A stress intensity predictive model for reactor pressure vessel via coupled signal processing and machine learning model

Reactor pressure vessel (RPV) is in the center of the nuclear containment building and houses nuclear fuel, there is a risk of a nuclear power plant radiation leakage accident in the event of an earthquake. It is important to determine stress intensities that evaluate structural integrity and also analyze the seismic response of RPV in order to prevent severe disasters. We propose a stress intensity regression model using a signal extraction method and machine learning in addition to the existing method. The combined way between the methods from finite element model enables us to predict the stress intensity immediately with only signal features and properties. It could be an additional verification tool to ensure safety of nuclear power plants.