Sammendrag
In a previous industry innovation project, it has been demonstrated that a digital replica of the physical casting process can be established with high throughput micro-macro scale computation, SQL database and an artificial neural network (ANN). The digital replica is able to efficiently predict sump depth and hot-tearing tendency in the center of billets for a range of industrial AA6xxx alloy composition, casting parameters including casting speed and casting temperature. In this work, we assess the possibility of integrating the established digital twin with virtual commissioning of Aluminum billet DC-casting equipment. The high performance computing facility, Idun, offered by Norwegian University of Technology, is used to enable the massive simulations to cover the whole potential processing parameter window. SQL database is used to provide the meta descriptions of the simulation results, and artificial intelligence is used to parameterize and analyze the simulation results. It is expected that this work will improve the reliability of virtual commissioning.