Computational intelligence-based trajectory scheduling for control of nuclear research reactors

This paper puts forward computational intelligence-based sigmoidal type trajectory scheduling for the control of nuclear research reactors. In order to calculate parameters of the sigmoidal type trajectory, a generator is designed based on artificial neural networks. Data used to train the artificial neural networks have been acquired by utilizing genetic algorithms. The contribution of the proposed trajectory to the reactor control system is investigated. Furthermore, the behaviour of the controller with the proposed trajectory has been tested for various initial and desired power levels, as well as under disturbance. It is seen that the controller can control the system successfully under all conditions within the acceptable error tolerance.