AUTOMATIC STARTUP OF NUCLEAR REACTORS USING DIFFERENTIAL NEURAL NETWORKS

In this paper, the automatic startup of a nuclear reactor subjected to period scram constraint is considered. To achieve this operation in a minimum time avoiding the difficulties associated with the application on-line of maximum principle or dynamic programming, first the optimal trajectory is calculated off-line. Next, the nuclear plant considered as a black box is identified by a differential neural network. The structure provided by this neural identifier is fed back to follow the optimal trajectory. The modeling error is compensated by the usage of the power derivative. Thus, the asymptotic stability of the tracking error can be guaranteed.