Computationally efficient predictive control based on ANN state-space models

Artificial neural networks (ANN) have been shown to be flexible and effective function estimators for the identification of nonlinear state-space models. However, if the resulting models are used directly for nonlinear model predictive control (NMPC), the resulting nonlinear optimization problem is often overly complex due to the size of the network, requires the use of high-order observers to track the states of the ANN model, and the overall control scheme does not exploit the available autograd tools for these models. In this paper, we propose an efficient approach to auto-convert ANN state-space models to linear parameter-varying (LPV) form and solve predictive control problems by successive solutions of linear model predictive problems, corresponding to quadratic programs (QPs). Furthermore, we show how existing deep-learning methods, such as SUBNET that uses a state encoder, enable efficient implementation of MPCs on identified ANN models. Performance of the proposed approach is demonstrated by a simulation study on an unbalanced disc system.