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
1Kutateladze Institute of Thermophysics, Siberian Branch, Russian Academy of Sciences, 630090, Novosibirsk, prosp. Akademika Lavrent’eva, 1
2Novosibirsk State University, 630090, Novosibirsk, Pirogova 2
Keywords: классификация изображений, мониторинг, машинное обучение, свёрточная нейронная сеть, факел, image classification, monitoring, computer training, convolutional neural network, flame
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.
|
