Identification and Control of Flexible Joint Robot Using Multi-Time-Scale Neural Network

doi:10.1007/s12204-020-2210-3

Journal of Shanghai Jiao Tong University(Science) ›› 2020, Vol. 25 ›› Issue (5): 553-560.doi: 10.1007/s12204-020-2210-3

Previous Articles Next Articles

Identification and Control of Flexible Joint Robot Using Multi-Time-Scale Neural Network

ZHENG Dongdong (郑冬冬), LI Pengcheng (李鹏程), XIE Wenfang (谢文芳), LI Dan (李丹)

(1. Department of Mechanical, Industrial & Aerospace Engineering, Concordia University, Montreal H3G 1M8, Canada;
2. College of Mechanical & Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016,
China; 3. Department of Electrical and Computer Engineering, Concordia University, Montreal H3G 1M8, Canada)
(1. Department of Mechanical, Industrial & Aerospace Engineering, Concordia University, Montreal H3G 1M8, Canada;
2. College of Mechanical & Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016,
China; 3. Department of Electrical and Computer Engineering, Concordia University, Montreal H3G 1M8, Canada)

Online:2020-10-28 Published:2020-09-11
Contact: XIE Wenfang (谢文芳) E-mail:wfxie@encs.concordia.ca

Abstract

Abstract: In this paper, a new identification and control scheme for the flexible joint robotic manipulator is
proposed. Firstly, by defining some new state variables, the commonly used dynamic equations of the flexible joint
robotic manipulators are transformed into the standard form of a singularly perturbed model. Subsequently, an
optimal bounded ellipsoid algorithm based identification scheme using multi-time-scale neural network is proposed
to identify the unknown system dynamic equations. Lastly, by using the singular perturbation theory, an indirect
adaptive controller based on the identified model is proposed to control the system such that the joint angles can
track the given reference signals. The closed-loop stability of the whole system is proved, and the effectiveness of
the proposed schemes is verified by simulations.

Key words: flexible joint| robotic manipulator| multi-time-scale neural network| singular perturbation| adaptive
controller

摘要： In this paper, a new identification and control scheme for the flexible joint robotic manipulator is
proposed. Firstly, by defining some new state variables, the commonly used dynamic equations of the flexible joint
robotic manipulators are transformed into the standard form of a singularly perturbed model. Subsequently, an
optimal bounded ellipsoid algorithm based identification scheme using multi-time-scale neural network is proposed
to identify the unknown system dynamic equations. Lastly, by using the singular perturbation theory, an indirect
adaptive controller based on the identified model is proposed to control the system such that the joint angles can
track the given reference signals. The closed-loop stability of the whole system is proved, and the effectiveness of
the proposed schemes is verified by simulations.

关键词: flexible joint| robotic manipulator| multi-time-scale neural network| singular perturbation| adaptive
controller

CLC Number:

TP 242

ZHENG Dongdong, LI Pengcheng, XIE Wenfang, LI Dan . Identification and Control of Flexible Joint Robot Using Multi-Time-Scale Neural Network[J]. Journal of Shanghai Jiao Tong University(Science), 2020, 25(5): 553-560.

References 20

[1]	SICILIANO B, SCIAVICCO L, VILLANI L, et al.Robotics: Modelling, planning and control [M]. London,UK: Springer-Verlag, 2009.
[2]	SPONG M W. Modeling and control of elastic joint robots [J]. Journal of Dynamic Systems, Measurement,and Control, 1987, 109(4): 310-318.
[3]	SPONG M W, KHORASANI K, KOKOTOVIC P V.An integral manifold approach to the feedback control of flexible joint robots [J]. IEEE Journal of Robotics and Automation, 1987, 3(4): 291-300.
[4]	KHORASANI K. Nonlinear feedback control of flexible joint manipulators: A single link case study[J]. IEEE Transactions on Automatic Control, 1990,35(10): 1145-1149.
[5]	RUDERMAN M. Compensation of nonlinear torsion in flexible joint robots: Comparison of two approaches[J]. IEEE Transactions on Industrial Electronics, 2016,63(9): 5744-5751.
[6]	GUO C Q, GAO H B, NI F L, et al. A vibration suppression method for flexible joints manipulator based on trajectory optimization [C]//Proceedings of 2016 IEEE International Conference on Mechatronics and Automation. Harbin, China: IEEE, 2016: 338-343.
[7]	NAIDU D S. Singular perturbation analysis of a flexible beam used in underwater exploration [J]. International Journal of Systems Science, 2011, 42(1): 183-194.
[8]	CHAOUI H, SICARD P. Adaptive neural network control of flexible-joint robotic manipulators with friction and disturbance [C]//IECON 2012-38th Annual Conference on IEEE Industrial Electronics Society. Montreal,Quebec, Canada: IEEE, 2012: 2644-2649.
[9]	MACNAB C J B. Improved output tracking of a flexible-joint arm using neural networks [J]. Neural Processing Letters, 2010, 32(2): 201-218.
[10]	SUBUDHI B, MORRIS A S. Singular perturbation approach to trajectory tracking of flexible robot with joint elasticity [J]. International Journal of Systems Science, 2003, 34(3): 167-179.
[11]	KHORASANI K. Adaptive control of flexible-joint robots [C]//Proceedings of the 1991 IEEE International Conference on Robotics and Automation. Sacramento,California, USA: IEEE, 1991: 2127-2134.
[12]	GE S S, POSTLETHWAITE I. Adaptive neural network controller design for flexible joint robots using singular perturbation technique [J]. Transactions of the Institute of Measurement and Control, 1995, 17(3):120-131.
[13]	MIAO Z Q, WANG Y N. Robust dynamic surface control of flexible joint robots using recurrent neural networks[J]. Journal of Control Theory and Applications,2013, 11(2): 222-229.
[14]	YEN H M, LI T H S, CHANG Y C. Adaptive neural network based tracking control for electrically driven flexible-joint robots without velocity measurements [J].Computers and Mathematics with Applications, 2012,64(5): 1022-1032.
[15]	LOZANO R, BROGLIATO B. Adaptive control of robot manipulators with flexible joints [J]. IEEE Transactions on Automatic Control, 1992, 37(2): 174-181.
[16]	FU Z J, XIE W F, HAN X, et al. Nonlinear systems identification and control via dynamic multitime scales neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(11): 1814-1823.
[17]	ZHENG D D, XIE W F, REN X M, et al. Identification and control for singularly perturbed systems using multitime-scale neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2017,28(2): 321-333.
[18]	GHORBEL F, HUNG J Y, SPONG M W. Adaptive control of flexible-joint manipulators [J]. IEEE Control Systems Magazine, 1989, 9(7): 9-13.
[19]	ETXEBARRIA V, SANZ A, LIZARRAGA I. Control of a lightweight flexible robotic arm using sliding modes [J]. International Journal of Advanced Robotic Systems, 2005, 2(2): 103-110.
[20]	ZHENG D D, XIE W F, CHAI T, et al. Identification and trajectory tracking control of nonlinear singularly perturbed system [J]. IEEE Transactions on Industrial Electronics, 2017, 64(5): 3737-3747.

Identification and Control of Flexible Joint Robot Using Multi-Time-Scale Neural Network

Identification and Control of Flexible Joint Robot Using Multi-Time-Scale Neural Network

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References 20

Related Articles 3

Recommended Articles

Metrics

Comments

[1]	XU Chenhui, YU Fanghui, HE Defeng. Disturbance-Blocking-Based Distributed Receding Horizon Estimation of Flexible Joint Robots [J]. Journal of Shanghai Jiao Tong University, 2022, 56(7): 868-876.
[2]	LI Pengfei,QIAO Xinqi,WU Zuozhu. Simplification of DME Combustion Mechanism and Validation with HCCI Combustion [J]. Journal of Shanghai Jiaotong University, 2015, 49(01): 129-134.
[3]	WU Zuo-Zhu, QIAO Xin-Qi, HUANG Zhen. A Criterion Based on Computational Singular Perturbation for the Construction of Reduced Mechanism for Dimethyl Ether [J]. Journal of Shanghai Jiaotong University, 2013, 47(03): 376-380.