Machine-learning-assisted microstructure–property linkages of carbon nanotube-reinforced aluminum matrix nanocomposites produced by laser powder bed fusion

Abstract

In this study, the cellular microstructural features in a subgrain size of carbon nanotube (CNT)-reinforced aluminum matrix nanocomposites produced by laser powder bed fusion (LPBF) (a size range between 0.5–1 μm) were quantitatively extracted and calculated from scanning electron microscopy images by applying a cell segmentation method and various image analysis techniques. Over 80 geometric features for each cellular cell were extracted and statistically analyzed using machine learning techniques to explore the structure–property linkages of carbon nanotube reinforced AlSi10Mg nanocomposites. Predictive models for hardness and relative mass density were established using these subgrain cellular microstructural features. Data dimension reduction using principal component analysis was conducted to reduce the feature number to 3. The results showed that even AlSi10Mg nanocomposite specimens produced using different laser parameters exhibited similar Al–Si eutectic microstructures, displaying a large difference in their mechanical properties including hardness and relative mass density due to cellular structure variance. For hardness prediction, the Extra Tress regression models showed a relative error of 2.47% for prediction accuracies. For the relative mass density prediction, the Decision Tress regression models showed a relative error of 1.42% for prediction accuracies. The results demonstrate that the developed models deliver satisfactory performance for hardness and relative mass density prediction of AlSi10Mg nanocomposites. The framework established in this study can be applied to the LPBF process optimization and mechanical properties manipulation of AlSi10Mg-based alloys and other additive manufacturing newly designed alloys or composites.