Neural Network Trajectory Tracking Control of Compliant Parallel Robot

Abstract:

Trajectory tracking control of compliant parallel robot is presented. According to the characteristics of compliant joint, the system model is derived and the dynamic equation is obtained based on the Lagrange method. Radial Basis Function (RBF) neural network control is designed to globally approximate the model uncertainties. Further, an itemized approximate RBF control method is proposed for higher identify precision. The trajectory tracking abilities of two control strategies are compared through simulation.

• Periodical: Applied Mechanics and Materials (Volumes 799-800)
• Pages: 1069-1073
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.799-800.1069
• Online since: October 2015
• Authors: Hao Tian, Yue Qing Yu*
• Keywords: Compliant Joint, Neural Network Control, Parallel Robot, Trajectory Tracking

References

[1] Y. Yun, Q. Xu, Y. Li: J Mech Eng, Vol. 44 (2008), p.12.

[2] B. Yi, G. B. Chung, H. Y. Na, et al: IEEE T Robotic Autom, Vol. 19 (2003), p.604.

[3] Y. Li, Q. Xu: Mech Mach Theory, Vol. 44 (2009), p.2127.

[4] Y. Tian, B. Shirinzadeh, D. Zhang: Microelectron Eng, Vol. 87 (2010), p.230.

[5] Y. Yu, Z. Cui, X. Zhao, et al: T Chin Soc Agr Mach, Vol. 44 (2013), p.274.

[6] Y. Yu, L. Ma, Z. Cui, et al: T Chin Soc Agr Mach, Vol. 45 (2014), p.284.

[7] H. Tian, Y. Yu: T Chin Soc Agr Mach, Vol. 45 (2014), p.278.

[8] F. L. Lewis, K. Liu, A. Yesildirek: IEEE T Neural Networ, Vol. 6 (1995), p.703.