Predictive Analysis of Wettability of Al–Si Based Multiphase Alloys and Aluminum Matrix Composites by Machine Learning and Physical Modeling

Abstract

Wetting of multiphase alloys and their composites depends on multiple parameters, and these relationships are difficult to predict from first principles only. We study correlations between the composition, surface finish, and microstructure of Al–Si alloys (Si content 7–50%) and Al metal matrix composites (MMCs) with graphite (Gr), NiAl3, and SiC and the water contact angle (CA) experimentally, theoretically, and with machine learning (ML) techniques. Their surface properties were modified by mechanical abrasion, etching, and addition of alloying elements. An ML approach was developed to investigate correlations between the predictor variables (properties of the materials) and the CA. Theoretical models of wetting of rough surfaces (Wenzel, Cassie–Baxter, and their modifications) do not fully capture the CA, while ML models follow the experimental values. A full factorial design is utilized with combinations of all levels of the predictor factors (grit size, silicon percentage, droplet size, elapsed time, etching, reinforcing particles). To map the predictor variables to the response variables, 409 experimental data points were applied to train and test various supervised ML models, namely, regression, artificial neural network (ANN), chi-square automatic interaction detection (CHAID), extreme gradient boosting (XGBoost), and random forest. The correlations between the most significant factors and CA are explored through visualization techniques. The most accurately trained model shows a strong positive linear correlation (r > 0.9) between predicted and observed CA values in the test set, indicating the robustness of the model. The experimental measurements and artificial intelligence results demonstrate that CA increases following mechanically abrading the surface, etching, and adding Gr to the surface. The ML methods are promising to predict wetting properties and to provide a deeper understanding of the physical phenomena associated with the wettability of metallic alloys and their metal matrix composites.

Surface Stoichiometry and Roughness of a Degraded A380 Alloy after Casting, Technical Cleaning and Packaging

“…In Figure 3 d, a narrow-range Al 2p XPS spectrum is shown. Fitting it with metallic and oxide/hydroxide components is an obvious choice, i.e., Al 2p components at 72.3 eV, corresponding to elementary aluminium, and 73.9 eV, corresponding to Al oxide or hydroxide [ 12 , 13 , 14 ], are thus obtained.…”

“…In addition, achieving a flawless surface treatment of the castings remains a great challenge for the metal foundry industry [ 1 ]. Dedicated studies aiming to improve the castability of Al–Si alloys [ 2 , 3 ], their mechanical properties [ 4 ], the properties of wear and friction [ 4 , 5 , 6 , 7 , 8 ], aging and fatigue behaviour [ 9 , 10 , 11 ], fouling and corrosion resistance [ 12 , 13 ], etc., are extensive and constantly ongoing.…”

“…The surface roughness has a significant effect on reducing the corrosion resistance, as does a change in the surface chemistry. Here, the constant trade-off between these two influential surface parameters must be considered [ 13 , 23 , 24 ].…”

“…Due to the increased need for applications that require high strength and wear resistance, additions of various alloying elements, e.g., Mg, Cu, and Zn on the microstructure, and mechanical and tribological properties are investigated [ 4 , 30 ], and parallel to this, additions of various particles in the case of Al-based, metal-matrix composites (MMCs) [ 13 , 24 ]. For an assessment of the wear behaviour, machine-learning models currently available are a very supportive tool in predicting the friction and wear of Al alloys from material and tribological test data [ 7 , 8 , 13 , 24 ]. A proper topography characterization and further calculations of the representative surface parameters are essential to correlate manufacturing process parameters and key quality factors.…”

A Review of Application of Machine Learning in Design, Synthesis, and Characterization of Metal Matrix Composites: Current Status and Emerging Applications

“…They used a data-driven approach for various multiphase alloys [69][70][71] and metal matrix composite. [72][73][74] They demonstrated that the established physics-based models in the field of wetting, i.e., Wenzel 75 and Cassie-Baxter, 76 fail to precisely predict the contact angle values of complex systems like MMC, while the data-driven model showed high robustness to capture the variability of the water contact angle (CA) as a function of surface physical and chemical properties and test parameters. Table IV…”