A machine learning enabled ultra-fine grain design strategy of Mg–Mn-based alloys
Grain size is the critical characteristic of ultra-fine grain Magnesium (Mg), which is a concrete representation of the whole heat deformation procedure. In this paper, a design strategy was proposed to quantitatively investigate the composition and process conditions for the preparation of ultrafin...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | Journal of Materials Research and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2238785423003241 |
| _version_ | 1827978285667057664 |
|---|---|
| author | Xiaoxi Mi Xuerui Jing Hailian Wang Jianbin Xu Jia She Aitao Tang Bjørn Holmedal Fusheng Pan |
| author_facet | Xiaoxi Mi Xuerui Jing Hailian Wang Jianbin Xu Jia She Aitao Tang Bjørn Holmedal Fusheng Pan |
| author_sort | Xiaoxi Mi |
| collection | DOAJ |
| description | Grain size is the critical characteristic of ultra-fine grain Magnesium (Mg), which is a concrete representation of the whole heat deformation procedure. In this paper, a design strategy was proposed to quantitatively investigate the composition and process conditions for the preparation of ultrafine grains. Herein, a dataset of Mg–Mn-based wrought alloys was constructed, and the average grain size was set as the design target. Based on this dataset, five machine learning (ML) algorithms, including the k-nearest neighbor (kNN), support vector machine (SVM), decision tree (DT), random forest (RF), and artificial neural network (ANN), were integrated to conduct in-depth analysis and make predictions. Among these models, the computational accuracy of both the DT classifier and ANN predictor is around 90%. The main factors affecting the formation of ultrafine grains were found by ML, and the interrelationships between the features were quantitatively analyzed as well. Then, four suggested routes with conditions were extracted from the tree models for preparing ultrafine grain Mg alloys. And four new Mg alloys were designed through these routes and taken as experimental validation. After testing, the actual grain sizes are close to the predictions, and the accuracy of the experimental verification exceeds 80%. Compared with conventional “trial and error” design methods, the grain design strategy proposed in this paper brings new thought and good prior guidance for developing high-performance commercial Mg alloys. |
| first_indexed | 2024-04-09T21:18:28Z |
| format | Article |
| id | doaj.art-77cd8bce36644b199b9b7e76078bf029 |
| institution | Directory Open Access Journal |
| issn | 2238-7854 |
| language | English |
| last_indexed | 2024-04-09T21:18:28Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Materials Research and Technology |
| spelling | doaj.art-77cd8bce36644b199b9b7e76078bf0292023-03-28T06:48:07ZengElsevierJournal of Materials Research and Technology2238-78542023-03-012345764590A machine learning enabled ultra-fine grain design strategy of Mg–Mn-based alloysXiaoxi Mi0Xuerui Jing1Hailian Wang2Jianbin Xu3Jia She4Aitao Tang5Bjørn Holmedal6Fusheng Pan7College of Materials Science and Engineering, Chongqing University, Chongqing, ChinaCollege of Materials Science and Engineering, Chongqing University, Chongqing, ChinaCollege of Materials Science and Engineering, Chongqing University, Chongqing, ChinaDepartment of Materials Science and Engineering, Norwegian University of Science and Technology (NTNU), Trondheim, NorwayCollege of Materials Science and Engineering, Chongqing University, Chongqing, China; National Engineering Research Center for Magnesium Alloys, Chongqing University, Chongqing, ChinaCollege of Materials Science and Engineering, Chongqing University, Chongqing, China; National Engineering Research Center for Magnesium Alloys, Chongqing University, Chongqing, China; Corresponding author.Department of Materials Science and Engineering, Norwegian University of Science and Technology (NTNU), Trondheim, NorwayCollege of Materials Science and Engineering, Chongqing University, Chongqing, China; National Engineering Research Center for Magnesium Alloys, Chongqing University, Chongqing, ChinaGrain size is the critical characteristic of ultra-fine grain Magnesium (Mg), which is a concrete representation of the whole heat deformation procedure. In this paper, a design strategy was proposed to quantitatively investigate the composition and process conditions for the preparation of ultrafine grains. Herein, a dataset of Mg–Mn-based wrought alloys was constructed, and the average grain size was set as the design target. Based on this dataset, five machine learning (ML) algorithms, including the k-nearest neighbor (kNN), support vector machine (SVM), decision tree (DT), random forest (RF), and artificial neural network (ANN), were integrated to conduct in-depth analysis and make predictions. Among these models, the computational accuracy of both the DT classifier and ANN predictor is around 90%. The main factors affecting the formation of ultrafine grains were found by ML, and the interrelationships between the features were quantitatively analyzed as well. Then, four suggested routes with conditions were extracted from the tree models for preparing ultrafine grain Mg alloys. And four new Mg alloys were designed through these routes and taken as experimental validation. After testing, the actual grain sizes are close to the predictions, and the accuracy of the experimental verification exceeds 80%. Compared with conventional “trial and error” design methods, the grain design strategy proposed in this paper brings new thought and good prior guidance for developing high-performance commercial Mg alloys.http://www.sciencedirect.com/science/article/pii/S2238785423003241Mg–Mn-based alloyUltrafine grainMachine learningClassificationPrediction |
| spellingShingle | Xiaoxi Mi Xuerui Jing Hailian Wang Jianbin Xu Jia She Aitao Tang Bjørn Holmedal Fusheng Pan A machine learning enabled ultra-fine grain design strategy of Mg–Mn-based alloys Journal of Materials Research and Technology Mg–Mn-based alloy Ultrafine grain Machine learning Classification Prediction |
| title | A machine learning enabled ultra-fine grain design strategy of Mg–Mn-based alloys |
| title_full | A machine learning enabled ultra-fine grain design strategy of Mg–Mn-based alloys |
| title_fullStr | A machine learning enabled ultra-fine grain design strategy of Mg–Mn-based alloys |
| title_full_unstemmed | A machine learning enabled ultra-fine grain design strategy of Mg–Mn-based alloys |
| title_short | A machine learning enabled ultra-fine grain design strategy of Mg–Mn-based alloys |
| title_sort | machine learning enabled ultra fine grain design strategy of mg mn based alloys |
| topic | Mg–Mn-based alloy Ultrafine grain Machine learning Classification Prediction |
| url | http://www.sciencedirect.com/science/article/pii/S2238785423003241 |
| work_keys_str_mv | AT xiaoximi amachinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT xueruijing amachinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT hailianwang amachinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT jianbinxu amachinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT jiashe amachinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT aitaotang amachinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT bjørnholmedal amachinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT fushengpan amachinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT xiaoximi machinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT xueruijing machinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT hailianwang machinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT jianbinxu machinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT jiashe machinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT aitaotang machinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT bjørnholmedal machinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys AT fushengpan machinelearningenabledultrafinegraindesignstrategyofmgmnbasedalloys |