Towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learning
The simultaneous optimization of competing properties is a challenge of machine learning based materials design. We proposed a domain knowledge constrained active learning loop for the design of high entropy alloys with optimized strength and ductility, by narrowing down the unexplored space using t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127522008085 |
| _version_ | 1797991327642681344 |
|---|---|
| author | Hongchao Li Ruihao Yuan Hang Liang William Yi Wang Jinshan Li Jun Wang |
| author_facet | Hongchao Li Ruihao Yuan Hang Liang William Yi Wang Jinshan Li Jun Wang |
| author_sort | Hongchao Li |
| collection | DOAJ |
| description | The simultaneous optimization of competing properties is a challenge of machine learning based materials design. We proposed a domain knowledge constrained active learning loop for the design of high entropy alloys with optimized strength and ductility, by narrowing down the unexplored space using the valence electron concentration criterion. The active learning loop iterated six times and one alloy with an ultimate strength of 1258 MPa and an elongation of 17.3 % was synthesized. To uncover the underlying mechanism for synergetic optimization, we characterized the phase structure and eutectic microstructure, and discussed the possible origins from the view of strain hardening and crack initiation. The proposed framework that combines domain knowledge with machine learning can facilitate the design of target materials with coordinating optimization of competing properties. |
| first_indexed | 2024-04-11T08:50:23Z |
| format | Article |
| id | doaj.art-10011cf7b6694ff29c6a27a7d41a8bdc |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-04-11T08:50:23Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-10011cf7b6694ff29c6a27a7d41a8bdc2022-12-22T04:33:35ZengElsevierMaterials & Design0264-12752022-11-01223111186Towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learningHongchao Li0Ruihao Yuan1Hang Liang2William Yi Wang3Jinshan Li4Jun Wang5State Key Laboratory of Solidification Processing, Northwestern Polytechnical University, Xi’an 710072, ChinaCorresponding authors.; State Key Laboratory of Solidification Processing, Northwestern Polytechnical University, Xi’an 710072, ChinaState Key Laboratory of Solidification Processing, Northwestern Polytechnical University, Xi’an 710072, ChinaState Key Laboratory of Solidification Processing, Northwestern Polytechnical University, Xi’an 710072, ChinaState Key Laboratory of Solidification Processing, Northwestern Polytechnical University, Xi’an 710072, ChinaCorresponding authors.; State Key Laboratory of Solidification Processing, Northwestern Polytechnical University, Xi’an 710072, ChinaThe simultaneous optimization of competing properties is a challenge of machine learning based materials design. We proposed a domain knowledge constrained active learning loop for the design of high entropy alloys with optimized strength and ductility, by narrowing down the unexplored space using the valence electron concentration criterion. The active learning loop iterated six times and one alloy with an ultimate strength of 1258 MPa and an elongation of 17.3 % was synthesized. To uncover the underlying mechanism for synergetic optimization, we characterized the phase structure and eutectic microstructure, and discussed the possible origins from the view of strain hardening and crack initiation. The proposed framework that combines domain knowledge with machine learning can facilitate the design of target materials with coordinating optimization of competing properties.http://www.sciencedirect.com/science/article/pii/S0264127522008085Active learningDomain knowledgeBayesian optimizationHigh-entropy alloysMechanical properties |
| spellingShingle | Hongchao Li Ruihao Yuan Hang Liang William Yi Wang Jinshan Li Jun Wang Towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learning Materials & Design Active learning Domain knowledge Bayesian optimization High-entropy alloys Mechanical properties |
| title | Towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learning |
| title_full | Towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learning |
| title_fullStr | Towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learning |
| title_full_unstemmed | Towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learning |
| title_short | Towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learning |
| title_sort | towards high entropy alloy with enhanced strength and ductility using domain knowledge constrained active learning |
| topic | Active learning Domain knowledge Bayesian optimization High-entropy alloys Mechanical properties |
| url | http://www.sciencedirect.com/science/article/pii/S0264127522008085 |
| work_keys_str_mv | AT hongchaoli towardshighentropyalloywithenhancedstrengthandductilityusingdomainknowledgeconstrainedactivelearning AT ruihaoyuan towardshighentropyalloywithenhancedstrengthandductilityusingdomainknowledgeconstrainedactivelearning AT hangliang towardshighentropyalloywithenhancedstrengthandductilityusingdomainknowledgeconstrainedactivelearning AT williamyiwang towardshighentropyalloywithenhancedstrengthandductilityusingdomainknowledgeconstrainedactivelearning AT jinshanli towardshighentropyalloywithenhancedstrengthandductilityusingdomainknowledgeconstrainedactivelearning AT junwang towardshighentropyalloywithenhancedstrengthandductilityusingdomainknowledgeconstrainedactivelearning |