Machine learning-based model predictive control of diffusion-reaction processes

In this work, we develop a machine-learning-based predictive control design for nonlinear parabolic partial differential equation (PDE) systems using process state measurement time-series data. First, the Karhunen-Loève expansion is used to derive dominant spatial empirical eigenfunctions of PDE system from Then, these are as basis functions within Galerkin's model reduction framework temporal evolution small number modes capturing dynamics system. Subsequently, feedforward neural networks (FNN) approximate reduced-order data desired operating region. Lyapunov-based (MPC) scheme FNN models developed stabilize Finally, diffusion-reaction example demonstrate effectiveness proposed method.