Neutron diffraction peak position prediction method and device based on neural network, and medium

Abstract

The invention discloses a neutron diffraction peak position prediction method and device based on a neural network and a medium, and the method comprises the steps: adjusting an included angle between a detector and an incident neutron beam, carrying out the diffraction of a detected material through the neutron beam, and collecting neutrons generated by the diffraction of the detected material through the detector; converting the channel position of the detector into a diffraction angle, and counting the diffraction intensity and the intensity error of each channel according to the number of neutrons collected by the detector; establishing a neural network architecture of a neutron diffraction peak position prediction model, taking the diffraction angle and intensity of each channel as input and output, taking an intensity error as a weight, introducing the weight into a loss function, training a neural network, and obtaining a function relationship between the angle and the diffraction intensity through the obtained neutron diffraction peak position prediction model; the angle corresponding to the maximum value of the diffraction intensity being the neutron diffraction peak position of the tested material. According to the invention, neutron diffraction data can be accurately fitted in real time, the neutron diffraction peak position can be accurately obtained, the residual stress of the tested material can be accurately measured, and the real stress field of the deep part of the material can be reflected.

Description

technical field [0001] The invention relates to the field of neutron scattering-material residual stress calculation, in particular to a neural network-based neutron diffraction peak position prediction method, equipment and medium. Background technique [0002] At this stage, there is a huge gap between the domestic cutting-edge manufacturing industry and developed countries such as the United States and Germany. In order to make up for shortcomings such as new material design, aero-engine manufacturing, and integrated circuit chip development, the country will implement intelligent manufacturing in depth. Therefore, in order to promote the optimization and upgrading of the manufacturing industry, we will accelerate the R&D and verification of high-end new materials, advanced aero-engines and gas turbines, and promote research on large-scale turbofan aero-engines with large bypass ratios, and F-class and G / H-class heavy-duty gas turbines. In order to fully study the mechani...

AI Technical Summary

Problems solved by technology

The calculation of material residual stress has extremely high requirements on the accuracy of neutron diffraction peak positions, and the diffraction peak position results fitted by the current algorithm are not enough to support the peak position accuracy required for stress calculation

Images