Monitoring of combustion regimes based on the visualization of the flame and machine learning

Standard

Monitoring of combustion regimes based on the visualization of the flame and machine learning. / Tokarev, M. P.; Abdurakipov, S. S.; Gobyzov, O. A. и др.

в: Journal of Physics: Conference Series, Том 1128, № 1, 012138, 07.12.2018.

Результаты исследований: Научные публикации в периодических изданиях › статья по материалам конференции › Рецензирование

Harvard

Tokarev, MP, Abdurakipov, SS, Gobyzov, OA, Seredkin, AV & Dulin, VM 2018, 'Monitoring of combustion regimes based on the visualization of the flame and machine learning', Journal of Physics: Conference Series, Том. 1128, № 1, 012138. https://doi.org/10.1088/1742-6596/1128/1/012138

APA

Tokarev, M. P., Abdurakipov, S. S., Gobyzov, O. A., Seredkin, A. V., & Dulin, V. M. (2018). Monitoring of combustion regimes based on the visualization of the flame and machine learning. Journal of Physics: Conference Series, 1128(1), [012138]. https://doi.org/10.1088/1742-6596/1128/1/012138

Vancouver

Tokarev MP, Abdurakipov SS, Gobyzov OA, Seredkin AV, Dulin VM. Monitoring of combustion regimes based on the visualization of the flame and machine learning. Journal of Physics: Conference Series. 2018 дек. 7;1128(1):012138. doi: 10.1088/1742-6596/1128/1/012138

Author

Tokarev, M. P. ; Abdurakipov, S. S. ; Gobyzov, O. A. и др. / Monitoring of combustion regimes based on the visualization of the flame and machine learning. в: Journal of Physics: Conference Series. 2018 ; Том 1128, № 1.

BibTeX

@article{fac9f20caee54670b7c7f51112e69164,

title = "Monitoring of combustion regimes based on the visualization of the flame and machine learning",

abstract = "Development of modern intelligent monitoring and control systems in energy, allowing reducing the level of harmful emissions and energy intensity production is relevant. In the scientific literature usage of new efficient machine learning techniques for automatic extraction of features for the classification of combustion regimes is insufficiently covered. In this paper we describe a method for determining combustion regimes based on images of flames. To determine the combustion regimes, a convolutional neural network is trained using labeled data. It is shown that in the gas flame colour images the accuracy of the classification of regimes is up to 98%. Results of the convolutional neural network are compared to classification results of various linear models.",

author = "Tokarev, {M. P.} and Abdurakipov, {S. S.} and Gobyzov, {O. A.} and Seredkin, {A. V.} and Dulin, {V. M.}",

note = "Publisher Copyright: {\textcopyright} 2018 Institute of Physics Publishing. All rights reserved.; 3rd All-Russian Scientific Conference Thermophysics and Physical Hydrodynamics with the School for Young Scientists, TPH 2018 ; Conference date: 10-09-2018 Through 16-09-2018",

year = "2018",

month = dec,

day = "7",

doi = "10.1088/1742-6596/1128/1/012138",

language = "English",

volume = "1128",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing Ltd.",

number = "1",

}

RIS

TY - JOUR

T1 - Monitoring of combustion regimes based on the visualization of the flame and machine learning

AU - Tokarev, M. P.

AU - Abdurakipov, S. S.

AU - Gobyzov, O. A.

AU - Seredkin, A. V.

AU - Dulin, V. M.

PY - 2018/12/7

Y1 - 2018/12/7

N2 - Development of modern intelligent monitoring and control systems in energy, allowing reducing the level of harmful emissions and energy intensity production is relevant. In the scientific literature usage of new efficient machine learning techniques for automatic extraction of features for the classification of combustion regimes is insufficiently covered. In this paper we describe a method for determining combustion regimes based on images of flames. To determine the combustion regimes, a convolutional neural network is trained using labeled data. It is shown that in the gas flame colour images the accuracy of the classification of regimes is up to 98%. Results of the convolutional neural network are compared to classification results of various linear models.

AB - Development of modern intelligent monitoring and control systems in energy, allowing reducing the level of harmful emissions and energy intensity production is relevant. In the scientific literature usage of new efficient machine learning techniques for automatic extraction of features for the classification of combustion regimes is insufficiently covered. In this paper we describe a method for determining combustion regimes based on images of flames. To determine the combustion regimes, a convolutional neural network is trained using labeled data. It is shown that in the gas flame colour images the accuracy of the classification of regimes is up to 98%. Results of the convolutional neural network are compared to classification results of various linear models.

UR - http://www.scopus.com/inward/record.url?scp=85058645173&partnerID=8YFLogxK

U2 - 10.1088/1742-6596/1128/1/012138

DO - 10.1088/1742-6596/1128/1/012138

M3 - Conference article

AN - SCOPUS:85058645173

VL - 1128

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

IS - 1

M1 - 012138

T2 - 3rd All-Russian Scientific Conference Thermophysics and Physical Hydrodynamics with the School for Young Scientists, TPH 2018

Y2 - 10 September 2018 through 16 September 2018

ER -

ID: 17894894