A deep learning-based ode solver for chemical kinetics

Tianhan Zhang, Yaoyu Zhang, Weinan E, Yiguang Ju

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations


Developing efficient and accurate algorithms for chemistry integration is a challenging task due to its strong stiffness and high dimensionality. The current work presents a deep learning-based numerical method called DeepCombustion0.0 to solve stiff ordinary differential equation systems. The homogeneous autoignition of DME/air mixture, including 54 species, is adopted as an example to illustrate the validity and accuracy of the algorithm. The training and testing datasets cover a wide range of temperature, pressure, and mixture conditions between 750 – 1200 K, 30 – 50 atm, and equivalence ratio = 0.7 – 1.5. Both the firststage low-temperature ignition (LTI) and the second-stage high-temperature ignition (HTI) are considered. The methodology highlights the importance of the adaptive data sampling techniques, power transform preprocessing, and binary deep neural network (DNN) design. By using the adaptive random samplings and appropriate power transforms, smooth submanifolds in the state vector phase space are observed, on which two three-layer DNNs can be appropriately trained. The neural networks are end-to-end, which predict temporal gradients of the state vectors directly. The results show that temporal evolutions predicted by DNN agree well with traditional numerical methods in all state vector dimensions, including temperature, pressure, and species concentrations. Besides, the ignition delay time differences are within 1%. At the same time, the CPU time is reduced by more than 20 times and 200 times compared with the HMTS and VODE method, respectively. The current work demonstrates the enormous potential of applying the deep learning algorithm in chemical kinetics and combustion modeling.

Original languageEnglish (US)
Title of host publicationAIAA Scitech 2021 Forum
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
ISBN (Print)9781624106095
StatePublished - 2021
EventAIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2021 - Virtual, Online
Duration: Jan 11 2021Jan 15 2021

Publication series

NameAIAA Scitech 2021 Forum


ConferenceAIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2021
CityVirtual, Online

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering


Dive into the research topics of 'A deep learning-based ode solver for chemical kinetics'. Together they form a unique fingerprint.

Cite this