Projects per year
Abstract
The intricate nature of detailed kinetic mechanisms for plasmaassisted combustion motivates the development of highfidelity surrogates to simplify their use in extensive numerical simulations. This chapter presents a machinelearning approach based on the coupling of Principal Component Analysis (PCA) with Gaussian Process Regression (GPR) to produce a reliable reducedorder representation of the detailed plasmacombustion physics. The entire statespace is expressed in function of a selected number of principal components using a nonlinear Gaussian regression model. This machinelearning framework allows for a superior dimensionality compression compared to conventional datadriven reduction strategies based solely on principal component analysis. The performance of the present technique is assessed for the simulation of ethyleneair ignition by nanosecond repetitive pulsed discharges.
Original language  English 

Title of host publication  Advances in Uncertainty Quantification and Optimization Under Uncertainty with Aerospace Applications: Proceedings of the 2020 UQOP International Conference 
Subtitle of host publication  Space Technology Proceedings 
Publisher  Springer, Cham 
Pages  379392 
Number of pages  13 
Volume  8 
ISBN (Electronic)  9783030805425 
ISBN (Print)  9783030805418 
Publication status  Published  16 Jul 2021 
Fingerprint
Dive into the research topics of 'A MachineLearning Framework for PlasmaAssisted Combustion Using Principal Component Analysis and Gaussian Process Regression'. Together they form a unique fingerprint.Projects
 1 Finished

SRP60: SRPGroeifinanciering: A system identification framework for multifidelity modelling
De Troyer, T., Runacres, M., Blondeau, J., Bram, S., Bellemans, A. & Contino, F.
1/03/19 → 29/02/24
Project: Fundamental