Iterative learning algorithm of upper limb rehabilitation robot based on BP neural network

At present, in the trajectory tracking control of upper limb rehabilitation robot, there are nonlinear and uncertain problems of patients' spasticity disturbance. Therefore, an iterative learning control algorithm based on Back Propagation neural network is proposed in this paper. Based on the repeatability of the rehabilitation robot system, a multi-layer feedforward neural network trained by error reverse propagation algorithm is combined with iterative learning. The algorithm can effectively compensate the effect of spasmodic interference on the system performance and improve the convergence rate of trajectory tracking errors. The structure of the iterative learning control system based on neural network and the iterative learning control algorithm based on Back Propagation neural network are described. The process of network selection and robot trajectory tracking iterative learning control is given. Through simulation experiments, the feasibility and effectiveness of the algorithm are verified, which solves the above problems and meets the control requirements of rehabilitation training.