Neural network model for correlating microstructural features and hardness properties of nickel-based superalloys
In precipitation hardening metallic materials, the size and volume fraction of precipitation phases are regarded as primary microstructural parameters to control the strength instead of others. Why? In this research, a supervised learning approach was developed to correlate γ′ precipitation microstr...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-11-01
|
| Series: | Journal of Materials Research and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2238785420319013 |
| _version_ | 1818414345294446592 |
|---|---|
| author | Yangping Li Yangyi Liu Sihua Luo Zi Wang Ke Wang Zaiwang Huang Haifeng Zhao Liang Jiang |
| author_facet | Yangping Li Yangyi Liu Sihua Luo Zi Wang Ke Wang Zaiwang Huang Haifeng Zhao Liang Jiang |
| author_sort | Yangping Li |
| collection | DOAJ |
| description | In precipitation hardening metallic materials, the size and volume fraction of precipitation phases are regarded as primary microstructural parameters to control the strength instead of others. Why? In this research, a supervised learning approach was developed to correlate γ′ precipitation microstructures with hardness based on experimentally observed 483 scanning electron microscope (SEM) images comprised with different γ′ precipitates. First, up to 23 descriptors were defined and extracted numerically as training inputs from SEM images by pattern recognition techniques. Then, 10 descriptors were further selected to reduce computational cost of deep neural network (DNN) with the assistance of shallow neural network (SNN). Furthermore, to improve the accuracy of DNN, new training sets were proposed to combine these 10 descriptors with two more descriptors: area distribution and one heat treatment parameter - cooling rate. In conclusion, the supervised learning approach was proven to outperform the prediction of existing physics-based constitutive models. |
| first_indexed | 2024-12-14T11:17:37Z |
| format | Article |
| id | doaj.art-a72a71e6d82e4bcab7284d0f38fe0482 |
| institution | Directory Open Access Journal |
| issn | 2238-7854 |
| language | English |
| last_indexed | 2024-12-14T11:17:37Z |
| publishDate | 2020-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Materials Research and Technology |
| spelling | doaj.art-a72a71e6d82e4bcab7284d0f38fe04822022-12-21T23:03:56ZengElsevierJournal of Materials Research and Technology2238-78542020-11-01961446714477Neural network model for correlating microstructural features and hardness properties of nickel-based superalloysYangping Li0Yangyi Liu1Sihua Luo2Zi Wang3Ke Wang4Zaiwang Huang5Haifeng Zhao6Liang Jiang7University of Chinese Academy of Sciences, Beijing, PR China; Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, PR ChinaUniversity of Chinese Academy of Sciences, Beijing, PR China; Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, PR ChinaState Key Laboratory of Powder Metallurgy, Central South University, Changsha, Hunan, PR ChinaState Key Laboratory of Powder Metallurgy, Central South University, Changsha, Hunan, PR ChinaUniversity of Chinese Academy of Sciences, Beijing, PR China; Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, PR ChinaState Key Laboratory of Powder Metallurgy, Central South University, Changsha, Hunan, PR China; Corresponding author.University of Chinese Academy of Sciences, Beijing, PR China; Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, PR China; Corresponding author.Institute for Advanced Studies in Precision Material, Yantai University, Yantai, Shandong, PR China; Corresponding author.In precipitation hardening metallic materials, the size and volume fraction of precipitation phases are regarded as primary microstructural parameters to control the strength instead of others. Why? In this research, a supervised learning approach was developed to correlate γ′ precipitation microstructures with hardness based on experimentally observed 483 scanning electron microscope (SEM) images comprised with different γ′ precipitates. First, up to 23 descriptors were defined and extracted numerically as training inputs from SEM images by pattern recognition techniques. Then, 10 descriptors were further selected to reduce computational cost of deep neural network (DNN) with the assistance of shallow neural network (SNN). Furthermore, to improve the accuracy of DNN, new training sets were proposed to combine these 10 descriptors with two more descriptors: area distribution and one heat treatment parameter - cooling rate. In conclusion, the supervised learning approach was proven to outperform the prediction of existing physics-based constitutive models.http://www.sciencedirect.com/science/article/pii/S2238785420319013Powder metallurgy nickel base superalloysγ′ precipitation microstructureHardnessMachine learningDeep neural network (DNN) |
| spellingShingle | Yangping Li Yangyi Liu Sihua Luo Zi Wang Ke Wang Zaiwang Huang Haifeng Zhao Liang Jiang Neural network model for correlating microstructural features and hardness properties of nickel-based superalloys Journal of Materials Research and Technology Powder metallurgy nickel base superalloys γ′ precipitation microstructure Hardness Machine learning Deep neural network (DNN) |
| title | Neural network model for correlating microstructural features and hardness properties of nickel-based superalloys |
| title_full | Neural network model for correlating microstructural features and hardness properties of nickel-based superalloys |
| title_fullStr | Neural network model for correlating microstructural features and hardness properties of nickel-based superalloys |
| title_full_unstemmed | Neural network model for correlating microstructural features and hardness properties of nickel-based superalloys |
| title_short | Neural network model for correlating microstructural features and hardness properties of nickel-based superalloys |
| title_sort | neural network model for correlating microstructural features and hardness properties of nickel based superalloys |
| topic | Powder metallurgy nickel base superalloys γ′ precipitation microstructure Hardness Machine learning Deep neural network (DNN) |
| url | http://www.sciencedirect.com/science/article/pii/S2238785420319013 |
| work_keys_str_mv | AT yangpingli neuralnetworkmodelforcorrelatingmicrostructuralfeaturesandhardnesspropertiesofnickelbasedsuperalloys AT yangyiliu neuralnetworkmodelforcorrelatingmicrostructuralfeaturesandhardnesspropertiesofnickelbasedsuperalloys AT sihualuo neuralnetworkmodelforcorrelatingmicrostructuralfeaturesandhardnesspropertiesofnickelbasedsuperalloys AT ziwang neuralnetworkmodelforcorrelatingmicrostructuralfeaturesandhardnesspropertiesofnickelbasedsuperalloys AT kewang neuralnetworkmodelforcorrelatingmicrostructuralfeaturesandhardnesspropertiesofnickelbasedsuperalloys AT zaiwanghuang neuralnetworkmodelforcorrelatingmicrostructuralfeaturesandhardnesspropertiesofnickelbasedsuperalloys AT haifengzhao neuralnetworkmodelforcorrelatingmicrostructuralfeaturesandhardnesspropertiesofnickelbasedsuperalloys AT liangjiang neuralnetworkmodelforcorrelatingmicrostructuralfeaturesandhardnesspropertiesofnickelbasedsuperalloys |