Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks

1615 Views
1518 Downloads
Export citation: ABNT
MILČIĆ, Dragan ;ALSAMMARRAIE, Amir ;MADIĆ, Miloš ;KRSTIĆ, Vladislav ;MILČIĆ, Miodrag .
Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 67, n.9, p. 411-420, september 2021. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/predictions-of-friction-coefficient-in-hydrodynamic-journal-bearing-using-artificial-neural-networks/>. Date accessed: 09 dec. 2024. 
doi:http://dx.doi.org/10.5545/sv-jme.2021.7230.
Milčić, D., Alsammarraie, A., Madić, M., Krstić, V., & Milčić, M.
(2021).
Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks.
Strojniški vestnik - Journal of Mechanical Engineering, 67(9), 411-420.
doi:http://dx.doi.org/10.5545/sv-jme.2021.7230
@article{sv-jmesv-jme.2021.7230,
	author = {Dragan  Milčić and Amir  Alsammarraie and Miloš  Madić and Vladislav  Krstić and Miodrag  Milčić},
	title = {Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {67},
	number = {9},
	year = {2021},
	keywords = {artificial neural network, hydrodynamic journal bearing, babbitt metal tin-based alloy, friction coefficient},
	abstract = {This paper explores the influence of the frequency of shaft sleeve rotation and radial load on a journal bearing made of tin-babbitt alloy (Tegotenax V840) under hydrodynamic lubrication conditions. An experimental test of the frictional behaviour of a radial plain bearing was performed on an originally developed device for testing rotating elements: radial and plain bearings. Using the back-propagation neural network, based on experimental data, artificial neural network models were developed to predict the dependence of the friction coefficient and bearing temperature in relation to the radial load and speed. Using experimental data of the measured friction coefficient with which the artificial neural network was trained, well-trained networks with a mean absolute percentage error on training and testing of 0.0054 % and 0.0085 %, respectively, were obtained. Thus, a well-trained neural network model can predict the friction coefficient depending on the radial load and the speed.},
	issn = {0039-2480},	pages = {411-420},	doi = {10.5545/sv-jme.2021.7230},
	url = {https://www.sv-jme.eu/article/predictions-of-friction-coefficient-in-hydrodynamic-journal-bearing-using-artificial-neural-networks/}
}
Milčić, D.,Alsammarraie, A.,Madić, M.,Krstić, V.,Milčić, M.
2021 September 67. Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 67:9
%A Milčić, Dragan 
%A Alsammarraie, Amir 
%A Madić, Miloš 
%A Krstić, Vladislav 
%A Milčić, Miodrag 
%D 2021
%T Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks
%B 2021
%9 artificial neural network, hydrodynamic journal bearing, babbitt metal tin-based alloy, friction coefficient
%! Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks
%K artificial neural network, hydrodynamic journal bearing, babbitt metal tin-based alloy, friction coefficient
%X This paper explores the influence of the frequency of shaft sleeve rotation and radial load on a journal bearing made of tin-babbitt alloy (Tegotenax V840) under hydrodynamic lubrication conditions. An experimental test of the frictional behaviour of a radial plain bearing was performed on an originally developed device for testing rotating elements: radial and plain bearings. Using the back-propagation neural network, based on experimental data, artificial neural network models were developed to predict the dependence of the friction coefficient and bearing temperature in relation to the radial load and speed. Using experimental data of the measured friction coefficient with which the artificial neural network was trained, well-trained networks with a mean absolute percentage error on training and testing of 0.0054 % and 0.0085 %, respectively, were obtained. Thus, a well-trained neural network model can predict the friction coefficient depending on the radial load and the speed.
%U https://www.sv-jme.eu/article/predictions-of-friction-coefficient-in-hydrodynamic-journal-bearing-using-artificial-neural-networks/
%0 Journal Article
%R 10.5545/sv-jme.2021.7230
%& 411
%P 10
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 67
%N 9
%@ 0039-2480
%8 2021-09-28
%7 2021-09-28
Milčić, Dragan, Amir  Alsammarraie, Miloš  Madić, Vladislav  Krstić, & Miodrag  Milčić.
"Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks." Strojniški vestnik - Journal of Mechanical Engineering [Online], 67.9 (2021): 411-420. Web.  09 Dec. 2024
TY  - JOUR
AU  - Milčić, Dragan 
AU  - Alsammarraie, Amir 
AU  - Madić, Miloš 
AU  - Krstić, Vladislav 
AU  - Milčić, Miodrag 
PY  - 2021
TI  - Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2021.7230
KW  - artificial neural network, hydrodynamic journal bearing, babbitt metal tin-based alloy, friction coefficient
N2  - This paper explores the influence of the frequency of shaft sleeve rotation and radial load on a journal bearing made of tin-babbitt alloy (Tegotenax V840) under hydrodynamic lubrication conditions. An experimental test of the frictional behaviour of a radial plain bearing was performed on an originally developed device for testing rotating elements: radial and plain bearings. Using the back-propagation neural network, based on experimental data, artificial neural network models were developed to predict the dependence of the friction coefficient and bearing temperature in relation to the radial load and speed. Using experimental data of the measured friction coefficient with which the artificial neural network was trained, well-trained networks with a mean absolute percentage error on training and testing of 0.0054 % and 0.0085 %, respectively, were obtained. Thus, a well-trained neural network model can predict the friction coefficient depending on the radial load and the speed.
UR  - https://www.sv-jme.eu/article/predictions-of-friction-coefficient-in-hydrodynamic-journal-bearing-using-artificial-neural-networks/
@article{{sv-jme}{sv-jme.2021.7230},
	author = {Milčić, D., Alsammarraie, A., Madić, M., Krstić, V., Milčić, M.},
	title = {Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {67},
	number = {9},
	year = {2021},
	doi = {10.5545/sv-jme.2021.7230},
	url = {https://www.sv-jme.eu/article/predictions-of-friction-coefficient-in-hydrodynamic-journal-bearing-using-artificial-neural-networks/}
}
TY  - JOUR
AU  - Milčić, Dragan 
AU  - Alsammarraie, Amir 
AU  - Madić, Miloš 
AU  - Krstić, Vladislav 
AU  - Milčić, Miodrag 
PY  - 2021/09/28
TI  - Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 67, No 9 (2021): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2021.7230
KW  - artificial neural network, hydrodynamic journal bearing, babbitt metal tin-based alloy, friction coefficient
N2  - This paper explores the influence of the frequency of shaft sleeve rotation and radial load on a journal bearing made of tin-babbitt alloy (Tegotenax V840) under hydrodynamic lubrication conditions. An experimental test of the frictional behaviour of a radial plain bearing was performed on an originally developed device for testing rotating elements: radial and plain bearings. Using the back-propagation neural network, based on experimental data, artificial neural network models were developed to predict the dependence of the friction coefficient and bearing temperature in relation to the radial load and speed. Using experimental data of the measured friction coefficient with which the artificial neural network was trained, well-trained networks with a mean absolute percentage error on training and testing of 0.0054 % and 0.0085 %, respectively, were obtained. Thus, a well-trained neural network model can predict the friction coefficient depending on the radial load and the speed.
UR  - https://www.sv-jme.eu/article/predictions-of-friction-coefficient-in-hydrodynamic-journal-bearing-using-artificial-neural-networks/
Milčić, Dragan, Alsammarraie, Amir, Madić, Miloš, Krstić, Vladislav, AND Milčić, Miodrag.
"Predictions of Friction Coefficient in Hydrodynamic Journal Bearing Using Artificial Neural Networks" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 67 Number 9 (28 September 2021)

Authors

Affiliations

  • University of Niš, Faculty of Mechanical Engineering, Serbia 1
  • Tikrit University, Engineering Faculty, Iraq 2
  • Ljubex International, Serbia 3

Paper's information

Strojniški vestnik - Journal of Mechanical Engineering 67(2021)9, 411-420
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.

https://doi.org/10.5545/sv-jme.2021.7230

This paper explores the influence of the frequency of shaft sleeve rotation and radial load on a journal bearing made of tin-babbitt alloy (Tegotenax V840) under hydrodynamic lubrication conditions. An experimental test of the frictional behaviour of a radial plain bearing was performed on an originally developed device for testing rotating elements: radial and plain bearings. Using the back-propagation neural network, based on experimental data, artificial neural network models were developed to predict the dependence of the friction coefficient and bearing temperature in relation to the radial load and speed. Using experimental data of the measured friction coefficient with which the artificial neural network was trained, well-trained networks with a mean absolute percentage error on training and testing of 0.0054 % and 0.0085 %, respectively, were obtained. Thus, a well-trained neural network model can predict the friction coefficient depending on the radial load and the speed.

artificial neural network, hydrodynamic journal bearing, babbitt metal tin-based alloy, friction coefficient