Abstract:
Solar thermal plants have high nonlinearities and non-manipulated energy source which
make their control task a very challenging work. Linear controllers can’t cope with undesirable
deviations of the outlet temperature over all the operation range of the dynamics of this type of
plants. Moreover, nonlinear predictive control relying on online nonlinear optimisation have the
drawback of time consuming and numerical calculus issues. In this work, neural nonlinear
predictive control and an infinite gain scheduling neural predictive control are designed and applied
to control the temperature in a distributed parabolic trough solar collector field. The performance
of both tracking and disturbance rejection of the proposed controller is compared to those the
nonlinear predictive control strategies. The superiority of the proposed control strategy is well
demonstrated through some indices in simulation results. The thesis concludes with
recommendations and perspectives for future works
