Model predictive control for nonlinear affine systems based on the simplified dual neural network

Model predictive control (MPC), also known as receding horizon control (RHC), is an advanced control strategy for optimizing the performance of control systems. For nonlinear systems, standard MPC schemes based on linearization would result in poor performance. In this paper, we propose an MPC scheme for nonlinear affine systems based on a recurrent neural network (RNN) called the simplified dual network. The proposed RNN-based approach is efficient and suitable for real-time MPC implementation in industrial applications. Simulation results are provided to demonstrate the effectiveness and efficiency of the proposed MPC scheme.