COMBUSTION REGIME MONITORING BY DETECTING THE FLAME IMAGES AND COMPUTER TRAINING
S. S. Abdurakipov1,2, O. A. Gobyzov1,2, M. P. Tokarev1,2, V. M. Dulin1,2
a:2:{s:4:"TEXT";s:227:"1Kutateladze Institute of Thermophysics, Siberian Branch, Russian Academy of Sciences, 630090, Novosibirsk, prosp. Akademika Lavrent’eva, 1
2Novosibirsk State University, 630090, Novosibirsk, Pirogova 2";s:4:"TYPE";s:4:"html";}
Keywords: классификация изображений, мониторинг, машинное обучение, свёрточная нейронная сеть, факел, image classification, monitoring, computer training, convolutional neural network, flame
Subsection: MODELING IN PHYSICAL AND TECHNICAL RESEARCH
Abstract
A method for automatic determination of combustion regimes using flame images on the basis of the tagged data of a trained convolutional neural network is under consideration. It is shown that the accuracy of regime classification reaches 98 % on the flame images of a gas burner. The results of the operation of the convolutional neural network and classification using different linear models are compared.
|
