Processing Laue Microdiffraction Raster Scanning Patterns with Machine Learning Algorithms: A Case Study with a Fatigued Polycrystalline Sample
The massive amount of diffraction images collected in a raster scan of Laue microdiffraction calls for a fast treatment with little if any human intervention. The conventional method that has to index diffraction patterns one-by-one is laborious and can hardly give real-time feedback. In this work,...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/15/4/1502 |
| _version_ | 1797478437014732800 |
|---|---|
| author | Peng Rong Fengguo Zhang Qing Yang Han Chen Qiwei Shi Shengyi Zhong Zhe Chen Haowei Wang |
| author_facet | Peng Rong Fengguo Zhang Qing Yang Han Chen Qiwei Shi Shengyi Zhong Zhe Chen Haowei Wang |
| author_sort | Peng Rong |
| collection | DOAJ |
| description | The massive amount of diffraction images collected in a raster scan of Laue microdiffraction calls for a fast treatment with little if any human intervention. The conventional method that has to index diffraction patterns one-by-one is laborious and can hardly give real-time feedback. In this work, a data mining protocol based on unsupervised machine learning algorithm was proposed to have a fast segmentation of the scanning grid from the diffraction patterns without indexation. The sole parameter that had to be set was the so-called “distance threshold” that determined the number of segments. A statistics-oriented criterion was proposed to set the “distance threshold”. The protocol was applied to the scanning images of a fatigued polycrystalline sample and identified several regions that deserved further study with, for instance, differential aperture X-ray microscopy. The proposed data mining protocol is promising to help economize the limited beamtime. |
| first_indexed | 2024-03-09T21:31:55Z |
| format | Article |
| id | doaj.art-e37604237b444f6fa0f3c6727951626a |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-09T21:31:55Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-e37604237b444f6fa0f3c6727951626a2023-11-23T20:54:17ZengMDPI AGMaterials1996-19442022-02-01154150210.3390/ma15041502Processing Laue Microdiffraction Raster Scanning Patterns with Machine Learning Algorithms: A Case Study with a Fatigued Polycrystalline SamplePeng Rong0Fengguo Zhang1Qing Yang2Han Chen3Qiwei Shi4Shengyi Zhong5Zhe Chen6Haowei Wang7Chengdu Aircraft Industrial (Group) Co., Ltd., Chengdu 610073, ChinaState Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Metal Matrix Composites, Shanghai Jiao Tong University, Shanghai 200240, ChinaThe massive amount of diffraction images collected in a raster scan of Laue microdiffraction calls for a fast treatment with little if any human intervention. The conventional method that has to index diffraction patterns one-by-one is laborious and can hardly give real-time feedback. In this work, a data mining protocol based on unsupervised machine learning algorithm was proposed to have a fast segmentation of the scanning grid from the diffraction patterns without indexation. The sole parameter that had to be set was the so-called “distance threshold” that determined the number of segments. A statistics-oriented criterion was proposed to set the “distance threshold”. The protocol was applied to the scanning images of a fatigued polycrystalline sample and identified several regions that deserved further study with, for instance, differential aperture X-ray microscopy. The proposed data mining protocol is promising to help economize the limited beamtime.https://www.mdpi.com/1996-1944/15/4/1502Laue microdiffractionunsupervised machine learningfatigued microstructure |
| spellingShingle | Peng Rong Fengguo Zhang Qing Yang Han Chen Qiwei Shi Shengyi Zhong Zhe Chen Haowei Wang Processing Laue Microdiffraction Raster Scanning Patterns with Machine Learning Algorithms: A Case Study with a Fatigued Polycrystalline Sample Materials Laue microdiffraction unsupervised machine learning fatigued microstructure |
| title | Processing Laue Microdiffraction Raster Scanning Patterns with Machine Learning Algorithms: A Case Study with a Fatigued Polycrystalline Sample |
| title_full | Processing Laue Microdiffraction Raster Scanning Patterns with Machine Learning Algorithms: A Case Study with a Fatigued Polycrystalline Sample |
| title_fullStr | Processing Laue Microdiffraction Raster Scanning Patterns with Machine Learning Algorithms: A Case Study with a Fatigued Polycrystalline Sample |
| title_full_unstemmed | Processing Laue Microdiffraction Raster Scanning Patterns with Machine Learning Algorithms: A Case Study with a Fatigued Polycrystalline Sample |
| title_short | Processing Laue Microdiffraction Raster Scanning Patterns with Machine Learning Algorithms: A Case Study with a Fatigued Polycrystalline Sample |
| title_sort | processing laue microdiffraction raster scanning patterns with machine learning algorithms a case study with a fatigued polycrystalline sample |
| topic | Laue microdiffraction unsupervised machine learning fatigued microstructure |
| url | https://www.mdpi.com/1996-1944/15/4/1502 |
| work_keys_str_mv | AT pengrong processinglauemicrodiffractionrasterscanningpatternswithmachinelearningalgorithmsacasestudywithafatiguedpolycrystallinesample AT fengguozhang processinglauemicrodiffractionrasterscanningpatternswithmachinelearningalgorithmsacasestudywithafatiguedpolycrystallinesample AT qingyang processinglauemicrodiffractionrasterscanningpatternswithmachinelearningalgorithmsacasestudywithafatiguedpolycrystallinesample AT hanchen processinglauemicrodiffractionrasterscanningpatternswithmachinelearningalgorithmsacasestudywithafatiguedpolycrystallinesample AT qiweishi processinglauemicrodiffractionrasterscanningpatternswithmachinelearningalgorithmsacasestudywithafatiguedpolycrystallinesample AT shengyizhong processinglauemicrodiffractionrasterscanningpatternswithmachinelearningalgorithmsacasestudywithafatiguedpolycrystallinesample AT zhechen processinglauemicrodiffractionrasterscanningpatternswithmachinelearningalgorithmsacasestudywithafatiguedpolycrystallinesample AT haoweiwang processinglauemicrodiffractionrasterscanningpatternswithmachinelearningalgorithmsacasestudywithafatiguedpolycrystallinesample |