–48.
13.
Cocatre-ZilgienJ. H.DelcomynF.HartJ. M.Performance of a muscle-like ‘leaky’ pneumatic actuator powered by modulated air pulses. IEEE J. Robot. Syst., 1996, 13 (6), 379–390.
14.
PackR. T.ChristopherJ. L.Jr.KawamuraK.A rubbertuator -based structure-climbing inspection robot. In Proceedings of IEEE International Conference on Robotics and automation, 1997, Vol. 3, pp. 1869–1874.
15.
AhnK. K.AnhH. P. H.System modeling and identification of the two-link PAM manipulator optimized with genetic algorithm. In Proceedings of IEEE-ICASE International Conference, Busan, Korea, 2006, pp. 356–361.
16.
AhnK. K.AnhH. P. H.Modeling and adaptive self-tuning MVC of the 2-axes pneumatic artificial muscle (PAM) manipulator optimized with genetic algorithm. KSME J., 2006 (submitted).
17.
AhnK. K.ThanhT. D. C.Intelligent phase plane switching control of pneumatic artificial muscle manipulators with magneto-rheological brake. Mechatronics, 2006, 16 (2), 85–95.
18.
NagaokaT.KonishiY.IshigakiH.Nonlinear optimal predictive control of rubber artificial muscle. Proc. SPIE, Int. Soc. Opt. Engng, 1995, 2595, 54–61.
19.
HamerlainM.Anthropomorphic robot arm driven by artificial muscles using a variable structure control. In Proceedings of IEEE International Conference on Intelligent robots systems, Pittsburgh, Pennsylvania, 1995, pp. 550–555.
20.
ReppergerD. W.PhillipsC. A.KrierM.Controller design involving gain scheduling for a large scale pneumatic muscle actuator. In Proceedings of IEEE Conference on Control applications, Hawaii, 1999, pp. 285–290.
21.
HesselrothT.SarkarK.Van der SmagtP.SchultenK.Neural network control of a pneumatic robot arm. IEEE Trans. Syst., Man, Cybernetics B, Cybernetics, 1994, 24 (1), 28–38.
22.
CarbonellP.JiangZ. P.ReppergerD. W.A fuzzy backstepping controller for a pneumatic muscle actuator system. In Proceedings of IEEE International Symposium on Intelligent control, Mexico City, September 2001, pp. 353–358.
23.
LillyJ. H.ChangX.Tracking control of a pneumatic muscle by an evolutionary fuzzy controller. IEEE Trans. Intell. Autom. Soft Comput., 2003, 9 (3), 227–244.
24.
Medrano-CerdaG. A.BowlerC. J.CaldwellD. G.Adaptive position control of antagonistic pneumatic muscle actuators. In Proceedings of IEEE International Conference on Intelligent robots and systems, Pittsburgh, Pennsylvania, 1995, pp. 378–383.
25.
ChanS. W.LillyJ.ReppergerD. W.BerlinJ. E.Fuzzy PD + I learning control for a pneumatic muscle. In Proceedings of IEEE International Conference on Fuzzy systems, St. Louis, Missouri, May 2003, pp. 278–283.
