Low-cycle fatigue life prediction method for stud connectors based on interpretable machine learning
Abstract Low-cycle fatigue is a common failure mode of stud connectors in bridges. Accurate prediction of their life is crucial for material design and engineering applications. However, traditional theoretical formulas and experimental methods suffer from limitations such as low accuracy and indivi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-08-01
|
| Series: | Journal of Materials Science: Materials in Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40712-025-00316-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849237619048710144 |
|---|---|
| author | Jianan Pan Xiaoling Liu Bing Wang Ying Liu |
| author_facet | Jianan Pan Xiaoling Liu Bing Wang Ying Liu |
| author_sort | Jianan Pan |
| collection | DOAJ |
| description | Abstract Low-cycle fatigue is a common failure mode of stud connectors in bridges. Accurate prediction of their life is crucial for material design and engineering applications. However, traditional theoretical formulas and experimental methods suffer from limitations such as low accuracy and individual variability. This study aims to develop a high-precision prediction model for low-cycle fatigue life using machine learning methods, providing a new approach for material performance evaluation. Firstly, through literature analysis and correlation analysis, key feature variables were identified: f u , ln(τ max), ln(Δτ). Secondly, the predictive performance of nine machine learning models was compared by combining cross-validation and hyperparameter optimization. Based on the principle of complementary advantages, an ensemble model was established using Random Forest (RF) and Extreme Gradient Boosting Tree (XGBoost) as the basis. Finally, the SHAP tool was introduced to explain the model’s decision-making process. The results showed that compared to individual models, the integrated model reduced the MAPE by 8.91% and the RMSE by 14.83%, while increasing the R 2 by 7.32%. The main factor affecting the low-cycle fatigue life of studs is ln (τ max). The interaction between ln (τ max) and ln (Δ τ) has the greatest impact on the low-cycle fatigue life of the stud. These findings not only enhance the understanding of fatigue mechanisms in stud connectors but also provide a robust framework for optimizing material selection and design in steel–concrete composite structures. |
| format | Article |
| id | doaj-art-9046fa9acefb4d1e9bb84455acf35e33 |
| institution | Kabale University |
| issn | 3004-8958 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Materials Science: Materials in Engineering |
| spelling | doaj-art-9046fa9acefb4d1e9bb84455acf35e332025-08-20T04:01:53ZengSpringerOpenJournal of Materials Science: Materials in Engineering3004-89582025-08-0120111410.1186/s40712-025-00316-6Low-cycle fatigue life prediction method for stud connectors based on interpretable machine learningJianan Pan0Xiaoling Liu1Bing Wang2Ying Liu3Faculty of Maritime and Transportation, Ningbo University, NingboFaculty of Maritime and Transportation, Ningbo University, NingboSchool of Civil & Environmental Engineering and Geography Science, Ningbo UniversityFaculty of Maritime and Transportation, Ningbo University, NingboAbstract Low-cycle fatigue is a common failure mode of stud connectors in bridges. Accurate prediction of their life is crucial for material design and engineering applications. However, traditional theoretical formulas and experimental methods suffer from limitations such as low accuracy and individual variability. This study aims to develop a high-precision prediction model for low-cycle fatigue life using machine learning methods, providing a new approach for material performance evaluation. Firstly, through literature analysis and correlation analysis, key feature variables were identified: f u , ln(τ max), ln(Δτ). Secondly, the predictive performance of nine machine learning models was compared by combining cross-validation and hyperparameter optimization. Based on the principle of complementary advantages, an ensemble model was established using Random Forest (RF) and Extreme Gradient Boosting Tree (XGBoost) as the basis. Finally, the SHAP tool was introduced to explain the model’s decision-making process. The results showed that compared to individual models, the integrated model reduced the MAPE by 8.91% and the RMSE by 14.83%, while increasing the R 2 by 7.32%. The main factor affecting the low-cycle fatigue life of studs is ln (τ max). The interaction between ln (τ max) and ln (Δ τ) has the greatest impact on the low-cycle fatigue life of the stud. These findings not only enhance the understanding of fatigue mechanisms in stud connectors but also provide a robust framework for optimizing material selection and design in steel–concrete composite structures.https://doi.org/10.1186/s40712-025-00316-6Fatigue life predictionLow-cycle fatigueExplainable machine learningStud connectorsIntegrated model |
| spellingShingle | Jianan Pan Xiaoling Liu Bing Wang Ying Liu Low-cycle fatigue life prediction method for stud connectors based on interpretable machine learning Journal of Materials Science: Materials in Engineering Fatigue life prediction Low-cycle fatigue Explainable machine learning Stud connectors Integrated model |
| title | Low-cycle fatigue life prediction method for stud connectors based on interpretable machine learning |
| title_full | Low-cycle fatigue life prediction method for stud connectors based on interpretable machine learning |
| title_fullStr | Low-cycle fatigue life prediction method for stud connectors based on interpretable machine learning |
| title_full_unstemmed | Low-cycle fatigue life prediction method for stud connectors based on interpretable machine learning |
| title_short | Low-cycle fatigue life prediction method for stud connectors based on interpretable machine learning |
| title_sort | low cycle fatigue life prediction method for stud connectors based on interpretable machine learning |
| topic | Fatigue life prediction Low-cycle fatigue Explainable machine learning Stud connectors Integrated model |
| url | https://doi.org/10.1186/s40712-025-00316-6 |
| work_keys_str_mv | AT jiananpan lowcyclefatiguelifepredictionmethodforstudconnectorsbasedoninterpretablemachinelearning AT xiaolingliu lowcyclefatiguelifepredictionmethodforstudconnectorsbasedoninterpretablemachinelearning AT bingwang lowcyclefatiguelifepredictionmethodforstudconnectorsbasedoninterpretablemachinelearning AT yingliu lowcyclefatiguelifepredictionmethodforstudconnectorsbasedoninterpretablemachinelearning |