ResNet-based gamma energy spectrum data analysis method, storage medium and ResNet-based gamma energy spectrum data analysis system

The invention relates to a ResNet-based gamma energy spectrum data analysis method. The method comprises the steps of generating gamma energy spectrum data for training by utilizing Monte Carlo simulation; performing normalization processing on each channel of counting in the gamma energy spectrum; taking each processed count as input, taking energy and quantity of gamma rays as output in the form of a one-dimensional array, and building a ResNet neural network model; training the built model by adopting a stochastic gradient descent algorithm; and obtaining predicted values of gamma ray energy and quantity through the trained model. The invention also provides a storage medium and a ResNet-based gamma energy spectrum data analysis system, and by adopting the ResNet-based gamma energy spectrum data analysis method, the storage medium and the system, the precision defects of an existing method in gamma ray energy and quantity analysis can be made up, and the accuracy of radioactive quantitative analysis is imp