Journal of Rare Earths, Год журнала: 2025, Номер unknown
Опубликована: Май 1, 2025
Язык: Английский
Journal of Rare Earths, Год журнала: 2025, Номер unknown
Опубликована: Май 1, 2025
Язык: Английский
Metals, Год журнала: 2025, Номер 15(5), С. 512 - 512
Опубликована: Май 1, 2025
The development and validation of constitutive models for high-temperature deformation are critical bridging microstructure evolution with macroscopic mechanical behavior in materials. In this study, we systematically analyzed the hot Fe-Mn-Cr-based alloys, compared modeling processes physical, phenomenological, data-driven approaches detail, optimized their structural predictive properties. First, advantages, disadvantages, applicability three traditional models, namely physical Arrhenius model, phenomenological Johnson–Cook artificial neural network (ANN) flow stress prediction. Subsequently, mathematical derivations numerical optimization methods evaluated. parameters architecture ANN model then using algorithms to enhance training efficiency prediction accuracy. Finally, sensitivity analysis integrated Bayesian posterior probability density functions enables calibration uncertainty quantification. results demonstrate that achieves superior accuracy (R2 = 0.9985, AARE 3.01%) methods. inference-based quantification parameter significantly enhances reliability interpretability parameters. This study not only reveals strain–temperature coupling effects alloys but also provides systematic methodological support high-performance a theoretical foundation material processing technology design.
Язык: Английский
Процитировано
0Journal of Materials Engineering and Performance, Год журнала: 2025, Номер unknown
Опубликована: Май 12, 2025
Язык: Английский
Процитировано
0Journal of Rare Earths, Год журнала: 2025, Номер unknown
Опубликована: Май 1, 2025
Язык: Английский
Процитировано
0