High-accuracy prediction of the thermo-physical properties of 6xxx series aluminum alloys using explainable artificial intelligence

被引:0
作者
Uzunoglu, Yusuf [1 ]
Alaca, Yusuf [2 ]
机构
[1] Erciyes Univ, Mat Sci & Engn, TR-38039 Kayseri, Turkiye
[2] Hitit Univ, Comp Engn, TR-19030 Corum, Turkiye
关键词
CALPHAD methodology; explainable artificial intelligence; artificial neural networks; alloy design; aluminum alloys;
D O I
10.1142/S2047684125500101
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Prediction models are commonly trained using datasets derived from open-source material data or detailed experimental studies to estimate material properties. However, preparing such datasets often requires time-consuming and labor-intensive processes. The CALPHAD (CALculation of PHAse Diagrams) methodology, on the other hand, enables the simulation of the physical, mechanical, and thermodynamic properties of materials for specific alloy compositions through phase transformation calculations and thermodynamic data sources. In this study, data obtained from aluminum alloys simulated using the CALPHAD-based JMatPro software were utilized as a dataset source to train a prediction model developed with Explainable Artificial Intelligence and Artificial Neural Networks. Accordingly, the thermo-physical properties (density, thermal conductivity, linear expansion, average expansion coefficient, Young's modulus, bulk modulus, shear modulus, and Poisson's ratio) of 225 different 6xxx series (Al-Mg-Si) aluminum alloys in the temperature range 25-155 degrees C were simulated, generating a dataset of 6075 rows. Of this dataset, 80% was used for model training, while the remaining 20% was used for validation and testing. The analyses revealed that the proposed model successfully predicted compositions with the desired thermo-physical properties at specific temperatures. The predicted composition was simulated under the same conditions as those used to generate the dataset in JMatPro software, and the obtained values showed a 98.57% accuracy rate compared to the target values. In conclusion, the dataset generated from aluminum alloys simulated using the CALPHAD methodology provides a reliable training source for AI-based material analysis. The proposed approach offers significant advantages in terms of speed and accuracy for material design and development processes.
引用
收藏
页数:22
相关论文
共 33 条
  • [1] Bergstra J, 2012, J MACH LEARN RES, V13, P281
  • [2] Brooks C. R., 1991, ASM Handbook, V4, P1861
  • [3] Machine learning for molecular and materials science
    Butler, Keith T.
    Davies, Daniel W.
    Cartwright, Hugh
    Isayev, Olexandr
    Walsh, Aron
    [J]. NATURE, 2018, 559 (7715) : 547 - 555
  • [4] Davis J. R., 1993, Metals Handbook Desk Edition, P351
  • [5] A machine learning-based classification approach for phase diagram prediction
    Deffrennes, Guillaume
    Terayama, Kei
    Abe, Taichi
    Tamura, Ryo
    [J]. MATERIALS & DESIGN, 2022, 215
  • [6] Dosinger C., 2022, Berg Huttenmann. Monatsh., V167, P29
  • [7] Elisha K., 2024, J. Eng. Inf. Technol., V12, P124
  • [8] Integrating forecasting methods to support finite element analysis and explore heat transfer complexities
    Fatima, Maryam
    Kim, Peter S.
    Lei, Youming
    Siddiqui, A. M.
    Sohail, Ayesha
    [J]. INTERNATIONAL JOURNAL OF NUMERICAL METHODS FOR HEAT & FLUID FLOW, 2024, 34 (12) : 4281 - 4305
  • [9] Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1
  • [10] Hillert Mats, 2007, Phase Equilibria, Phase Diagrams and Phase Transformations: their Thermodynamic Basis