6533b824fe1ef96bd128084c
RESEARCH PRODUCT
Continuous dynamic recrystallization phenomena modelling in friction stir welding of aluminium alloys: A neural-network-based approach
Gianluca BuffaLivan Fratinisubject
Materials scienceArtificial neural networkMechanical EngineeringMetallurgyMechanical engineeringRecrystallization (metallurgy)chemistry.chemical_elementStrain rateIndustrial and Manufacturing EngineeringFinite element methodchemistryAluminiumvisual_artAluminium alloyvisual_art.visual_art_mediumFriction stir weldingFriction weldingdescription
The current paper focuses on the continuous dynamic recrystallization phenomena (CDRX) occurring in friction stir welding processes of AA6082 T6 aluminium alloys. In particular, in order to predict the average grain size, a properly trained neural network is linked to the finite element method (FEM) model of the process. The utilized net, which takes as inputs the local values of strain, strain rate, and temperature, was trained starting from experimental data and numerical results. The obtained results show the capability of the artificial intelligence (AI) technique in conjunction with the FE tool to predict the final microstructure in the joint section.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2007-05-01 | Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture |