Search

The extensive energy consumption of primary aluminum production stimulates increasing need of producing primary-quality alloys with secondary sources, during which process amount of non-metallic inclusions (NMIs) in the alloy must be strictly controlled. In the present study funded by AMAP Open Innovation Research Cluster, NMIs generated during remelting a 5000 Al-Mg alloy was investigated to offer benchmarking characters of NMIs with respect to type, morphology, size, composition, and concentration. Under different remelting conditions NMIs formed in the melt ahead of solidification were concentrated using Porous Disc Filtration Apparatus (PoDFA) and characterized microstructurally and quantitatively. Investigated conditions included heating cycle, organic contaminations, and refractory materials. Results suggested oxide films and cuboid particles as typical oxides with, respectively, different compositions. The amount of formed oxides declined with the increase of heating rate. With respect to aluminum carbide (Al4C3), organic contaminations were confirmed to lead to an increased amount of its formation. The carbon-containing refractory material contributed more significantly than organic contaminations on the formation of Al4C3 at melt temperatures over 760 °C. Formulas were derived based on trial results to enable translation of NMIs PoDFA value [mm2/kg] into their mass fraction [ppm] in the melt. [ABSTRACT FROM AUTHOR]

[Display omitted] • Utilized machine learning to enhance the development of heat-resistant aluminum alloys. • Designed alloys exhibit outstanding high-temperature performance. • SHAP analysis highlights the critical roles of Ti and V, guiding future designs. • The simplicity and affordability of these alloys suggest significant industrial application potential. The high-temperature strength of aluminum alloys must be enhanced for improving their applicability across industries. This study proposes a machine learning approach for developing heat-resistant aluminum alloys. Using a combination of correlation-based screening and genetic algorithms, feature selection was performed on descriptors derived from the atomic compositions of alloys. Then, alloy compositions and descriptors were used as input variables of the model to improve its robustness and applicability due to the richness of information. Four distinct alloys were discovered by employing Bayesian optimization within the framework of a quaternary alloy system. The best alloy demonstrated an exceptional high-temperature strength of 175 MPa at 300 °C in the absence of heat treatment. Microstructural analyses of these alloys indicated the critical role of vanadium-rich intermetallics in enhancing the high-temperature strength of aluminum alloys. Furthermore, the output of the model was explained using the SHapley Additive exPlanations method. The findings emphasize the critical importance of titanium and vanadium in enhancing the high-temperature strength of aluminum alloys tailored for environments with high thermal stress. [ABSTRACT FROM AUTHOR]