About this Abstract |
Meeting |
MS&T23: Materials Science & Technology
|
Symposium
|
Materials Processing and Fundamental Understanding Based on Machine Learning and Data Informatics
|
Presentation Title |
Online Mechanical Properties Control for Steel Coils Using Machine Learning Model |
Author(s) |
Junho Park, Joo Hyun Ryu, Kyung Rae Jo, Tae Kyo Han |
On-Site Speaker (Planned) |
Junho Park |
Abstract Scope |
The applications of data-driven machine learning(ML) in metallurgy fields have been reported in recent years. In particular, steel manufacturing processes involving machine learning in continuous annealing/galvanizing lines are needed to digitalize steel plants. Here we report a strategy and examples for prediction and controlling the mechanical properties such as yield strength, ultimate tensile strength and elongation of steel coils for automotive parts. In this research, the model is trained by more than 40 valuables including chemical compositions, dimensions of coils and annealing process parameters. This model is proposed to predict the mechanical properties over the whole length of coils and deduce the annealing condition after cold milling by metaheuristics algorithm. |