Thesis supervisor: Jurij Sidor
co-supervisor: László Gulyás
Location of studies (in Hungarian): ELTE Abbreviation of location of studies: ELTE
Description of the research topic:
Modern production of materials accounts for a very complex shape change of final products. In many instances, the cost-efficient manufacturing processes involve deformation and heat treatment steps, whereas both of them are complex due to the intricate nature of materials. In polycrystalline metallic systems, the billions of micro-sized crystals are subjected to drastic transformation processes. These mesoscopic changes are not easy to access with simple numerical approaches, since majority of them involve a number of model parameters, which need to be defined for each material type and each processing route separately. Gaining a comprehensive understanding of the evolution of structural elements across different length scales, including the microscopic scale and nanoscale, necessitates the application of advanced computational techniques. In light of this, the primary objective of the PhD research is to investigate the boundaries of current algorithms and to develop new ones. This will facilitate identifying correlations between the processing parameters and the development of characteristic microstructure and substructure elements during thermomechanical processing. The numerical outcomes obtained via virtual processing will be utilized to enhance the existing technologies and pave the way for the creation of novel processing approaches.
Among the advanced computational techniques planned to be applied, the widely applied tools of (deep) machine learning offer a promising route. In complex application domains like the one at hand, however, the possibility to inject domain knowledge (e.g., physical laws and well-understood chemical processes) is of paramount importance. This possibility limits the search space and thus increases the quality of the emerging model. Therefore, the application of such a hybrid approach will be studied. This may also enable methods that improve the explainability of the predictions of the trained model.
Required language skills: angol Recommended language skills (in Hungarian): B1 Further requirements: MSc in one of the following fields: informatics, materials engineering, civil engineering, physics, mechanical engineering or related areas.
Fluent in English.
Number of students who can be accepted: 1
Deadline for application: 2024-05-31
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
