In-situ electron diffraction data processing analysis method based on machine learning and application

Abstract

The invention provides an in-situ electron diffraction data processing analysis method based on machine learning and application, and the method comprises the steps: automatic calibration of the center of a single-frame electron diffraction pattern, automatic detection and tracking of a diffraction spot, calculation and calibration of a diffraction ring, and analysis of the in-situ electron diffraction data. And a data storage and analysis method for radial radius, bright-dark contrast and tangential angle variation of a single diffraction spot. According to the method, methods of machine learning, image processing and the like are combined, and qualitative analysis and quantitative calculation of each diffraction spot in each frame of electron diffraction pattern in the in-situ electron diffraction data are realized.

Description

technical field [0001] The present invention relates to the technical field of electron microscopy structure characterization, the technical field of machine learning, and the technical field of image processing, and in particular, to an in-situ electron diffraction data processing and analysis method and application based on machine learning. Background technique [0002] Electron Diffraction refers to the diffraction phenomenon that occurs when electrons with a certain energy pass through certain samples or obstacles. In the field of electron microscopy structural characterization, electron diffraction is a powerful tool for microstructural analysis of thin samples, expanding the analytical capabilities of transmission electron microscopy in inverted space. The internal microstructure of the sample is different, the diffraction pattern (Diffraction Pattern) is also different. For example, the diffraction pattern of amorphous materials is diffuse scattering rings; while po...

AI Technical Summary

Problems solved by technology

However, due to the dynamic diffraction effect of electron diffraction and the possibility of defects inside the crystal, the electron diffraction intensity does not simply have a linear correlation with the microstructure, and it is generally difficult to rule out kinetic effects and defects in the analysis.

In addition, relying on traditional manual methods to calibrate, calculate and analyze the diffraction spots and diffraction rings in the electron diffraction pattern is not only highly subjective, but also very time-consuming

Especially for in-situ electron diffraction data, a single data packet often contains hundreds of electron diffraction images. If manual methods are still used to calibrate and analyze each image, the calculation and analysis process will be difficult due to the huge amount of data. become difficult to practice

In addition, the traditional electronic diffraction pattern processing method usually performs annular integration on the diffraction spots and diffraction rings, and analyzes the microstructure characteristics of the material according to the one-dimensional contrast information after the annular integration. This method loses the two-dimensional distribution characteristics of the diffraction intensity. And ignore the specific information carried by a single diffraction spot

Images