On October 20, we organized a scientific seminar on “Developing Grey-box Process Models “. The scientific seminar was led by Cesar de Prada, a professor at University of Valladolid, Spain. The scientific seminar was organized in the framework of the FrontSeat project as part of the seminar series on “Research Seminar on Smart Cybernetics”.
When developing a process model, very often one finds parts that can be modeled with equations derived from physical knowledge, such as mass or energy balances, while there are other not well-known phenomena involving some variables that are more difficult to translate into equations. In this case, one can try to model these unknown parts as black boxes using experimental data and then combine both types of models as a “grey” one. In recent years there has been a growing interest in this type of model that presents two main problems: The first one is how to develop the structure and parameters of the black-box part consistent with the overall behavior of the full model and fits the experimental data. The second one refers to how to maintain a sensible extrapolation capability outside the region where data were available. The talk describes a methodology that aims to solve both problems and presents an original method based on SOS polynomials that facilitate the development of such models. The methodology is illustrated with some practical examples on an industrial scale.
This project has received funding from the European Union’s Horizon under grant no. 101079342 (Fostering Opportunities Towards Slovak Excellence in Advanced Control for Smart Industries).