Standard

Modeling of the Tonal Noise Characteristics in a Foil Flow by using Machine Learning. / Abdurakipov, S. S.; Tokarev, M. P.; Pervunin, K. S. et al.

In: Optoelectronics, Instrumentation and Data Processing, Vol. 55, No. 2, 01.03.2019, p. 205-211.

Research output: Contribution to journal › Article › peer-review

Harvard

Abdurakipov, SS, Tokarev, MP, Pervunin, KS & Dulin, VM 2019, 'Modeling of the Tonal Noise Characteristics in a Foil Flow by using Machine Learning', Optoelectronics, Instrumentation and Data Processing, vol. 55, no. 2, pp. 205-211. https://doi.org/10.3103/S8756699019020134

APA

Abdurakipov, S. S., Tokarev, M. P., Pervunin, K. S., & Dulin, V. M. (2019). Modeling of the Tonal Noise Characteristics in a Foil Flow by using Machine Learning. Optoelectronics, Instrumentation and Data Processing, 55(2), 205-211. https://doi.org/10.3103/S8756699019020134

Vancouver

Abdurakipov SS, Tokarev MP, Pervunin KS, Dulin VM. Modeling of the Tonal Noise Characteristics in a Foil Flow by using Machine Learning. Optoelectronics, Instrumentation and Data Processing. 2019 Mar 1;55(2):205-211. doi: 10.3103/S8756699019020134

Author

Abdurakipov, S. S. ; Tokarev, M. P. ; Pervunin, K. S. et al. / Modeling of the Tonal Noise Characteristics in a Foil Flow by using Machine Learning. In: Optoelectronics, Instrumentation and Data Processing. 2019 ; Vol. 55, No. 2. pp. 205-211.

BibTeX

@article{fc6d9cd52a3745dd82e253ee13bab237,
title = "Modeling of the Tonal Noise Characteristics in a Foil Flow by using Machine Learning",
abstract = "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 of regimes of high-level tonal noise coming from the dimensionless parameters of the flow. Different families of algorithms are considered: from linear models to artificial neural networks. It is shown that a gradient boosting model with a determination coefficient 95% is the most accurate for describing and predicting the spectral curves of acoustic pressure on the entire interval of values of amplitudes and characteristic frequencies.",
keywords = "foil flow, machine learning, tonal noise",
author = "Abdurakipov, {S. S.} and Tokarev, {M. P.} and Pervunin, {K. S.} and Dulin, {V. M.}",
note = "Publisher Copyright: {\textcopyright} 2019, Allerton Press, Inc.",
year = "2019",
month = mar,
day = "1",
doi = "10.3103/S8756699019020134",
language = "English",
volume = "55",
pages = "205--211",
journal = "Optoelectronics, Instrumentation and Data Processing",
issn = "8756-6990",
publisher = "Allerton Press Inc.",
number = "2",

}

RIS

TY - JOUR

T1 - Modeling of the Tonal Noise Characteristics in a Foil Flow by using Machine Learning

AU - Abdurakipov, S. S.

AU - Tokarev, M. P.

AU - Pervunin, K. S.

AU - Dulin, V. M.

N1 - Publisher Copyright: © 2019, Allerton Press, Inc.

PY - 2019/3/1

Y1 - 2019/3/1

N2 - 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 of regimes of high-level tonal noise coming from the dimensionless parameters of the flow. Different families of algorithms are considered: from linear models to artificial neural networks. It is shown that a gradient boosting model with a determination coefficient 95% is the most accurate for describing and predicting the spectral curves of acoustic pressure on the entire interval of values of amplitudes and characteristic frequencies.

AB - 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 of regimes of high-level tonal noise coming from the dimensionless parameters of the flow. Different families of algorithms are considered: from linear models to artificial neural networks. It is shown that a gradient boosting model with a determination coefficient 95% is the most accurate for describing and predicting the spectral curves of acoustic pressure on the entire interval of values of amplitudes and characteristic frequencies.

KW - foil flow

KW - machine learning

KW - tonal noise

UR - http://www.scopus.com/inward/record.url?scp=85067337372&partnerID=8YFLogxK

U2 - 10.3103/S8756699019020134

DO - 10.3103/S8756699019020134

M3 - Article

AN - SCOPUS:85067337372

VL - 55

SP - 205

EP - 211

JO - Optoelectronics, Instrumentation and Data Processing

JF - Optoelectronics, Instrumentation and Data Processing

SN - 8756-6990

IS - 2

ER -

ID: 20588260