For decades, traditional scale-modeling techniques have been relying on first-principles models (FPMs). FPMs have been used to find non-dimensional numbers (PIs) and identify normalized underlying forces and energies behind the phenomenon in focus. The two main challenges with FPM-based PIs extraction are finding the relevant PIs and proper correlations between PIs. The emergence and surge of data-driven modeling (DDM) provide a new opportunity to leverage experimental data in model development across scales/plants. In this paper, first, the two mentioned issues in PIs development will be elaborated to reveal the gap, and second, a new insight into scale modeling and similarity concepts will be presented. Then, to showcase the presented framework for a two-fluid spray nozzle case study, DDM techniques will be synergized with FPMs to obtain a robust relationship between relevant properties of the model spray and atomization parameters.

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.