EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Based Fatigue Life Prediction for E36 Steel Welded Joints

Lina Zhu iD, Hongye Guo, Zongxian Song, Yong Liu, Jinling Peng, Jifeng Wang

Materials · 24.07.2025 · 18 (15) · 3481

DOI: 10.3390/ma18153481 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 24.07.2025. Verfasst von Lina Zhu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Wheel Rail Center, Tianjin Research Institute for Advanced Equipment, Tsinghua University, Tianjin 300300, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Tianjin Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

E36 steel, widely used in shipbuilding and offshore structures, offers moderate strength and excellent low-temperature toughness. However, its welded joints are highly susceptible to fatigue failure. Cracks typically initiate at weld toes or within the heat-affected zone (HAZ), severely limiting the fatigue life of fabricated components. Traditional life prediction methods are complex, inefficient, and lack accuracy. This study proposes a machine learning (ML) framework for efficient fatigue life prediction of E36 welded joints. Welded specimens using SQJ501 filler wire on prepared E36 steel established a dataset from 23 original fatigue test data points. The dataset was expanded via Z-parameter model fitting, with data scarcity addressed using SMOTE. Pearson correlation analysis validated data relationships. After grid-optimized training on the augmented data, models were evaluated on the original dataset. Results demonstrate that the machine learning models significantly outperformed the Z-parameter formula (R2 = 0.643, MAPE = 16.15%). The artificial neural network (R2 = 0.972, MAPE = 4.45%) delivered the best overall performance, while the random forest model exhibited high consistency between validation (R2 = 0.888, MAPE = 6.34%) and testing sets (R2 = 0.897), with its error being significantly lower than that of support vector regression.

Schlagwörter

Stichwörter der Autor:innen

E36 steelSMOTEZ-parameter modelartificial neural networkmachine learningrandom forestsupport vector regression

Autor:innen und Institutionen

  • Wheel Rail Center, Tianjin Research Institute for Advanced Equipment, Tsinghua University, Tianjin 300300, China.
  • School of Mechanical Engineering, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China.
  • School of Aeronautics and Astronautics, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China.
  • School of Materials Science and Engineering, Tianjin University, Tianjin 300350, China.

ORCID-Profile: Lina Zhu

Förderung

  • Tianjin Natural Science Foundation

Zitieren

APA

Zhu, L., Guo, H., Song, Z., Liu, Y., Peng, J., & Wang, J. (2025). Machine Learning-Based Fatigue Life Prediction for E36 Steel Welded Joints. Materials, 18(15), 3481. https://doi.org/10.3390/ma18153481

Vancouver

Zhu L, Guo H, Song Z, Liu Y, Peng J, Wang J. Machine Learning-Based Fatigue Life Prediction for E36 Steel Welded Joints. Materials. 2025;18(15):3481. doi:10.3390/ma18153481

BibTeX
@article{Zhu2025,
  author = {Zhu, Lina and Guo, Hongye and Song, Zongxian and Liu, Yong and Peng, Jinling and Wang, Jifeng},
  title = {Machine Learning-Based Fatigue Life Prediction for E36 Steel Welded Joints},
  journal = {Materials},
  year = {2025},
  volume = {18},
  number = {15},
  pages = {3481},
  doi = {10.3390/ma18153481}
}
Kostenlos starten →