Design of a sliding mode neurocontroller for a nuclear research reactor

This paper presents the application of a special technique which combines neural networks and sliding modes for solving the robust tracking problem in a nuclear reactor when only the input and the output are available. Due to the appropriate sensor absence, the design is based on a differential neural network observer. The highly nonlinear structure provided by this neural network is linearized using sliding mode. Finally, this linear model is employed for determining a sliding mode control for tracking a reference model. The efficiency of this technique with a guaranteed bound for the averaged tracking error is illustrated by simulation.