Adaptive Neural-Network Boundary Control for a Flexible Manipulator With Input Constraints and Model Uncertainties

• Published in: IEEE transactions on cybernetics Vol. 51; no. 10; pp. 4796 - 4807
• Main Authors: Ren, Yong, Zhao, Zhijia, Zhang, Chunliang, Yang, Qinmin, Hong, Keum-Shik
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.10.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Adaptive control; Adaptive neural network (NN) boundary control (BC); Artificial neural networks; Boundary control; Constraint modelling; Control theory; Cybernetics; flexible manipulator; Flexible manipulators; input constraints; Magnetic resonance imaging; Manipulators; model uncertainties; Neural networks; Radial basis function; Robot arms; Subsystems; Tracking errors; Uncertainty; Vibrations
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2020.3021069

This article develops an adaptive neural-network (NN) boundary control scheme for a flexible manipulator subject to input constraints, model uncertainties, and external disturbances. First, a radial basis function NN method is utilized to tackle the unknown input saturations, dead zones, and model uncertainties. Then, based on the backstepping approach, two adaptive NN boundary controllers with update laws are employed to stabilize the like-position loop subsystem and like-posture loop subsystem, respectively. With the introduced control laws, the uniform ultimate boundedness of the deflection and angle tracking errors for the flexible manipulator are guaranteed. Finally, the control performance of the developed control technique is examined by a numerical example.