A framework with a data-driven model based approach to compute and analyze the operability sets is presented. The computationally expensive steady-state simulations are replaced by machine learning models developed through statistical analysis of selected rigorous simulations. The entire solution manifold is computed using a high-dimensional continuation algorithm. The framework is applied to a plant-wide system. The steps of the framework are discussed in depth within the context of the plant-wide system. The operability sets computed by high-dimensional continuation are analyzed in detail. Operability sets of lower dimensional subsystems are computed to gain better insights. Input behavior at cost optimal conditions and the multiplicities in the subsystems are also explored.

Deeper understanding of each process step involved in the manufacturing of steel products will be of immense value to process engineers. In this work, the authors explore the flexibilities in a key process step called ladle refining using the operability framework of Vinson and Georgakis (doi:/10.1016/S0959‐1524(99)00045‐1). The methodology systematically uncovers the process behavior using its mathematical model. The RSM model presented by Shukla et al. (doi:10.1002/srin.201500392) for ladle refining is utilized here. Typically, operating windows for a given process requirement are determined after conducting several plant trials or experiments. These can be time consuming and expensive. The quantitative approach presented in this work can help the operator to identify best possible regions to work with. For example, the authors are able to answer questions such as, in what part of input space should the process be operated to achieve inclusion removal efficiency better than 70% with melt exit temperature in the range of 1825–1850 K? Identifying operating points with certain desired conditions such as maximum inclusion removal efficiency becomes a straightforward search among the computed points. The methodology can be extended to include other unit operations in the process chain.