Fracture and Structural Integrity e-ISSN 1971-8993 Open access
Fatigue and Fracture of metallic alloys Vol. 18, No. 68 (2024)

Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions

Author and affiliation details
DOI
10.3221/IGF-ESIS.68.24
Pages
357-370
Published
Licence
CC BY 4.0

Abstract

Various input variables, including corrosion time, fretting force, stress, lubrication, heat-treating, and nano-particles, were evaluated by modeling of stress-controlled fatigue lifetimes in AlSi12CuNiMg aluminum alloy of the engine pistons with different machine learning (ML) techniques. Bending fatigue experiments were conducted through cyclic loading with zero mean stress, and then experimental data was predicted by five different ML-based models. Moreover, when the optimal ML prediction model was found, it was analyzed using the Shapley additive explanation (SHAP) values method. Results illustrated that extreme gradient boosting (XGBoost) had superior data for estimations, with average training coefficients of determination of at least 63% and 90%, respectively for fatigue lifetime and its logarithmic value. The SHAP values interpretation of the XGBoost model revealed that fretting force, stress, and corrosion time were the most significant inputs in estimating the logarithm values of fatigue lifetimes, respectively.

Keywords

Article history

  1. ReceivedUntil the next stage: 34 days
  2. RevisedUntil the next stage: 27 days
  3. AcceptedUntil the next stage: 4 days
  4. Published

About the authors

Mohammad Azadi

Mohammad Azadi was born in Shiraz, Iran in 1983. He received B.Sc. and M.Sc. degrees in mechanical engineering from Shiraz University, Shiraz, Iran and K.N. Toosi University of Technology, Tehran, Iran, respectively, in 2006 and 2008; and then, the Ph.D. degree in mechanical engineering from Sharif University of Technology, Tehran, Iran, in 2013. During his Ph.D., he has awarded an exchange program by the Ministry of Science, Research and Technology and also Irankhodro Powertrain Company, in order to perform a fatigue testing project in University of Leoben, Leoben, Austria, 2012.

From 2008 to 2015, he has worked in Irankhodro Powertrain Company, Tehran, Iran and for last two years, he was a project manager of a national turbo-charged engine. Since 2015, he has been an Assistant Professor in the Faculty of Mechanical Engineering, Semnan University, Semnan, Iran. Now, He is an Associate Professor, since 2019.

He is the author of two chapter-books, two conference proceedings, more than 90 journal articles, about 110 conference papers and 12 patents. He has been also funded to perform 8 research projects by Iranian universities and industries; in addition to one international project, entitled "Iran-Austria Impulse". He is an advisory board of International Journal of Engineering and also a reviewer in different ISI journals, such as International Journal of Fatigue and Materials Science and Engineering A. His research interests include solid mechanics, fatigue, fracture and creep, numerical methods, surface engineering, materials characterization, design of experiments, with the application of engine, aerospace and automotive industries, besides biomechanics. Nowadays, he is working on additive manufacturing to fabricate composites and nano-composites by 3D-printing, in order to evaluate fatigue properties of materials.

How to cite

APA

Azadi, M., & Matin, M. (2024). Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions. Fracture and Structural Integrity, 18(68), 357–370. https://doi.org/10.3221/IGF-ESIS.68.24

IEEE

M. Azadi and M. Matin, “Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions,” Fracture and Structural Integrity, vol. 18, no. 68, pp. 357–370, 2024, doi: 10.3221/IGF-ESIS.68.24.

MLA

Azadi, Mohammad, and Mahmood Matin. “Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions.” Fracture and Structural Integrity, vol. 18, no. 68, 2024, pp. 357–370. https://doi.org/10.3221/IGF-ESIS.68.24.

Chicago

Azadi, Mohammad, and Mahmood Matin. 2024. “Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions.” Fracture and Structural Integrity 18 (68): 357–370. https://doi.org/10.3221/IGF-ESIS.68.24.

Harvard

Azadi, M. and Matin, M. (2024) ‘Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions’, Fracture and Structural Integrity, 18(68), pp. 357–370. doi: 10.3221/IGF-ESIS.68.24.

Vancouver

Azadi M, Matin M. Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions. Fracture and Structural Integrity. 2024;18(68):357-370. doi:10.3221/IGF-ESIS.68.24

BibTeX

@article{azadi2024, author = {Azadi, Mohammad and Matin, Mahmood}, title = {Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions}, journal = {Fracture and Structural Integrity}, year = {2024}, volume = {18}, number = {68}, pages = {357--370}, doi = {10.3221/IGF-ESIS.68.24}, url = {https://doi.org/10.3221/IGF-ESIS.68.24}, issn = {1971-8993} }

RIS

TY - JOUR AU - Azadi, Mohammad AU - Matin, Mahmood TI - Shapley additive explanation on machine learning predictions of fatigue lifetimes in piston aluminum alloys under different manufacturing and loading conditions JO - Fracture and Structural Integrity T2 - Fracture and Structural Integrity PY - 2024 DA - 2024/03/11 VL - 18 IS - 68 SP - 357 EP - 370 DO - 10.3221/IGF-ESIS.68.24 UR - https://doi.org/10.3221/IGF-ESIS.68.24 SN - 1971-8993 ER -

Licence

Creative Commons Attribution 4.0 International

May be shared and adapted, provided appropriate credit is given. Copyright © 2024 Mohammad Azadi, Mahmood Matin.

Copyright 
Authors are allowed to retain both the copyright and the publishing rights of their articles without restrictions.  

Open Access Statement

Fracture and Structural Integrity (F&SI) is an open-access journal which means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles in this journal without asking prior permission from the publisher or the author. This is in accordance with the DOAI definition of open access.

F&SI operates under the Creative Commons Licence Attribution 4.0 International (CC-BY 4.0). This allows to copy and redistribute the material in any medium or format, to remix, transform and build upon the material for any purpose, even commercially, but giving appropriate credit, providing a link to the license, and indicating if changes were made.

Similar articles