Micropillar compression using discrete dislocation dynamics and machine learning
Discrete dislocation dynamics (DDD) simulations reveal the evolution of dislocation structures and the interaction of dislocations. This study investigated the compression behavior of single-crystal copper micropillars using few-shot machine learning with data provided by DDD simulations. Two types...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Theoretical and Applied Mechanics Letters |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095034923000557 |
| _version_ | 1797399134605410304 |
|---|---|
| author | Jin Tao Dean Wei Junshi Yu Qianhua Kan Guozheng Kang Xu Zhang |
| author_facet | Jin Tao Dean Wei Junshi Yu Qianhua Kan Guozheng Kang Xu Zhang |
| author_sort | Jin Tao |
| collection | DOAJ |
| description | Discrete dislocation dynamics (DDD) simulations reveal the evolution of dislocation structures and the interaction of dislocations. This study investigated the compression behavior of single-crystal copper micropillars using few-shot machine learning with data provided by DDD simulations. Two types of features are considered: external features comprising specimen size and loading orientation and internal features involving dislocation source length, Schmid factor, the orientation of the most easily activated dislocations and their distance from the free boundary. The yielding stress and stress-strain curves of single-crystal copper micropillar are predicted well by incorporating both external and internal features of the sample as separate or combined inputs. It is found that the Machine learning accuracy predictions for single-crystal micropillar compression can be improved by incorporating easily activated dislocation features with external features. However, the effect of easily activated dislocation on yielding is less important compared to the effects of specimen size and Schmid factor which includes information of orientation but becomes more evident in small-sized micropillars. Overall, incorporating internal features, especially the information of most easily activated dislocations, improves predictive capabilities across diverse sample sizes and orientations. |
| first_indexed | 2024-03-09T01:35:05Z |
| format | Article |
| id | doaj.art-4e99a6b33b53493d989598c44282694b |
| institution | Directory Open Access Journal |
| issn | 2095-0349 |
| language | English |
| last_indexed | 2024-03-09T01:35:05Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Theoretical and Applied Mechanics Letters |
| spelling | doaj.art-4e99a6b33b53493d989598c44282694b2023-12-09T06:05:45ZengElsevierTheoretical and Applied Mechanics Letters2095-03492024-01-01141100484Micropillar compression using discrete dislocation dynamics and machine learningJin Tao0Dean Wei1Junshi Yu2Qianhua Kan3Guozheng Kang4Xu Zhang5School of Mechanics and Aerospace Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Mechanics and Aerospace Engineering, Southwest Jiaotong University, Chengdu 610031, China; State Key Laboratory of Nonlinear Mechanics, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Mechanics and Aerospace Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Mechanics and Aerospace Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Mechanics and Aerospace Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Mechanics and Aerospace Engineering, Southwest Jiaotong University, Chengdu 610031, China; Corresponding author.Discrete dislocation dynamics (DDD) simulations reveal the evolution of dislocation structures and the interaction of dislocations. This study investigated the compression behavior of single-crystal copper micropillars using few-shot machine learning with data provided by DDD simulations. Two types of features are considered: external features comprising specimen size and loading orientation and internal features involving dislocation source length, Schmid factor, the orientation of the most easily activated dislocations and their distance from the free boundary. The yielding stress and stress-strain curves of single-crystal copper micropillar are predicted well by incorporating both external and internal features of the sample as separate or combined inputs. It is found that the Machine learning accuracy predictions for single-crystal micropillar compression can be improved by incorporating easily activated dislocation features with external features. However, the effect of easily activated dislocation on yielding is less important compared to the effects of specimen size and Schmid factor which includes information of orientation but becomes more evident in small-sized micropillars. Overall, incorporating internal features, especially the information of most easily activated dislocations, improves predictive capabilities across diverse sample sizes and orientations.http://www.sciencedirect.com/science/article/pii/S2095034923000557Discrete dislocation dynamics simulationsMachine learningSize effectsOrientation effectsMicrostructural features |
| spellingShingle | Jin Tao Dean Wei Junshi Yu Qianhua Kan Guozheng Kang Xu Zhang Micropillar compression using discrete dislocation dynamics and machine learning Theoretical and Applied Mechanics Letters Discrete dislocation dynamics simulations Machine learning Size effects Orientation effects Microstructural features |
| title | Micropillar compression using discrete dislocation dynamics and machine learning |
| title_full | Micropillar compression using discrete dislocation dynamics and machine learning |
| title_fullStr | Micropillar compression using discrete dislocation dynamics and machine learning |
| title_full_unstemmed | Micropillar compression using discrete dislocation dynamics and machine learning |
| title_short | Micropillar compression using discrete dislocation dynamics and machine learning |
| title_sort | micropillar compression using discrete dislocation dynamics and machine learning |
| topic | Discrete dislocation dynamics simulations Machine learning Size effects Orientation effects Microstructural features |
| url | http://www.sciencedirect.com/science/article/pii/S2095034923000557 |
| work_keys_str_mv | AT jintao micropillarcompressionusingdiscretedislocationdynamicsandmachinelearning AT deanwei micropillarcompressionusingdiscretedislocationdynamicsandmachinelearning AT junshiyu micropillarcompressionusingdiscretedislocationdynamicsandmachinelearning AT qianhuakan micropillarcompressionusingdiscretedislocationdynamicsandmachinelearning AT guozhengkang micropillarcompressionusingdiscretedislocationdynamicsandmachinelearning AT xuzhang micropillarcompressionusingdiscretedislocationdynamicsandmachinelearning |