Revealing geometrically necessary dislocation density from electron backscatter patterns via multi-modal deep learning

Qi Lu; Jiayi Wu; Shilong Liu; Shiqi Zhang; Xiaorong Cai; Wei Li; Jun Jiang; Xuejun Jin

doi:10.1016/j.ultramic.2022.113519

Revealing geometrically necessary dislocation density from electron backscatter patterns via multi-modal deep learning

Ultramicroscopy. 2022 Jul:237:113519. doi: 10.1016/j.ultramic.2022.113519. Epub 2022 Mar 29.

Authors

Qi Lu¹, Jiayi Wu², Shilong Liu³, Shiqi Zhang⁴, Xiaorong Cai¹, Wei Li¹, Jun Jiang⁵, Xuejun Jin⁶

Affiliations

¹ Shanghai Key Laboratory of Materials Laser Processing and Modification, Shanghai Jiao Tong University, Shanghai 200240, PR China; Institute of Advanced Steels and Materials, School of Materials Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, PR China.
² Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an 710049, China.
³ Shanghai Key Laboratory of Materials Laser Processing and Modification, Shanghai Jiao Tong University, Shanghai 200240, PR China; Institute of Advanced Steels and Materials, School of Materials Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, PR China. Electronic address: sliu6@sjtu.edu.cn.
⁴ The State Key Laboratory of Refractories and Metallurgy, Wuhan University of Science and Technology, Wuhan, Hubei 430081, China. Electronic address: zhangsq@wust.edu.cn.
⁵ Department of Mechanical Engineering, Imperial College London, London SW7 2AZ, UK.
⁶ Shanghai Key Laboratory of Materials Laser Processing and Modification, Shanghai Jiao Tong University, Shanghai 200240, PR China; Institute of Advanced Steels and Materials, School of Materials Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, PR China. Electronic address: jin@sjtu.edu.cn.

PMID: 35378371
DOI: 10.1016/j.ultramic.2022.113519

Abstract

The characterization of geometrically necessary dislocation (GND) is central to understanding the plastic deformation in materials. Currently, fast and accurate determination of GND density via Electron Backscatter Diffraction (EBSD) remains a challenge. Here, a multi-modal deep learning approach is proposed to predict GND density in terms of electron backscatter patterns (EBSPs) and dislocation configurations. The proposed multi-modal architecture consists of two separated convolutional neural network (CNN) processing streams. One CNN stream aims at extracting pattern shifts from EBSPs, and the other CNN stream focuses on learning suitable representations of dislocation configurations. We also introduce a specific data augmentation strategy termed neighboring pairs generating strategy for the GND prediction task. Taking the GND density from dictionary indexing-based analysis as the target property, high accuracy is achieved on several aluminum samples. Also, our networks are robust to various forms of noise, and the prediction speed is as fast as modern EBSD scanning rates, enabling real-time GND density analysis possible.

Keywords: Dislocation configuration map; Electron backscatter patterns; GND; Multi-modal deep learning; Neighboring pairs generating strategy.