This study proposes a machine learning tabulation (MLT) method that employs deep neural networks (DNNs) to predict ignition delay and knock propensity in spark ignition (SI) engines. The commonly used Arrhenius model and Livengood–Wu integral for fast knock prediction are not accurate enough to account for residual gas species and may require adjustments or modifications to account for specific engine characteristics. Detailed kinetics modeling is computationally expensive, so the MLT approach is introduced to solve these issues. The MLT method uses precalculated thermochemical states of the mixture that are clustered based on a combustion progress variable. Hundreds of DNNs are trained with the stochastic Levenberg–Marquardt (SLM) optimization algorithm, reducing training time and memory requirements for large-scale problems. MLT has high interpolation accuracy, eliminates the need for table storage, and reduces memory requirements by three orders of magnitude. The proposed MLT approach can operate across a wider range of conditions and handle a variety of fuels, including those with complex reaction mechanisms. MLT computational time is independent of the reaction mechanism’s size. It demonstrates a remarkable capability to reduce computation time by a factor of approximately 300 when dealing with complex reaction mechanisms comprising 621 species. MLT has the potential to significantly advance our understanding of complex combustion processes and aid in the design of more efficient and environmentally friendly combustion engines. In summary, the MLT approach has acceptable accuracy with less computation cost than detailed kinetics, making it ideal for fast model-based knock detection. This article presents a detailed description of the MLT method, including its workflow, challenges involved in data generation, pre-processing, data classification and regression, and integration into the engine cycle simulation. The results of the study are summarized, which includes validation against kinetics for ignition delay and engine simulation for knock angle prediction. The conclusions are presented along with future work.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Machine Learning Tabulation Scheme for Fast Chemical Kinetics Computation


    Weitere Titelangaben:

    Sae Int. J. Engines


    Beteiligte:


    Erscheinungsdatum :

    2023-12-28




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    TABULATION DEVICE, TABULATION METHOD, AND TABULATION PROGRAM

    KOMIYA KENJI / ISOMURA ATSUSHI / TAKAGI MASARU | Europäisches Patentamt | 2022

    Freier Zugriff

    TABULATION DEVICE, TABULATION METHOD, AND TABULATION PROGRAM

    NAITO ICHIBE / OKI NOBUHIRO / SHIGEMATSU NAOKO et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    TABULATION DEVICE, TABULATION METHOD, AND TABULATION PROGRAM

    ISOMURA ATSUSHI / NAITO ICHIBE / OKI NOBUHIRO et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    TABULATION DEVICE AND TABULATION SYSTEM FOR MARKER

    OZAWA TADASHI / WATANABE AKIHIKO / NAGATOKU NORIHIRO et al. | Europäisches Patentamt | 2017

    Freier Zugriff

    Ohio's accident tabulation technique

    Eckhardt, H.G. | Engineering Index Backfile | 1952