Application of machine learning methods in multiaxial fatigue life prediction

Krzysztof Pałczyński; Dariusz Skibicki; Łukasz Pejkowski; Tomasz Andrysiak

doi:10.1111/ffe.13874

journal article Nov 06, 2022

Application of machine learning methods in multiaxial fatigue life prediction

Krzysztof Pałczyński

Dariusz Skibicki Łukasz Pejkowski

Tomasz Andrysiak

Fatigue & Fracture of Engineering Materials & Structures Vol. 46 No. 2 pp. 416-432 · Wiley

View at Publisher Save 10.1111/ffe.13874

Abstract

AbstractThis paper compares the results of multiaxial fatigue life estimation using machine learning methods and classical fatigue models. The fatigue life of PA38‐T6 aluminum alloy under uniaxial, proportional, and non‐proportional loading, including asynchronous loading, is studied. Machine learning methods are trained only on basic loadings, namely, axial, torsional, and 90° out‐of‐phase. The results obtained with the machine learning algorithms, dense neural networks, support vector regression (with linear and radial basis functions), decision tree, random forest, and XGBoost algorithms, are comparable to the results of classical models like Ellyin–Gołoś, Fatemi–Socie, and Ince–Glinka. The best results are achieved for dense neural networks. In that case, they are often slightly more accurate than those obtained using classical methods.

Topics

No keywords indexed for this article. Browse by subject →

References

58

[1]

10.1016/j.matdes.2014.03.019

[2]

10.1016/j.engfailanal.2021.105472

[3]

10.1016/s1350-6307(02)00068-7

[4]

10.1016/j.engfailanal.2018.03.033

[5]

10.1051/matecconf/201816516007

[6]

10.1016/j.ijfatigue.2017.09.008

[7]

10.1016/j.ijfatigue.2010.11.002

[8]

Khonsari MM "General quantification of fatigue damage with provision for microstructure: a review" Fatigue Fract Eng Mater Struct (2021)

[9]

10.1063/1.4965945

[10]

10.1016/j.ijfatigue.2020.105966

[11]

10.1016/j.msea.2010.05.018

[12]

10.1016/j.msea.2014.01.015

[13]

10.1016/j.ijfatigue.2019.105460

[14]

10.1016/j.ijfatigue.2012.09.014

[15]

10.1111/ffe.13640

[16]

10.1111/ffe.13792

[17]

10.1111/ffe.13793

[18]

10.1111/ffe.13759

[19]

10.1111/ffe.13693

[20]

10.1111/ffe.13433

[21]

10.1111/ffe.13660

[22]

10.1111/ffe.13559

[23]

10.1111/ffe.13608

[24]

10.1111/ffe.13540

[25]

10.1016/j.ijfatigue.2020.105941

[26]

10.1016/j.ijfatigue.2020.106089

[27]

10.1016/j.ijfatigue.2019.105194

[28]

10.1016/j.ijfatigue.2020.105619

[29]

10.1016/j.ijfatigue.2020.106136

[30]

10.1016/j.coco.2021.100812

[31]

10.1016/j.ymssp.2018.12.046

[32]

10.1016/j.ymssp.2022.108875

[33]

10.1016/j.engfailanal.2021.105435

[34]

10.1016/j.ijfatigue.2019.05.032

[35]

10.1016/j.ijfatigue.2021.106415

[36]

10.1016/j.ijfatigue.2005.04.012

[37]

10.1016/j.ijfatigue.2021.106356

[38]

A novel deep learning approach of multiaxial fatigue life-prediction with a self-attention mechanism characterizing the effects of loading history and varying temperature

Jingye Yang, Guozheng Kang, Qianhua Kan

International Journal of Fatigue 10.1016/j.ijfatigue.2022.106851

[39]

10.1111/ffe.13532

[40]

10.1111/j.1460-2695.1988.tb01169.x

[41]

10.1016/j.ymssp.2021.108599

[42]

10.1111/ffe.13343

[43]

Drucker H (1996)

[44]

10.1109/tge.1977.6498972

[45]

Random Forests

Leo Breiman

Machine Learning 10.1023/a:1010933404324

[46]

10.1145/2939672.2939785

[47]

10.1115/1.3226012

[48]

10.1115/1.2903365

[49]

Bannantine JA (1989)

[50]

10.1016/j.ijfatigue.2019.105202

Showing 50 of 58 references

Cited By

51

Prediction of multiaxial fatigue life with a data-driven knowledge transfer model

Lei Gan, Zhi-Ming Fan · 2025

International Journal of Fatigue

Metrics

51

Citations

58

References

Details

Published: Nov 06, 2022
Vol/Issue: 46(2)
Pages: 416-432
License: View

Authors

K

Krzysztof Pałczyński

Faculty of Telecommunications, Computer Science and Electrical Engineering Bydgoszcz University of Science and Technology Bydgoszcz Poland

D

Dariusz Skibicki

Faculty of Mechanical Engineering Bydgoszcz University of Science and Technology Bydgoszcz Poland

�

Łukasz Pejkowski

Faculty of Mechanical Engineering Bydgoszcz University of Science and Technology Bydgoszcz Poland

T

Tomasz Andrysiak

Faculty of Telecommunications, Computer Science and Electrical Engineering Bydgoszcz University of Science and Technology Bydgoszcz Poland

Cite This Article

Krzysztof Pałczyński, Dariusz Skibicki, Łukasz Pejkowski, et al. (2022). Application of machine learning methods in multiaxial fatigue life prediction. Fatigue & Fracture of Engineering Materials & Structures, 46(2), 416-432. https://doi.org/10.1111/ffe.13874

Application of machine learning methods in multiaxial fatigue life prediction

You May Also Like