A Power Regulation Strategy for Heat Pipe Cooled Reactors Based on Deep Learning and Hybrid Data-Driven Optimization Algorithm

Abstract

Heat pipe cooled reactors are suitable for deployment in remote or isolated areas as reliable small-scale power sources due to their good design characteristics. In order to cope with the real-time changing power demand in a dynamic environment, this study proposes a decision-making strategy for power regulation of heat pipe cooled reactors based on deep learning and hybrid data-driven optimization algorithm, which helps to achieve autonomous safe and efficient control of heat pipe cooled reactors under specific power demand. Firstly, an artificial neural network-based power prediction model for heat pipe cooled reactors is constructed; secondly, an evaluation criterion of power regulation schemes that integrates reactor safety and operational effectiveness is established based on utility theory, and finally, a hybrid data-driven optimization algorithm is proposed, which can quickly discover the power regulation scheme with the best utility under specific power demand. The strategy's effectiveness is verified by taking the power regulation process of the MegaPower heat pipe cooled reactor as an example. The results show that the strategy can make stable, accurate and near-optimal power regulation scheme decisions for arbitrary power demand within 20 seconds.

Keywords: Heat pipe cooled reactor, Power Control, Artificial Neural Network, Decision Algorithm