Adaptive digital twins of combustion systems using sparse sensing strategies

Procacci, Alberto; Amaduzzi, Ruggero; Coussement, Axel; Parente, Alessandro

doi:10.1016/j.proci.2022.07.029

Cited by 10 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 56 The application of non-intrusive projection-based ROMs has been, on the other hand, quite successful in combination with non-linear regression approaches such as Gaussian process regression (GPR), 57 neural networks, and polynomial chaos expansion (PCE). 58 Three-dimensional CFD simulations were combined with sensor data to develop the DT 59 , 60 of a semi-industrial furnace operating with methane-hydrogen mixtures and full hydrogen charges. The DT could predict scalar fields and, integral and point quantities with very high accuracy.…”

Section: Dts Of Industrial Combustion Systems: Where Do We Stand?mentioning

confidence: 99%

“…Today, the challenge is developing strategies to assimilate data of different natures and fidelity into a reduced representation of the system of interest. Approaches based on the combination of dimensionality reduction (using linear techniques such as PCA) and non-linear regression have been successful 59 , 60 in developing simulation-based DTs able to mimic the behavior of complex three-dimensional CFD numerical simulations ( Figure 3 ). To further reduce prediction errors in the design space, non-linear dimensionality reduction (e.g., autoencoders-like) appear particularly well suited.…”

Section: Dts Of Industrial Combustion Systems: What Do We Need To Mov...mentioning

confidence: 99%

See 1 more Smart Citation

Data-driven models and digital twins for sustainable combustion technologies

Parente,

Swaminathan

2024

iScience

Self Cite

View full text Add to dashboard Cite

Section: Dts Of Industrial Combustion Systems: Where Do We Stand?mentioning

confidence: 99%

Section: Dts Of Industrial Combustion Systems: What Do We Need To Mov...mentioning

confidence: 99%

Data-driven models and digital twins for sustainable combustion technologies

Parente,

Swaminathan

2024

iScience

Self Cite

View full text Add to dashboard Cite

“…Recently, the GPR and POD approach has been employed to develop a numerical DT of a semi-industrial furnace [7], while the POD coupled with sparse sensing was used to develop a hybrid numerical-experimental DT of the same furnace [8].…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2023

Self Cite

View full text Add to dashboard Cite

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 H2/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 6×8 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, O2) 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.

show abstract

“…Recently, the SpS framework has been employed to build an hybrid experimentalnumerical Digital Twin of a MILD combustion furnace by coupling the POD modes recovered from the numerical simulations with few experimental measurements (Procacci et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Parameter Estimation Using a Gaussian Process Regression-Based Reduced-Order Model and Sparse Sensing: Application to a Methane/Air Lifted Jet Flame

Procacci

Donato

Amaduzzi

et al. 2023

Flow Turbulence Combust

Self Cite

View full text Add to dashboard Cite

The goal of this work is to perform parameter estimation by comparing a Reduced Order Model (ROM), built using Proper Orthogonal Decomposition (POD) and Gaussian Process Regression (GPR), with a Sparse Sensing (SpS) model. This framework is demonstrated by selecting the optimal set of the Partially Stirred Reactor (PaSR) coefficients used in the modelling of the Cabra flame. The Cabra flame is a methane flame in a vitiated coflow, consisting of the combustion products of hydrogen and air. The PaSR model necessitates the knowledge of 4 scalar coefficients, which are unknown a priori. To select the optimal set of coefficients, 57 simulations were performed with a different combination of PaSR coefficients. These simulations were used to build the ROM via POD and GPR. To compare the numerical solution with the experimental data, the SpS technique has been employed. SpS is a framework that leverages dimensionality reduction to predict the state of the system given few measurements. The optimal coefficients have been estimated by applying an optimization algorithm to the ROM, using the solution provided by SpS as target. Finally, the data assimilation framework has been used to provide a solution with lower uncertainty bounds. The results show that this framework is able to estimate the optimal set of coefficients, and it can be used to identify residual sources of uncertainty in the numerical model by highlighting the difference between the optimized model and the experimental values.

show abstract

Adaptive digital twins of combustion systems using sparse sensing strategies

Cited by 10 publications

References 19 publications

Data-driven models and digital twins for sustainable combustion technologies

Data-driven models and digital twins for sustainable combustion technologies

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

Parameter Estimation Using a Gaussian Process Regression-Based Reduced-Order Model and Sparse Sensing: Application to a Methane/Air Lifted Jet Flame

Contact Info

Product

Resources

About