RFCS cofunded research

Aim of this project is to improve flexibility of production scheduling in flat steel production by generation of optimized production plans for each individual coil at each production step considering real-time plant information. This concept enables immediate reactions to critical situations like insufficient plant performances or off-spec coils. The optimal routings
will be estimated using real-time capable plant performance models derived from machine learning on large historical data, which will be incorporated in multi-objective, stochastic optimization methods.
The applicability of the system will be demonstrated at tin-plate production providing multiple production steps with free choice of multiple plants.