Autoencoder Neural Network for chemically reacting systems

Journal Article · 31 December 2021 · Journal of Machine Learning for Modeling and Computing

DOI: https://doi.org/10.1615/jmachlearnmodelcomput.2022045133 · OSTI ID:1905427

Zhang, Pei  ^[1]; Sankaran, Ramanan  ^[1]

---

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

Incorporating detailed chemical kinetic models is critical for accurate simulations of reacting flows. However, detailed models involve a large number of thermochemical (TC) state variables. Solving the governing equations to evolve these TC variables becomes impractical for real-world applications. In this work, we propose an autoencoder (AE) neural network (NN)-based reduced model to accelerate such simulations. The AE NN is first trained to find a low-dimensional latent representation of the TC states. Then, the evolving state of a chemical system can be tracked by solving the equations of the latent variables instead of the original TC equations. We demonstrate the reduced model in a syngas CO/H₂ combustion system, using training data collected from canonical perfectly stirred reactors (PSRs). It is found that the AE model can reduce the dimension of the combustion system from 12 to 2 while maintaining low reconstruction error and excellent elemental mass conservation for the test dataset. In the a posteriori test, the combustion states obtained from solving the two latent equations are compared to those from solving the 12 equations of the full model. The AE reduced method is found to be able to capture the diverse combustion states on the top two branches of the S-curve well including the extinction turning point, but with higher prediction errors for states near the ignition turning point.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE Office of Science (SC)
• Grant/Contract Number: AC05-00OR22725
• OSTI ID: 1905427
• Journal Information: Journal of Machine Learning for Modeling and Computing, Journal Name: Journal of Machine Learning for Modeling and Computing Journal Issue: 4 Vol. 3; ISSN 2689-3967
• Publisher: Begell HouseCopyright Statement
• Country of Publication: United States
• Language: English