Digital Twin for Experimental Data Fusion Applied to a Semi-Industrial Furnace Fed with H2-Rich Fuel Mixtures

The objective of this work is to build a Digital Twin of a semi-industrial furnace using Gaussian Process Regression coupled with dimensionality reduction via Proper Orthogonal Decomposition. The Digital Twin is capable of integrating different sources of information, such as temperature, chemiluminescence intensity and species concentration at the outlet. The parameters selected to build the design space are the equivalence ratio and the benzene concentration in the fuel stream. The fuel consists of a H-2/CH4/CO blend, doped with a progressive addition of C6H6. It is an H2-rich fuel mixture, representing a surrogate of a more complex Coke Oven Gas industrial mixture. The experimental measurements include the flame temperature distribution, measured on a 6x8 grid using an air-cooled suction pyrometer, spatially resolved chemiluminescence measurements of OH* and CH*, and the species concentration (i.e., NO, NO2, CO, H2O, CO2, O-2) measured in the exhaust gases. The GPR-based Digital Twin approach has already been successfully applied on numerical datasets coming from CFD simulations. In this work, we demonstrate that the same approach can be applied on heterogeneous datasets, obtained from experimental measurements.

Automated summary

The objective of this work is to build a Digital Twin of a semi-industrial furnace using Gaussian Process Regression coupled with dimensionality reduction. The Digital Twin integrates temperature, chemiluminescence intensity, and species concentration at the outlet. Experimental measurements include flame temperature distribution, chemiluminescence measurements of OH* and CH*, and species concentration in the exhaust gases. The GPR-based Digital Twin approach is successfully applied on numerical datasets and demonstrated to work on heterogeneous datasets from experimental measurements.