کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Robust Neuro-Adaptive Fuzzy Sliding Mode Control for a Remotely Operated Underwater Vehicle Manipulator

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 :

Remotely operated underwater vehicles،Robotic manipulators،Sliding mode control،Fuzzy logic،RBF neural network

چکیده :

Considering the increase in the various applications of remotely operated underwater vehicle (ROV) in recent years, this research proposes a fuzzy sliding mode control method using radial basis function neural networks (RBF-NNs) in order to enhance trajectory tracking by a 6 degree of freedom (DoF) remotely operated underwater vehicle manipulator. Sliding mode control is utilized as the central part of this method which leads to robustness against the highly nonlinear dynamics of the robot as well as the uncertainties and disturbances in the hydrodynamical underwater environments while performing high precision tasks. For this end, the capabilities of the sliding mode control are enhanced by employing an adaptive fuzzy sliding mode controller (AFSMC), with a proportional-–integral-–derivative (PID) sliding surface. To provide the adaptiveness, radial basis function neural networks are utilized to estimate the nonlinearities of the manipulator dynamics. The performance and robustness of the proposed controller are verified through simulation experiments under several different conditions.