Mikhail Petrovich Tokarev

Dr. Mikhail Petrovich Tokarev


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 November 2020 in Energies
Verified
Journal Article
Open access
PDF file
MTMikhail Petrovich Tokarev
Mikhail Petrovich Tokarev
EPEgor Palkin
Egor Palkin
Rustam MullyadzhanovRustam Mullyadzhanov
Rustam Mullyadzhanov
We apply deep reinforcement learning to active closed-loop control of a two-dimensional flow over a cylinder oscillating around its axis with a time-dependent angular velocity representing the only control parameter. Experimenting with the angular velocity, the neural network is able to devise a control strategy based on low frequency harmonic oscillations with some additional modulations to stabilize the Kármán vortex street at a low Reynolds number Re=100. We examine the convergence issue for two reward functions showing that later epoch number does not always guarantee a better result. The performance of the controller provide the drag reduction of 14% or 16% depending on the employed reward function. The additional efforts are very low as the maximum amplitude of the angular velocity is equal to 8% of the incoming flow in the first case while the latter reward function returns an impressive 0.8% rotation amplitude which is comparable with the state-of-the-art adjoint optimization results. A detailed comparison with a flow controlled by harmonic oscillations with fixed amplitude and frequency is presented, highlighting the benefits of a feedback loop.

1 November 2019 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
PCP A Chertovskikh
P A Chertovskikh
ASA V Seredkin
A V Seredkin
OGO A Gobyzov
O A Gobyzov
ASA S Styuf
A S Styuf
MPM G Pashkevich
M G Pashkevich
MTMikhail Petrovich Tokarev
Mikhail Petrovich Tokarev
This paper describes an intelligent adaptive PID controller design procedure. The controller consists of a discrete time PID and an auto-tuning neural network unit. First system identification with a nonlinear autoregressive model (NARX) was performed. This model was then used to train the neural PID tuner. A special MATLAB toolbox “SmatPID Toolbox” was developed to automate the process of controller synthesis. The resulting controller was tested in a laboratory coal-gas furnace control system to track specified air flow rates.

1 February 2024 in Physics of Fluids
Verified
Journal Article
Open access
PDF file
HLH. Li
H. Li
SYSergey N. Yakovenko
Sergey N. Yakovenko
VIV. Ivashchenko
V. Ivashchenko
ALA. Lukyanov
A. Lukyanov
Rustam MullyadzhanovRustam Mullyadzhanov
Rustam Mullyadzhanov
MTMikhail Petrovich Tokarev
Mikhail Petrovich Tokarev
This study presents a comparison of the performance of machine learning (ML) techniques, specifically multi-dimensional gene expression programming (MGEP), tensor basis neural network (TBNN), and also proposes a novel universally interpretable machine learning architecture to model the turbulent scalar flux (UIML-s) to enhance turbulence models for fluid flows at different Prandtl numbers in channels with complex shapes of walls in the channel cross section. In particular, peripheral subchannels of rod bundles are of primary interest. However, the accuracy of mean velocity and scalar distributions predicted by commonly used turbulence models still poses a challenge compared to data extracted from high-fidelity eddy-resolving numerical simulations, particularly for engineering applications involving complex geometry flows. In the present study, by utilizing an explicit algebraic expression for the nonlinear Reynolds-stress term obtained through both the evolutionary MGEP optimization and TBNN, the secondary flow structure has been adequately predicted in the cross-wise mean velocity distributions in the square duct and the rectangular channel with three longitudinal rods. This structure is also observed in the data from the concurrent runs performed by direct numerical simulation (DNS) but is completely absent in the results produced by a baseline Reynolds-averaged Navier–Stokes (RANS) closure, which employs the linear eddy viscosity model for the Reynolds stress tensor. Comparison of MGEP and TBNN has shown their nearly equal performance in a square duct flow; however, MGEP works better for the more complex geometry channel with three rods. Furthermore, based on the velocity field produced by the RANS-MGEP model, the ML modification of the gradient diffusion hypothesis, integrated into the aforementioned novel RANS-ML model called as UIML-s, significantly improves the mean scalar distributions in a flow with three bumps serving as a prototype for the peripheral subchannel of rod bundle. The normalized root mean squared error decreases from 13.5% to 7.6%, bringing the predicted distributions closer to the DNS data, particularly in the near-wall region. Another approach, MGEP-s, also yields the acceptable results, which are nearly identical to those from UIML-s. These findings highlight the potential of using data-driven calibration of turbulence models with nonlinear closures to enhance the predictability for RANS simulations of fluid flows, heat, and mass transfer in channels with complex geometry.

1 November 2018 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
MTMikhail Petrovich Tokarev
Mikhail Petrovich Tokarev
SAS S Abdurakipov
S S Abdurakipov
OGO A Gobyzov
O A Gobyzov
ASA V Seredkin
A V Seredkin
VDVladimir Dulin
Vladimir Dulin

1 September 2014 in Optoelectronics, Instrumentation and Data Processing
Verified
Journal Article
Closed access
PDF file
MAM. V. Alekseenko
M. V. Alekseenko
ABA. V. Bilsky
A. V. Bilsky
VDVladimir Dulin
Vladimir Dulin
LKL. A. Kozinkin
L. A. Kozinkin
DMD. M. Markovich
D. M. Markovich
MTMikhail Petrovich Tokarev
Mikhail Petrovich Tokarev
A modern method of velocity measurement in a flow volume on the basis of few-projections optical tomography and correlation of moving particles is considered. The method is used to measure instantaneous three-dimensional velocity distributions in non-swirling and swirling turbulent jet flows. In addition to measurement of three-dimensional velocity distributions, specific features of this experiment are a larger depth of the measurement region (up to 40 mm) and a higher resolution of cameras (up to 4 MP as compared to previous authors’ tomographic measurements). To verify the correctness of tomographic measurements, the velocity in the plane passing along the jet axis is measured by the Stereo PIV method. The difference between the stereoscopic and tomographic measurements of three components of the mean velocity for the flows considered in this study is smaller than 10%. A three-dimensional vortex structure of the core of a swirling jet is visualized with a spatial resolution of 3 mm.

1 January 2018 in AIP Conference Proceedings
Verified
Conference Paper
Closed access
OGOleg Gobyzov
Oleg Gobyzov
MTMikhail Petrovich Tokarev
Mikhail Petrovich Tokarev
SAS. S. Abdurakipov
S. S. Abdurakipov
ALAleksei S Lobasov
Aleksei S Lobasov