Zobrazeno 1 - 10
of 38
pro vyhledávání: '"S. S. Abdurakipov"'
Publikováno v:
Optoelectronics, Instrumentation and Data Processing. 58:98-108
Autor:
S. S. Abdurakipov, E. B. Butakov
Publikováno v:
Optoelectronics, Instrumentation and Data Processing. 56:586-597
The developed classical machine learning models based on linear models and decision trees, the modern algorithms of convolutional neural networks, and the neural network autoencoder are compared in solving the problem of predictive detection of pre-f
Publikováno v:
Combustion, Explosion, and Shock Waves. 55:697-701
An experimental study of the effect of pulverization on the thermal destruction of coal is carried out. Artificial neural networks are used to develop a model that allows predicting the degree of burnout of pulverized coals with high accuracy (an ave
Publikováno v:
Optoelectronics, Instrumentation and Data Processing. 55:205-211
A machine learning approach for prediction the characteristics of tonal noise formed in a foil flow is tested. Experimental data are used to construct and analyze the mathematical models of pressure amplitude regression and models of classification o
Autor:
S. S. Abdurakipov, K. G. Dobroselsky
Publikováno v:
Siberian Journal of Physics. 14:5-14
Using an optical method for measuring the velocity fields Particle Image Velocimetry (PIV) and a statistical method for analyzing coherent structures in turbulent flows Proper Orthogonal Decomposition (POD), an experimental study of the spatial struc
Publikováno v:
Combustion, Explosion, and Shock Waves. 54:642-648
This paper describes an experimental study of the spatial structure of the chemical reaction zone in turbulent swirling flames by planar laser-induced fluorescence of formaldehyde (HCHO). Combustion of the methane–air mixture at atmospheric pressur
Publikováno v:
Optoelectronics, Instrumentation and Data Processing. 54:513-519
A method for automatic determination of combustion regimes using flame images on the basis of a convolutional neural network on labeled data is under consideration. It is shown that the accuracy of regime classification reaches 98% on the flame image
Publikováno v:
Thermophysics and Aeromechanics. 25:379-386
Investigation results on unsteady flow dynamics in a gaseous jet flame with strong swirl, vortex breakdown, and precession of a vortex core obtained by panoramic optical methods are presented, as well as the results of theoretical analysis of the fas
Autor:
M. P. Tokarev, Mikhail Hrebtov, Sergey Alekseenko, Dmitriy M. Markovich, S. S. Abdurakipov, Vladimir M. Dulin
Publikováno v:
International Journal of Heat and Fluid Flow. 70:363-379
The present paper reports on high-speed tomographic particle image velocimetry measurements of large-scale coherent structures in the near field of swirling turbulent jets. Three flow cases are considered: a jet without superimposed swirl; a jet with
Publikováno v:
Siberian Journal of Physics. 13:46-59