Constrained Adaptive Non-linear Neural Model-Based Predictive Control of a Distributed Solar Collector Field

This paper describes the application of a non-linear adaptive constrained model-based predictive control scheme to the distributed collector field of a solar power plant at the Plataforma Solar de Almería (Spain). This methodology takes advantage of the intrinsic non-linear modelling capabilities of non-linear state-space neural networks and of their online training by means of an unscented Kalman filter. Tests on the ACUREX field illustrate the great engineering potential of the proposed control strategy.