کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

A Novel RBFNN-Based Triple Terminal Sliding Mode Control for robotic manipulators

نویسندگان :

Mahdi Armoon¹ Marzie Lafouti² Babak Tavassoli³ Hamid D.Taghirad⁴

1- دانشگاه صنعتی خواجه نصیرالدین طوسی 2- دانشگاه صنعتی خواجه نصیرالدین طوسی 3- دانشگاه صنعتی خواجه نصیرالدین طوسی 4- دانشگاه صنعتی خواجه نصیرالدین طوسی

کلمات کلیدی :

Triple terminal sliding mode control،Radial basis function neural network،Robotic manipulators،Finite time control،Lyapunov approach

چکیده :

This paper introduces a novel RBFNN-based triple terminal sliding mode control method which has been implemented on robotic system. Radial basis function neural networks (RBFNNs) and a triple terminal sliding mode controller are designed for the 3-DOF manipulator since an adaptive robust position control is used to track the robots' manipulator . In this research, friction, errors in modeling and external disturbances are considered as uncertainties. The RBFNN approximates the nonlinearity of the robot dynamics according to adaptive laws including unknown parameters estimation which leads to ensuring the asymptotic stability of the closed-loop system. Lyapunov's theorem of stability is used to determine the parameters of the controller and an online adaptive learning algorithm is utilized in order to adjust them. Thus, the stability, robustness and appropriate tracking performance for this robotic system are guaranteed. The simulations performed on a three-link robot show high accuracy of tracking, reduction of chattering phenomenon and fast .response in a finite-time despite approximate errors and uncertainties