Nonlinear Model Predictive Control of Single-Link Flexible-Joint Robot Using Recurrent Neural Network and Differential Evolution Optimization

A recurrent neural network (RNN) and differential evolution optimization (DEO) based nonlinear model predictive control (NMPC) technique is proposed for position of a single-link flexible-joint (FJ) robot. First, simple three-layer with rectified linear units as an activation function (ReLU-RNN) employed approximating the system dynamic model. Then, using RNN (MPC) scheme, DEO NMPC controller designed, algorithm used to solve controller. Finally, comparing numerical simulation findings demonstrates efficiency performance approach. The merit this method that not only precision satisfied, but also overshoots residual vibration are well suppressed.