Prediction of Deformation-Induced Martensite Start Temperature by Convolutional Neural Network with Dual Mode Features
Various models were established for deformation-induced martensite start temperature prediction over decades. However, most of them are empirical or considering limited factors. In this research, a dual mode database for medium Mn steels was established and a convolutional neural network model, whic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/15/10/3495 |
| _version_ | 1797498237783900160 |
|---|---|
| author | Chenchong Wang Da Ren Yong Li Xu Wang Wei Xu |
| author_facet | Chenchong Wang Da Ren Yong Li Xu Wang Wei Xu |
| author_sort | Chenchong Wang |
| collection | DOAJ |
| description | Various models were established for deformation-induced martensite start temperature prediction over decades. However, most of them are empirical or considering limited factors. In this research, a dual mode database for medium Mn steels was established and a convolutional neural network model, which considered all composition, critical processing information and microstructure images as inputs, was built for <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>M</mi><mi>s</mi><mi>σ</mi></msubsup></mrow></semantics></math></inline-formula> prediction. By comprehensively considering composition, processing and microstructure factors, this model was more rational and much more accurate than traditional thermodynamic models. Also, by the full use of images information, this model has stronger ability to overcome overfitting compared with various traditional machine learning models. This framework provides inspiration for the similar data analysis issues with small sample datasets but different data modes in the field of materials science. |
| first_indexed | 2024-03-10T03:30:35Z |
| format | Article |
| id | doaj.art-1fc5ca1eb67848cda03c4b0ad56dcaa7 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-10T03:30:35Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-1fc5ca1eb67848cda03c4b0ad56dcaa72023-11-23T11:56:15ZengMDPI AGMaterials1996-19442022-05-011510349510.3390/ma15103495Prediction of Deformation-Induced Martensite Start Temperature by Convolutional Neural Network with Dual Mode FeaturesChenchong Wang0Da Ren1Yong Li2Xu Wang3Wei Xu4State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, ChinaState Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, ChinaState Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, ChinaSchool of Mechanical Engineering, Liaoning Petrochemical University, Fushun 113001, ChinaState Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110819, ChinaVarious models were established for deformation-induced martensite start temperature prediction over decades. However, most of them are empirical or considering limited factors. In this research, a dual mode database for medium Mn steels was established and a convolutional neural network model, which considered all composition, critical processing information and microstructure images as inputs, was built for <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>M</mi><mi>s</mi><mi>σ</mi></msubsup></mrow></semantics></math></inline-formula> prediction. By comprehensively considering composition, processing and microstructure factors, this model was more rational and much more accurate than traditional thermodynamic models. Also, by the full use of images information, this model has stronger ability to overcome overfitting compared with various traditional machine learning models. This framework provides inspiration for the similar data analysis issues with small sample datasets but different data modes in the field of materials science.https://www.mdpi.com/1996-1944/15/10/3495steelsmicrostructuredeformation-induced martensite transformationdual mode datadeep learning |
| spellingShingle | Chenchong Wang Da Ren Yong Li Xu Wang Wei Xu Prediction of Deformation-Induced Martensite Start Temperature by Convolutional Neural Network with Dual Mode Features Materials steels microstructure deformation-induced martensite transformation dual mode data deep learning |
| title | Prediction of Deformation-Induced Martensite Start Temperature by Convolutional Neural Network with Dual Mode Features |
| title_full | Prediction of Deformation-Induced Martensite Start Temperature by Convolutional Neural Network with Dual Mode Features |
| title_fullStr | Prediction of Deformation-Induced Martensite Start Temperature by Convolutional Neural Network with Dual Mode Features |
| title_full_unstemmed | Prediction of Deformation-Induced Martensite Start Temperature by Convolutional Neural Network with Dual Mode Features |
| title_short | Prediction of Deformation-Induced Martensite Start Temperature by Convolutional Neural Network with Dual Mode Features |
| title_sort | prediction of deformation induced martensite start temperature by convolutional neural network with dual mode features |
| topic | steels microstructure deformation-induced martensite transformation dual mode data deep learning |
| url | https://www.mdpi.com/1996-1944/15/10/3495 |
| work_keys_str_mv | AT chenchongwang predictionofdeformationinducedmartensitestarttemperaturebyconvolutionalneuralnetworkwithdualmodefeatures AT daren predictionofdeformationinducedmartensitestarttemperaturebyconvolutionalneuralnetworkwithdualmodefeatures AT yongli predictionofdeformationinducedmartensitestarttemperaturebyconvolutionalneuralnetworkwithdualmodefeatures AT xuwang predictionofdeformationinducedmartensitestarttemperaturebyconvolutionalneuralnetworkwithdualmodefeatures AT weixu predictionofdeformationinducedmartensitestarttemperaturebyconvolutionalneuralnetworkwithdualmodefeatures |