TY - GEN
T1 - Adaptive radial basis function artificial neural network control for two-flexible-link robots
AU - Tekweme, Francis Kunzi
N1 - Publisher Copyright:
© IEOM Society International.
PY - 2020
Y1 - 2020
N2 - The focus of this paper is the use of an Adaptive Radial Basis Function Artificial Neural Network (ARBFANN) for the control of Two-Flexible-Link Robots (TFLR). Flexible links are modeled as Bernoulli beams. The Assumed Mode Method (AMM) together with the Lagrangian approach is used to derive the closed-form dynamic. Two modes are considered for each link. Singular perturbation method is used to derive a composite control for the TFLR. A stable robust two-time scale controller without any data for modeling is developed. The slow subsystem is controlled by an ARBFANN based on global approximation while the Linear Quadratic Regulator (LQR) controller stabilizes the fast subsystem and guarantee the closed-loop stability. The ARBFANN with a sliding mode robust term is trained on-line to approximate unknown nonlinear system dynamics, suppress errors in the modeling of neural network and, guarantee closed-loop stability. To verify the validity of the proposed control strategy, simulation results are included.
AB - The focus of this paper is the use of an Adaptive Radial Basis Function Artificial Neural Network (ARBFANN) for the control of Two-Flexible-Link Robots (TFLR). Flexible links are modeled as Bernoulli beams. The Assumed Mode Method (AMM) together with the Lagrangian approach is used to derive the closed-form dynamic. Two modes are considered for each link. Singular perturbation method is used to derive a composite control for the TFLR. A stable robust two-time scale controller without any data for modeling is developed. The slow subsystem is controlled by an ARBFANN based on global approximation while the Linear Quadratic Regulator (LQR) controller stabilizes the fast subsystem and guarantee the closed-loop stability. The ARBFANN with a sliding mode robust term is trained on-line to approximate unknown nonlinear system dynamics, suppress errors in the modeling of neural network and, guarantee closed-loop stability. To verify the validity of the proposed control strategy, simulation results are included.
KW - Artificial neural network
KW - Assumed modes
KW - Flexible links
KW - Radial basis function
KW - Singular perturbations and
UR - http://www.scopus.com/inward/record.url?scp=85105553640&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85105553640
SN - 9781792361234
T3 - Proceedings of the International Conference on Industrial Engineering and Operations Management
SP - 171
EP - 182
BT - Proceedings of the 2nd African International Conference on Industrial Engineering and Operations Management, 2020
PB - IEOM Society
T2 - 2nd African International Conference on Industrial Engineering and Operations Management, IEOM 2020
Y2 - 7 December 2020 through 10 December 2020
ER -