Wan, K. ; Hartl, S. ; Vervisch, L. ; Domingo, P. ; Barlow, R. S. ; Hasse, C. (2020)
Combustion regime identification from machine learning trained by Raman/Rayleigh line measurements.
In: Combustion and Flame, 219
doi: 10.1016/j.combustflame.2020.05.024
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
A combustion regime identification based on convolutional neural networks (CNNs) is developed using the recently proposed gradient-free regime identification (GFRI) approach applied to two turbulent CH4/air jet flames featuring multi-regime characteristics. The training and the subsequent application of the CNN rely on the processing of one-dimensional Raman/Rayleigh line measurements of species mass fractions and temperature (CNN input). The combustion regime index is then readily predicted at every point along the measured line (CNN output). For training the neural network, the combustion regime index is first determined using the GFRI method (Hartl et al., 2018) based on the chemical explosive mode analysis (CEMA). Six classes of combustion regimes, including premixed (P), dominantly premixed (DP), multi-regime (MR), dominantly non-premixed (DNP), non-premixed (NP), and lean back-supported (LBS), are well detected by the trained CNN, with a pixel-wise accuracy of more than 85 for burner operating conditions unseen during training (different free-stream equivalence ratios). The quasi instantaneous neural network response provides a perspective towards real-time global combustion regime identification for pollutants emission control. From the results, it is also concluded that introducing physical insight, by combining advanced experimental (Raman/Rayleigh line measurements) and numerical analysis (GFRI), allows for reducing the amount of data needed to train neural networks.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2020 |
| Autor(en): | Wan, K. ; Hartl, S. ; Vervisch, L. ; Domingo, P. ; Barlow, R. S. ; Hasse, C. |
| Art des Eintrags: | Bibliographie |
| Titel: | Combustion regime identification from machine learning trained by Raman/Rayleigh line measurements |
| Sprache: | Englisch |
| Publikationsjahr: | September 2020 |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Combustion and Flame |
| Jahrgang/Volume einer Zeitschrift: | 219 |
| DOI: | 10.1016/j.combustflame.2020.05.024 |
| URL / URN: | https://doi.org/10.1016/j.combustflame.2020.05.024 |
| Kurzbeschreibung (Abstract): | A combustion regime identification based on convolutional neural networks (CNNs) is developed using the recently proposed gradient-free regime identification (GFRI) approach applied to two turbulent CH4/air jet flames featuring multi-regime characteristics. The training and the subsequent application of the CNN rely on the processing of one-dimensional Raman/Rayleigh line measurements of species mass fractions and temperature (CNN input). The combustion regime index is then readily predicted at every point along the measured line (CNN output). For training the neural network, the combustion regime index is first determined using the GFRI method (Hartl et al., 2018) based on the chemical explosive mode analysis (CEMA). Six classes of combustion regimes, including premixed (P), dominantly premixed (DP), multi-regime (MR), dominantly non-premixed (DNP), non-premixed (NP), and lean back-supported (LBS), are well detected by the trained CNN, with a pixel-wise accuracy of more than 85 for burner operating conditions unseen during training (different free-stream equivalence ratios). The quasi instantaneous neural network response provides a perspective towards real-time global combustion regime identification for pollutants emission control. From the results, it is also concluded that introducing physical insight, by combining advanced experimental (Raman/Rayleigh line measurements) and numerical analysis (GFRI), allows for reducing the amount of data needed to train neural networks. |
| Freie Schlagworte: | Convolutional neural network, Combustion regime, Raman/Rayleigh, Flame regime marker, Gradient-free regime identification |
| Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Fachgebiet Simulation reaktiver Thermo-Fluid Systeme (STFS) Profilbereiche Profilbereiche > Thermo-Fluids & Interfaces |
| Hinterlegungsdatum: | 22 Jun 2020 05:43 |
| Letzte Änderung: | 22 Sep 2020 06:02 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum