Combining simulations and machine learning for neutron noise-based core diagnostics

Paper i proceeding, 2021

This paper gives an overview of the neutron noise-based core monitoring technique developed as part of the Horizon 2020 CORTEX project. This method relies on machine learning architectures trained and validated using advanced simulations of postulated anomalies in nuclear reactors. Using neutron flux measurements in operating reactors allows thereafter for the detection, classification and characterization of actual disturbances existing in the system.