An out-of-distribution-aware autoencoder model for reduced chemical kinetics

Zhang, Pei; Liu, Siyan; Lu, Dan; Sankaran, Ramanan; Zhang, Guannan

doi:10.3934/dcdss.2021138

An out-of-distribution-aware autoencoder model for reduced chemical kinetics

Journal Article · Thu Apr 01 00:00:00 EDT 2021 · Discrete and Continuous Dynamical Systems - Series S

DOI:https://doi.org/10.3934/dcdss.2021138· OSTI ID:1833943

^[1]; ^[1]; ^[1]; ^[1]; ^[1]

Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

While detailed chemical kinetic models have been successful in representing rates of chemical reactions in continuum scale computational fluid dynamics (CFD) simulations, applying the models in simulations for engineering device conditions is computationally prohibitive. To reduce the cost, data-driven methods, e.g., autoencoders, have been used to construct reduced chemical kinetic models for CFD simulations. Despite their success, data-driven methods rely heavily on training data sets and can be unreliable when used in out-of-distribution (OOD) regions (i.e., when extrapolating outside of the training set). In this paper, we present an enhanced autoencoder model for combustion chemical kinetics with uncertainty quantification to enable the detection of model usage in OOD regions, and thereby creating an OOD-aware autoencoder model that contributes to more robust CFD simulations of reacting flows.Here, we first demonstrate the effectiveness of the method in OOD detection in two well-known datasets, MNIST and Fashion-MNIST, in comparison with the deep ensemble method, and then present the OOD-aware autoencoder for reduced chemistry model in syngas combustion.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1833943

Journal Information:: Discrete and Continuous Dynamical Systems - Series S, Journal Name: Discrete and Continuous Dynamical Systems - Series S Journal Issue: 4 Vol. 15; ISSN 1937-1632

Publisher:: American Institute of Mathematical Sciences (AIMS)Copyright Statement

Country of Publication:: United States

Language:: English

References (20)

Principal component analysis of kinetic models: PRINCIPAL COMPONENT ANALYSIS OF KINETIC MODELS Vajda, S.; Valko, P.; Turányi, T. International Journal of Chemical Kinetics, Vol. 17, Issue 1 https://doi.org/10.1002/kin.550170107	journal	January 1985
Skeletal reaction models based on principal component analysis: Application to ethylene–air ignition, propagation, and extinction phenomena Esposito, G.; Chelliah, H. K. Combustion and Flame, Vol. 158, Issue 3 https://doi.org/10.1016/j.combustflame.2010.09.010	journal	March 2011
Ignition and extinction in perfectly stirred reactors with detailed chemistry Shan, Ruiqin; Lu, Tianfeng Combustion and Flame, Vol. 159, Issue 6 https://doi.org/10.1016/j.combustflame.2012.01.023	journal	June 2012
Nonlinear reduction of combustion composition space with kernel principal component analysis Mirgolbabaei, Hessam; Echekki, Tarek Combustion and Flame, Vol. 161, Issue 1 https://doi.org/10.1016/j.combustflame.2013.08.016	journal	January 2014
Reduced-order PCA models for chemical reacting flows Isaac, Benjamin J.; Coussement, Axel; Gicquel, Olivier Combustion and Flame, Vol. 161, Issue 11 https://doi.org/10.1016/j.combustflame.2014.05.011	journal	November 2014
The reconstruction of thermo-chemical scalars in combustion from a reduced set of their principal components Mirgolbabaei, Hessam; Echekki, Tarek Combustion and Flame, Vol. 162, Issue 5 https://doi.org/10.1016/j.combustflame.2014.11.027	journal	May 2015
Advanced regression methods for combustion modelling using principal components Isaac, Benjamin J.; Thornock, Jeremy N.; Sutherland, James Combustion and Flame, Vol. 162, Issue 6 https://doi.org/10.1016/j.combustflame.2015.03.008	journal	June 2015
Principal component analysis coupled with nonlinear regression for chemistry reduction Malik, Mohammad Rafi; Isaac, Benjamin J.; Coussement, Axel Combustion and Flame, Vol. 187 https://doi.org/10.1016/j.combustflame.2017.08.012	journal	January 2018
A nonlinear principal component analysis approach for turbulent combustion composition space Mirgolbabaei, Hessam; Echekki, Tarek; Smaoui, Nejib International Journal of Hydrogen Energy, Vol. 39, Issue 9 https://doi.org/10.1016/j.ijhydene.2013.12.195	journal	March 2014
Toward accommodating realistic fuel chemistry in large-scale computations Lu, Tianfeng; Law, Chung K. Progress in Energy and Combustion Science, Vol. 35, Issue 2 https://doi.org/10.1016/j.pecs.2008.10.002	journal	April 2009
Scalar mixing in direct numerical simulations of temporally evolving plane jet flames with skeletal CO/H2 kinetics Hawkes, Evatt R.; Sankaran, Ramanan; Sutherland, James C. Proceedings of the Combustion Institute, Vol. 31, Issue 1 https://doi.org/10.1016/j.proci.2006.08.079	journal	January 2007
Combustion modeling using principal component analysis Sutherland, James C.; Parente, Alessandro Proceedings of the Combustion Institute, Vol. 32, Issue 1 https://doi.org/10.1016/j.proci.2008.06.147	journal	January 2009
Identification of low-dimensional manifolds in turbulent flames Parente, A.; Sutherland, J. C.; Tognotti, L. Proceedings of the Combustion Institute, Vol. 32, Issue 1 https://doi.org/10.1016/j.proci.2008.06.177	journal	January 2009
MG-local-PCA method for reduced order combustion modeling Coussement, Axel; Gicquel, Olivier; Parente, Alessandro Proceedings of the Combustion Institute, Vol. 34, Issue 1 https://doi.org/10.1016/j.proci.2012.05.073	journal	January 2013
The oxidation of 2-butene: A high pressure ignition delay, kinetic modeling study and reactivity comparison with isobutene and 1-butene Li, Yang; Zhou, Chong-Wen; Somers, Kieran P. Proceedings of the Combustion Institute, Vol. 36, Issue 1 https://doi.org/10.1016/j.proci.2016.05.052	journal	January 2017
Terascale direct numerical simulations of turbulent combustion using S3D Chen, J. H.; Choudhary, A.; de Supinski, B. Computational Science & Discovery, Vol. 2, Issue 1 https://doi.org/10.1088/1749-4699/2/1/015001	journal	January 2009
A Practical Bayesian Framework for Backpropagation Networks MacKay, David J. C. Neural Computation, Vol. 4, Issue 3 https://doi.org/10.1162/neco.1992.4.3.448	journal	May 1992
A Novel Principal Component Analysis-Based Acceleration Scheme for LES-ODT: An A Priori Study Mirgolbabaei, Hessam; Echekki, Tarek 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition https://doi.org/10.2514/6.2013-168	conference	January 2013
Reduced Models for Chemical Kinetics derived from Parallel Ensemble Simulations of Stirred Reactors Zhang, Pei; Sankaran, Ramanan; Stoyanov, Miroslav AIAA Scitech 2020 Forum https://doi.org/10.2514/6.2020-0177	conference	January 2020
A priori examination of reduced chemistry models derived from canonical stirred reactors using three-dimensional direct numerical simulation datasets Zhang, Pei; Sankaran, Ramanan; Hawkes, Evatt R. AIAA Scitech 2021 Forum https://doi.org/10.2514/6.2021-1784	conference	January 2021

Similar Records

Autoencoder Neural Network for chemically reacting systems

Journal Article · Fri Dec 31 19:00:00 EST 2021 · Journal of Machine Learning for Modeling and Computing · OSTI ID:1905427

Reduced Models for Chemical Kinetics derived from Parallel Ensemble Simulations of Stirred Reactors

Conference · Tue Dec 31 23:00:00 EST 2019 · OSTI ID:1606718

Out of Distribution Detection with Neural Network Anchoring

Software · Wed Jul 20 20:00:00 EDT 2022 · OSTI ID:code-80817

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
chemical kinetics
dimension reduction
neural network
out of distribution
uncertainty quantification

An out-of-distribution-aware autoencoder model for reduced chemical kinetics

Citation Formats

References (20)

Similar Records

Related Subjects