Application of real-time models for multi-scale predictions during material processes

Abstract Cyber and virtual representations of material processes have been promoted within the frameworks of digital twinning and shadowing for improved process monitoring and control. Real-time modelling practices based on sound data science techniques can be integrated into these digitalization frameworks to create efficient predictive and corrective analytics. However, modelling material processes involves multi-physical and multi-scale aspects that need to be conveyed for any optimization of product manufacturing. In this research work, a set of data solvers, interpolators, and trainers has been developed to model the macro-micro evolutions during material processes. Data search spaces were defined based on the process parameters. Snapshot matrices were created, and an appropriately sized database was generated to build real-time process models. Since the macro-micro data ranges for material processes can span over 20 orders of magnitude, a partitioned database technique has been employed to create accurate real-time models. The application of these combined data solvers, interpolators, and trainers has been developed for a real-world extrusion case study. The evolutions of macro and micro properties were predicted for material particles along predefined streamlines. These streamlines cover the entire distance from the back of the extrusion billet to the end of the final profile. In this way, the complete evolution of macro-micro material properties during the extrusion processes can be modelled.