Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learning
The tensile properties of 2219-T8 aluminum alloy TIG welding joint were significantly affected by the microstructure, local mechanical properties and weld geometry. This paper proposed a machine learning model to predict and optimize the tensile properties of 2219-T8 aluminum alloy TIG welding joint...
| 出版年: | Materials & Design |
|---|---|
| 主要な著者: | , , , , , , |
| フォーマット: | 論文 |
| 言語: | 英語 |
| 出版事項: |
Elsevier
2024-09-01
|
| 主題: | |
| オンライン･アクセス: | http://www.sciencedirect.com/science/article/pii/S026412752400649X |
| _version_ | 1849858991097643008 |
|---|---|
| author | Zhandong Wan Zongli Yi Yue Zhao Sicong Zhang Quan Li Jian Lin Aiping Wu |
| author_facet | Zhandong Wan Zongli Yi Yue Zhao Sicong Zhang Quan Li Jian Lin Aiping Wu |
| author_sort | Zhandong Wan |
| collection | DOAJ |
| container_title | Materials & Design |
| description | The tensile properties of 2219-T8 aluminum alloy TIG welding joint were significantly affected by the microstructure, local mechanical properties and weld geometry. This paper proposed a machine learning model to predict and optimize the tensile properties of 2219-T8 aluminum alloy TIG welding joint. The relationship between tensile strength of joint and weld geometry, weld zone and partially melted zone (PMZ) properties was developed by Kriging model combining whale optimization algorithm (WOA). This surrogate model demonstrated a high precision, with R2 = 0.952 and RMSE=3.77 MPa. The surrogate model, which also served as a welding process guide, was utilized to determine the ideal weld geometry corresponding to various weak zone properties. By applying the optimization process based on the surrogate model, the optimized joint strength coefficient reached 70 %, and elongation exceeded 4 %. The collaborative regulation mechanism of geometry and property was also discussed. |
| format | Article |
| id | doaj-art-b5879cfa20f64beb9f1c8d0b6f218a8a |
| institution | Directory of Open Access Journals |
| issn | 0264-1275 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Elsevier |
| record_format | Article |
| spelling | doaj-art-b5879cfa20f64beb9f1c8d0b6f218a8a2025-08-20T01:20:34ZengElsevierMaterials & Design0264-12752024-09-0124511327410.1016/j.matdes.2024.113274Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learningZhandong Wan0Zongli Yi1Yue Zhao2Sicong Zhang3Quan Li4Jian Lin5Aiping Wu6College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, China; Department of Mechanical Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Mechanical Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Mechanical Engineering, Tsinghua University, Beijing 100084, China; State Key Laboratory of Clean and Efficient Turbomachinery Power Equipment, Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China; Key Laboratory for Advanced Materials Processing Technology, Ministry of Education, Tsinghua University, Beijing 100084, ChinaDepartment of Mechanical Engineering, Tsinghua University, Beijing 100084, ChinaCapital Aerospace Machinery Corporation Limited, Beijing 100076, ChinaCollege of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, ChinaDepartment of Mechanical Engineering, Tsinghua University, Beijing 100084, China; State Key Laboratory of Clean and Efficient Turbomachinery Power Equipment, Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China; Key Laboratory for Advanced Materials Processing Technology, Ministry of Education, Tsinghua University, Beijing 100084, China; Corresponding author at: Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China.The tensile properties of 2219-T8 aluminum alloy TIG welding joint were significantly affected by the microstructure, local mechanical properties and weld geometry. This paper proposed a machine learning model to predict and optimize the tensile properties of 2219-T8 aluminum alloy TIG welding joint. The relationship between tensile strength of joint and weld geometry, weld zone and partially melted zone (PMZ) properties was developed by Kriging model combining whale optimization algorithm (WOA). This surrogate model demonstrated a high precision, with R2 = 0.952 and RMSE=3.77 MPa. The surrogate model, which also served as a welding process guide, was utilized to determine the ideal weld geometry corresponding to various weak zone properties. By applying the optimization process based on the surrogate model, the optimized joint strength coefficient reached 70 %, and elongation exceeded 4 %. The collaborative regulation mechanism of geometry and property was also discussed.http://www.sciencedirect.com/science/article/pii/S026412752400649X2219-T8 aluminum alloyTIG weldingMachine learningTensile propertiesKriging model |
| spellingShingle | Zhandong Wan Zongli Yi Yue Zhao Sicong Zhang Quan Li Jian Lin Aiping Wu Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learning 2219-T8 aluminum alloy TIG welding Machine learning Tensile properties Kriging model |
| title | Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learning |
| title_full | Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learning |
| title_fullStr | Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learning |
| title_full_unstemmed | Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learning |
| title_short | Prediction and optimization of tensile properties of 2219-T8 aluminum alloy TIG welding joint by machine learning |
| title_sort | prediction and optimization of tensile properties of 2219 t8 aluminum alloy tig welding joint by machine learning |
| topic | 2219-T8 aluminum alloy TIG welding Machine learning Tensile properties Kriging model |
| url | http://www.sciencedirect.com/science/article/pii/S026412752400649X |
| work_keys_str_mv | AT zhandongwan predictionandoptimizationoftensilepropertiesof2219t8aluminumalloytigweldingjointbymachinelearning AT zongliyi predictionandoptimizationoftensilepropertiesof2219t8aluminumalloytigweldingjointbymachinelearning AT yuezhao predictionandoptimizationoftensilepropertiesof2219t8aluminumalloytigweldingjointbymachinelearning AT sicongzhang predictionandoptimizationoftensilepropertiesof2219t8aluminumalloytigweldingjointbymachinelearning AT quanli predictionandoptimizationoftensilepropertiesof2219t8aluminumalloytigweldingjointbymachinelearning AT jianlin predictionandoptimizationoftensilepropertiesof2219t8aluminumalloytigweldingjointbymachinelearning AT aipingwu predictionandoptimizationoftensilepropertiesof2219t8aluminumalloytigweldingjointbymachinelearning |