Hybrid machine learning and microstructure-based approach for modeling relationship between microstructure and hardness of AA2099 Al−Li alloy

基于机器学习与显微组织的AA2099铝锂合金显微组织与硬度关系建模

A hybrid approach combining machine learning and microstructure analysis was proposed to investigate the relationship between microstructure and hardness of AA2099 Al−Li alloy through nano-indentation,X-ray diffraction(XRD)and electron backscatter diffraction(EBSD)technologies.Random forest regression(RFR)model was employed to predict hardness based on microstructural features and uncover influential factors and their rankings.The results show that the increased hardness correlates with a smaller distance from indentation to grain boundary(D_(dis))or a shorter minimum grain axis(D_(min)),a lower Schmidt factor in friction stir weld direction(SF_(FD)),and higher sine values of the angle between{111}slip plane and surface(sinθ_(min)).D_(dis) and D_(min) emerge as pivotal determinants in hardness prediction.High-angle grain boundaries imped dislocation slip,thereby increasing hardness.Crystallographic orientation also significantly influences hardness,especially in the presence of T_(1) phases along{111}Al habit planes.This effect is attributable to the variation in encountered T_(1) variants during indenter loading.Consequently,the importance ranking of microstructural features shifts depending on T_(1) phase abundance:in samples with limited T_(1) phases,D_(dis) or D_(min)>SF_(FD)>sinθ_(min),while in samples with abundant T_(1) phases,D_(dis) or D_(min)>sinθ_(min)>SF_(FD).

提出一种将机器学习和显微组织分析相结合的方法,通过纳米压痕、X射线衍射和电子背散射衍射(EBSD)技术,研究AA2099铝锂合金显微组织与硬度的关系。利用随机森林回归(RFR)模型,基于显微组织特征对硬度进行预测,揭示硬度的影响因素并对其重要性进行排序。研究表明,压痕到晶界的距离(D_(dis))越小、最短晶粒轴(D_(min))越短、Schmidt因子(SF_(FD))越小以及{111}滑移面和表面夹角的正弦值(sinθ_(min))越大,硬度越高。在硬度预测中,D_(dis)和D_(min)为关键因素。大角度晶界能阻碍位错滑移,从而提高材料硬度。此外,晶体学取向对硬度也具有显著影响,特别是在{111}Al惯习面上析出T_(1)相时。这种影响归因于在压痕加载过程中所遇到的不同类型的T_(1)相变体。因此,显微组织特征的重要性排序取决于T_(1)相,在T_(1)相有限的样品中,排序为D_(dis)或D_(min)>SF_(FD)>sinθ_(min);而在具有大量T_(1)相的样品中,排序变为D_(dis)或D_(min)>sinθ_(min)>SF_(FD)。