Adaptive neural model-based predictive control with steady state offset compensation for a distributed solar collector field

An approach to the control of a distributed solar collector field relying on a non-linear adaptive constrained model-based predictive control scheme with steady-state offset compensation is developed and implemented. This methodology is based on a non-linear state-space neural networks within a model-based predictive control framework. The neural network training is carried out online by means of a distribution approximation filter approach. In order to get rid of static offsets an offset compensator is incorporated in the control loop. Tests on the ACUREX field illustrate the feasibility of the proposed approach.