Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning
The Material Genome Initiative has been driven by high-throughput calculations, experiments, characterizations, and machine learning, which has accelerated the efficiency of the discovery of novel materials. However, the precise quantification of the material microstructure features and the construc...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/13/1/107 |
| _version_ | 1827623230930681856 |
|---|---|
| author | Gang Xu Xiaotong Zhang Jinwu Xu |
| author_facet | Gang Xu Xiaotong Zhang Jinwu Xu |
| author_sort | Gang Xu |
| collection | DOAJ |
| description | The Material Genome Initiative has been driven by high-throughput calculations, experiments, characterizations, and machine learning, which has accelerated the efficiency of the discovery of novel materials. However, the precise quantification of the material microstructure features and the construction of microstructure–property models are still challenging in optimizing the performance of materials. In this study, we proposed a new model based on machine learning to enhance the power of the data augmentation of the micrographs and construct a microstructure–property linkage for cast austenitic steels. The developed model consists of two modules: the data augmentation module and microstructure–property linkage module. The data augmentation module used a multi-layer convolution neural network architecture with diverse size filter to extract the microstructure features from irregular micrographs and generate new augmented microstructure images. The microstructure–property linkage module used a modified VGG model to establish the relationship between the microstructure and material property. Taking cast austenitic stainless steels after solution treating in different temperatures as an example, the results showed that the prediction accuracy of the developed machine learning model had been improved. The coefficient R<sup>2</sup> of the model was 0.965, and the medians were only ±2 J different with the measured impact toughness. |
| first_indexed | 2024-03-09T11:41:46Z |
| format | Article |
| id | doaj.art-b3b54e460d584ddcb48b83a46db85077 |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-09T11:41:46Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-b3b54e460d584ddcb48b83a46db850772023-11-30T23:30:49ZengMDPI AGMetals2075-47012023-01-0113110710.3390/met13010107Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine LearningGang Xu0Xiaotong Zhang1Jinwu Xu2Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaCollaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, ChinaThe Material Genome Initiative has been driven by high-throughput calculations, experiments, characterizations, and machine learning, which has accelerated the efficiency of the discovery of novel materials. However, the precise quantification of the material microstructure features and the construction of microstructure–property models are still challenging in optimizing the performance of materials. In this study, we proposed a new model based on machine learning to enhance the power of the data augmentation of the micrographs and construct a microstructure–property linkage for cast austenitic steels. The developed model consists of two modules: the data augmentation module and microstructure–property linkage module. The data augmentation module used a multi-layer convolution neural network architecture with diverse size filter to extract the microstructure features from irregular micrographs and generate new augmented microstructure images. The microstructure–property linkage module used a modified VGG model to establish the relationship between the microstructure and material property. Taking cast austenitic stainless steels after solution treating in different temperatures as an example, the results showed that the prediction accuracy of the developed machine learning model had been improved. The coefficient R<sup>2</sup> of the model was 0.965, and the medians were only ±2 J different with the measured impact toughness.https://www.mdpi.com/2075-4701/13/1/107machine learningconvolutional neural networkdata augmentationmicrostructure–property linkagecast austenitic stainless steel |
| spellingShingle | Gang Xu Xiaotong Zhang Jinwu Xu Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning Metals machine learning convolutional neural network data augmentation microstructure–property linkage cast austenitic stainless steel |
| title | Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning |
| title_full | Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning |
| title_fullStr | Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning |
| title_full_unstemmed | Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning |
| title_short | Data Augmentation of Micrographs and Prediction of Impact Toughness for Cast Austenitic Steel by Machine Learning |
| title_sort | data augmentation of micrographs and prediction of impact toughness for cast austenitic steel by machine learning |
| topic | machine learning convolutional neural network data augmentation microstructure–property linkage cast austenitic stainless steel |
| url | https://www.mdpi.com/2075-4701/13/1/107 |
| work_keys_str_mv | AT gangxu dataaugmentationofmicrographsandpredictionofimpacttoughnessforcastausteniticsteelbymachinelearning AT xiaotongzhang dataaugmentationofmicrographsandpredictionofimpacttoughnessforcastausteniticsteelbymachinelearning AT jinwuxu dataaugmentationofmicrographsandpredictionofimpacttoughnessforcastausteniticsteelbymachinelearning |