Data-driven modeling provides an efficient approach to compute approximate solutions for complex multiphysics parametrized problems such as induction hardening (IH) process. Basically, some physical quantities of interest (QoI) related to the IH process will be evaluated under real-time constraint, without any explicit knowledge of the physical behavior of the system. Hence, computationally expensive finite element models will be replaced by a parametric solution, called metamodel. Two data-driven models for temporal evolution of temperature and austenite phase transformation, during induction heating, were first developed by using the proper orthogonal decomposition based reduced-order model followed by a nonlinear regression method for temperature field and a classification combined with regression for austenite evolution. Then, data-driven and hybrid models were created to predict hardness, after quenching. It is shown that the results of artificial intelligence models are promising and provide good approximations in the low-data limit case.

No abstract

No abstract

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

In this paper, a new elastic viscoplastic micromechanical modelling is proposed to represent the semi-solid behaviour and predict the ductile-brittle transition of the C38LTT near the solidus. It is based on a viscoplastic modelling previously presented in [1]. The originality of the new model comes from three main enhancements: the transition between the solid state and the semi-solid state was included meaning that the material properties were taken temperature-dependent, the elastic properties was taken into account similarly as [2] and the evolution of the internal variable describing the degree of agglomeration of the solid phase was enhanced. The model was implemented in the commercial software FORGE©. Tensile tests representing the experimental thermal conditions and obtained using a GLEEBLE© machine were simulated. The comparison of the predicted and experimental results shows that, for the first time to our knowledge, the three steps of the load-displacement response and ductile-brittle transition were successfully described.