Design of Refractory Alloys for Desired Thermal Conductivity via AI-Assisted In-Silico Microstructure Realization
A computational methodology based on supervised machine learning (ML) is described for characterizing and designing anisotropic refractory composite alloys with desired thermal conductivities (TCs). The structural design variables are parameters of our fast computational microstructure generator, wh...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/16/3/1088 |
| _version_ | 1797623968958513152 |
|---|---|
| author | Seyed Mohammad Ali Seyed Mahmoud Ghader Faraji Mostafa Baghani Mohammad Saber Hashemi Azadeh Sheidaei Majid Baniassadi |
| author_facet | Seyed Mohammad Ali Seyed Mahmoud Ghader Faraji Mostafa Baghani Mohammad Saber Hashemi Azadeh Sheidaei Majid Baniassadi |
| author_sort | Seyed Mohammad Ali Seyed Mahmoud |
| collection | DOAJ |
| description | A computational methodology based on supervised machine learning (ML) is described for characterizing and designing anisotropic refractory composite alloys with desired thermal conductivities (TCs). The structural design variables are parameters of our fast computational microstructure generator, which were linked to the physical properties. Based on the Sobol sequence, a sufficiently large dataset of artificial microstructures with a fixed volume fraction (VF) was created. The TCs were calculated using our previously developed fast Fourier transform (FFT) homogenization approach. The resulting dataset was used to train our optimal autoencoder, establishing the intricate links between the material’s structure and properties. Specifically, the trained ML model’s inverse design of tungsten-30% (VF) copper with desired TCs was investigated. According to our case studies, our computational model accurately predicts TCs based on two perpendicular cut-section images of the experimental microstructures. The approach can be expanded to the robust inverse design of other material systems based on the target TCs. |
| first_indexed | 2024-03-11T09:36:15Z |
| format | Article |
| id | doaj.art-28f7080f32864c5faf6d9fc79c75e74c |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-11T09:36:15Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-28f7080f32864c5faf6d9fc79c75e74c2023-11-16T17:16:58ZengMDPI AGMaterials1996-19442023-01-01163108810.3390/ma16031088Design of Refractory Alloys for Desired Thermal Conductivity via AI-Assisted In-Silico Microstructure RealizationSeyed Mohammad Ali Seyed Mahmoud0Ghader Faraji1Mostafa Baghani2Mohammad Saber Hashemi3Azadeh Sheidaei4Majid Baniassadi5School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran 15614, IranSchool of Mechanical Engineering, College of Engineering, University of Tehran, Tehran 15614, IranSchool of Mechanical Engineering, College of Engineering, University of Tehran, Tehran 15614, IranAerospace Engineering Department, Iowa State University, Ames, IA 50011, USAAerospace Engineering Department, Iowa State University, Ames, IA 50011, USASchool of Mechanical Engineering, College of Engineering, University of Tehran, Tehran 15614, IranA computational methodology based on supervised machine learning (ML) is described for characterizing and designing anisotropic refractory composite alloys with desired thermal conductivities (TCs). The structural design variables are parameters of our fast computational microstructure generator, which were linked to the physical properties. Based on the Sobol sequence, a sufficiently large dataset of artificial microstructures with a fixed volume fraction (VF) was created. The TCs were calculated using our previously developed fast Fourier transform (FFT) homogenization approach. The resulting dataset was used to train our optimal autoencoder, establishing the intricate links between the material’s structure and properties. Specifically, the trained ML model’s inverse design of tungsten-30% (VF) copper with desired TCs was investigated. According to our case studies, our computational model accurately predicts TCs based on two perpendicular cut-section images of the experimental microstructures. The approach can be expanded to the robust inverse design of other material systems based on the target TCs.https://www.mdpi.com/1996-1944/16/3/1088microstructure identificationsmachine learningthermal characterizationFast Fourier Transform (FFT) homogenization |
| spellingShingle | Seyed Mohammad Ali Seyed Mahmoud Ghader Faraji Mostafa Baghani Mohammad Saber Hashemi Azadeh Sheidaei Majid Baniassadi Design of Refractory Alloys for Desired Thermal Conductivity via AI-Assisted In-Silico Microstructure Realization Materials microstructure identifications machine learning thermal characterization Fast Fourier Transform (FFT) homogenization |
| title | Design of Refractory Alloys for Desired Thermal Conductivity via AI-Assisted In-Silico Microstructure Realization |
| title_full | Design of Refractory Alloys for Desired Thermal Conductivity via AI-Assisted In-Silico Microstructure Realization |
| title_fullStr | Design of Refractory Alloys for Desired Thermal Conductivity via AI-Assisted In-Silico Microstructure Realization |
| title_full_unstemmed | Design of Refractory Alloys for Desired Thermal Conductivity via AI-Assisted In-Silico Microstructure Realization |
| title_short | Design of Refractory Alloys for Desired Thermal Conductivity via AI-Assisted In-Silico Microstructure Realization |
| title_sort | design of refractory alloys for desired thermal conductivity via ai assisted in silico microstructure realization |
| topic | microstructure identifications machine learning thermal characterization Fast Fourier Transform (FFT) homogenization |
| url | https://www.mdpi.com/1996-1944/16/3/1088 |
| work_keys_str_mv | AT seyedmohammadaliseyedmahmoud designofrefractoryalloysfordesiredthermalconductivityviaaiassistedinsilicomicrostructurerealization AT ghaderfaraji designofrefractoryalloysfordesiredthermalconductivityviaaiassistedinsilicomicrostructurerealization AT mostafabaghani designofrefractoryalloysfordesiredthermalconductivityviaaiassistedinsilicomicrostructurerealization AT mohammadsaberhashemi designofrefractoryalloysfordesiredthermalconductivityviaaiassistedinsilicomicrostructurerealization AT azadehsheidaei designofrefractoryalloysfordesiredthermalconductivityviaaiassistedinsilicomicrostructurerealization AT majidbaniassadi designofrefractoryalloysfordesiredthermalconductivityviaaiassistedinsilicomicrostructurerealization |