Blanket remote maintenance robot motion control based on nonlinear model predictive control and neural network

Abstract

Blanket remote maintenance robot (BRMR) is a new generation robot used in blanket maintenance of China Fusion Engineering Test Reactor (CFETR). The BRMR is hydraulic (water) driven system. In this paper, firstly, the nonlinear model of the BRMR is established based on the physics-based method. Secondly, the nonlinear model predictive control (NMPC) algorithm is used to build master nonlinear controller of the BRMR. Thirdly, to enhance the control effectiveness of master NMPC controller, the auxiliary neural network controller is proposed to speed up system convergence process. Finally, the hybrid mater nonlinear model predictive with auxiliary neural network (HMNMPANN) controller is proposed. The simulation and experiment are conducted to verify the effectiveness of proposed control algorithms and controller.