An Improved Model for Predicting the Scattered S-N Curves

1320 Ogledov
608 Prenosov
Izvoz citacije: ABNT
KLEMENC, Jernej ;PODGORNIK, Bojan .
An Improved Model for Predicting the Scattered S-N Curves. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 65, n.5, p. 265-275, june 2019. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/sl/article/an-improved-model-for-predicting-the-scattered-s-n-curves/>. Date accessed: 05 jul. 2020. 
doi:http://dx.doi.org/10.5545/sv-jme.2018.5918.
Klemenc, J., & Podgornik, B.
(2019).
An Improved Model for Predicting the Scattered S-N Curves.
Strojniški vestnik - Journal of Mechanical Engineering, 65(5), 265-275.
doi:http://dx.doi.org/10.5545/sv-jme.2018.5918
@article{sv-jmesv-jme.2018.5918,
	author = {Jernej  Klemenc and Bojan  Podgornik},
	title = {An Improved Model for Predicting the Scattered S-N Curves},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {65},
	number = {5},
	year = {2019},
	keywords = {51CrV4 steel, conventional manufacturing technology, electro-slag remelting, S-N curve, serial hybrid neural network},
	abstract = {In this article an improved neural network model is presented that allows us to predict the scattered S-N curves. The model is capable of predicting the S-N curve in its high-cycle and very-high-cycle fatigue domains by considering also the increased scatter of the fatigue-life data below the knee point of the S-N curve. The scatter of the fatigue-life data for an arbitrary amplitude-stress level is modelled with a two-parametric Weibull’s probability density function, the parameters of which are varied as a function of the amplitude-stress level. The parameters of the S-N curve trend and its scatter distribution are not fixed, but depend on the parameters of the production process via a serial-hybrid neural network. The article presents the theoretical background and the application in the case of real experimental fatigue data for 51CrV4 spring steel manufactured with two different manufacturing technologies and two different heat treatments.},
	issn = {0039-2480},	pages = {265-275},	doi = {10.5545/sv-jme.2018.5918},
	url = {https://www.sv-jme.eu/sl/article/an-improved-model-for-predicting-the-scattered-s-n-curves/}
}
Klemenc, J.,Podgornik, B.
2019 June 65. An Improved Model for Predicting the Scattered S-N Curves. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 65:5
%A Klemenc, Jernej 
%A Podgornik, Bojan 
%D 2019
%T An Improved Model for Predicting the Scattered S-N Curves
%B 2019
%9 51CrV4 steel, conventional manufacturing technology, electro-slag remelting, S-N curve, serial hybrid neural network
%! An Improved Model for Predicting the Scattered S-N Curves
%K 51CrV4 steel, conventional manufacturing technology, electro-slag remelting, S-N curve, serial hybrid neural network
%X In this article an improved neural network model is presented that allows us to predict the scattered S-N curves. The model is capable of predicting the S-N curve in its high-cycle and very-high-cycle fatigue domains by considering also the increased scatter of the fatigue-life data below the knee point of the S-N curve. The scatter of the fatigue-life data for an arbitrary amplitude-stress level is modelled with a two-parametric Weibull’s probability density function, the parameters of which are varied as a function of the amplitude-stress level. The parameters of the S-N curve trend and its scatter distribution are not fixed, but depend on the parameters of the production process via a serial-hybrid neural network. The article presents the theoretical background and the application in the case of real experimental fatigue data for 51CrV4 spring steel manufactured with two different manufacturing technologies and two different heat treatments.
%U https://www.sv-jme.eu/sl/article/an-improved-model-for-predicting-the-scattered-s-n-curves/
%0 Journal Article
%R 10.5545/sv-jme.2018.5918
%& 265
%P 11
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 65
%N 5
%@ 0039-2480
%8 2019-06-18
%7 2019-06-18
Klemenc, Jernej, & Bojan  Podgornik.
"An Improved Model for Predicting the Scattered S-N Curves." Strojniški vestnik - Journal of Mechanical Engineering [Online], 65.5 (2019): 265-275. Web.  05 Jul. 2020
TY  - JOUR
AU  - Klemenc, Jernej 
AU  - Podgornik, Bojan 
PY  - 2019
TI  - An Improved Model for Predicting the Scattered S-N Curves
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2018.5918
KW  - 51CrV4 steel, conventional manufacturing technology, electro-slag remelting, S-N curve, serial hybrid neural network
N2  - In this article an improved neural network model is presented that allows us to predict the scattered S-N curves. The model is capable of predicting the S-N curve in its high-cycle and very-high-cycle fatigue domains by considering also the increased scatter of the fatigue-life data below the knee point of the S-N curve. The scatter of the fatigue-life data for an arbitrary amplitude-stress level is modelled with a two-parametric Weibull’s probability density function, the parameters of which are varied as a function of the amplitude-stress level. The parameters of the S-N curve trend and its scatter distribution are not fixed, but depend on the parameters of the production process via a serial-hybrid neural network. The article presents the theoretical background and the application in the case of real experimental fatigue data for 51CrV4 spring steel manufactured with two different manufacturing technologies and two different heat treatments.
UR  - https://www.sv-jme.eu/sl/article/an-improved-model-for-predicting-the-scattered-s-n-curves/
@article{{sv-jme}{sv-jme.2018.5918},
	author = {Klemenc, J., Podgornik, B.},
	title = {An Improved Model for Predicting the Scattered S-N Curves},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {65},
	number = {5},
	year = {2019},
	doi = {10.5545/sv-jme.2018.5918},
	url = {https://www.sv-jme.eu/sl/article/an-improved-model-for-predicting-the-scattered-s-n-curves/}
}
TY  - JOUR
AU  - Klemenc, Jernej 
AU  - Podgornik, Bojan 
PY  - 2019/06/18
TI  - An Improved Model for Predicting the Scattered S-N Curves
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 65, No 5 (2019): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2018.5918
KW  - 51CrV4 steel, conventional manufacturing technology, electro-slag remelting, S-N curve, serial hybrid neural network
N2  - In this article an improved neural network model is presented that allows us to predict the scattered S-N curves. The model is capable of predicting the S-N curve in its high-cycle and very-high-cycle fatigue domains by considering also the increased scatter of the fatigue-life data below the knee point of the S-N curve. The scatter of the fatigue-life data for an arbitrary amplitude-stress level is modelled with a two-parametric Weibull’s probability density function, the parameters of which are varied as a function of the amplitude-stress level. The parameters of the S-N curve trend and its scatter distribution are not fixed, but depend on the parameters of the production process via a serial-hybrid neural network. The article presents the theoretical background and the application in the case of real experimental fatigue data for 51CrV4 spring steel manufactured with two different manufacturing technologies and two different heat treatments.
UR  - https://www.sv-jme.eu/sl/article/an-improved-model-for-predicting-the-scattered-s-n-curves/
Klemenc, Jernej, AND Podgornik, Bojan.
"An Improved Model for Predicting the Scattered S-N Curves" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 65 Number 5 (18 June 2019)

Avtorji

Inštitucije

  • University of Ljubljana, Faculty of Mechanical Engineering, Slovenia 1
  • Institute of Metals and Technology, Slovenia 2

Informacije o papirju

Strojniški vestnik - Journal of Mechanical Engineering 65(2019)5, 265-275

https://doi.org/10.5545/sv-jme.2018.5918

In this article an improved neural network model is presented that allows us to predict the scattered S-N curves. The model is capable of predicting the S-N curve in its high-cycle and very-high-cycle fatigue domains by considering also the increased scatter of the fatigue-life data below the knee point of the S-N curve. The scatter of the fatigue-life data for an arbitrary amplitude-stress level is modelled with a two-parametric Weibull’s probability density function, the parameters of which are varied as a function of the amplitude-stress level. The parameters of the S-N curve trend and its scatter distribution are not fixed, but depend on the parameters of the production process via a serial-hybrid neural network. The article presents the theoretical background and the application in the case of real experimental fatigue data for 51CrV4 spring steel manufactured with two different manufacturing technologies and two different heat treatments.

51CrV4 steel, conventional manufacturing technology, electro-slag remelting, S-N curve, serial hybrid neural network