A Nonlinear Control Method for a Hand Rehabilitation Exoskeleton

For the dynamic equation of the rehabilitation exoskeleton layout on the hand, its nonlinear factors cannot be ignored. Traditional control technology has a great impact on the real-time performance of the control process. Therefore, after estimating the nonlinear function of the dynamic equation based on the RBF network, this paper uses adaptive sliding mode control to adaptively control the RBF neural network sliding mode controller. First, on the basis of smoothing the control quantity, the differential evolution algorithm is used to optimize the parameters of the network, thereby further improving the fitting ability of the network. Simulation experiments show that the nonlinear term fitting effect of the RBF neural network output is good for the control output. The RBF adaptive sliding mode controller optimized by the differential evolution algorithm has the characteristics of fast and accurate trajectory and speed tracking and better robustness.