Gamma-ray energy spectrum analysis method based on approximation coefficient and deep learning

Abstract

The invention discloses a gamma-ray energy spectrum analysis method based on the approximation coefficient and deep learning. The gamma-ray energy spectrum analysis method comprises following steps of modeling a gamma-ray detector by means of a monte carlo method, and simulating an interested nuclide energy spectrum to obtain a simulated energy spectrum; measuring the energy spectrum by the gamma-ray detector, carrying out smoothing processing on the energy spectrum, carrying out background rejection according to the time scale, and obtaining a pure count spectrum; extracting the approximation coefficient of the simulated energy spectrum by means of a wavelet decomposition method, carrying out normalization processing on the approximation coefficient of the simulated energy spectrum, extracting the approximation coefficient of the pure count spectrum by means of the wavelet decomposition method, and carrying out normalization processing on the approximation coefficient of the pure count spectrum; and taking the approximation coefficient of the simulated energy spectrum as a training sample of a deep learning network in order to predict the nuclide composition in the power spectrum actually measured by the gamma-ray detector. According to the invention, by extracting the approximation coefficient of the simulated energy spectrum and training the deep learning network by means of the simulation sample, and employing the simulation sample to predict the nuclide composition of the actually measured energy spectrum, the energy spectrum nuclides can be identified quickly and stably.

Description

technical field [0001] The invention belongs to the field of gamma energy spectrum analysis, in particular to a gamma energy spectrum analysis method based on approximation coefficients and deep learning. Background technique [0002] The accuracy and reliability of gamma spectrum analysis depend to a large extent on the processing of overlapping peaks. As the main carrier of gamma spectrum information, the characteristic peaks of nuclides usually overlap with each other. Due to the limitation of the energy resolution of the gamma detector and the interference of natural background radiation, it becomes very difficult to extract effective information from the gamma energy spectrum with overlapping peaks. Although the traditional neural network can solve this problem by inputting the full spectrum, due to the limitation of the number of hidden layers, its learning ability and predictive ability are low, and manual feature extraction is required to reduce the data dimension. ...

AI Technical Summary

Problems solved by technology

Due to the limitation of the energy resolution of the gamma detector and the interference of natural background radiation, it becomes very difficult to extract effective information from the gamma energy spectrum with overlapping peaks

Although the traditional neural network can solve this problem by inputting the full spectrum, due to the limitation of the number of hidden layers, its learning ability and predictive ability are low, and manual feature extraction is required to reduce the data dimension.

Images