Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 15.06 MB
Add to list
  1. Search results
  2. Prediction of residual stress distrib...

Prediction of residual stress distribution induced by ultrasonic nanocrystalline surface modification using machine learning

Chao Li (UGent) , Auezhan Amanov, Yifei Li (UGent) , Can Wang (UGent) , Dagang Wang and Magd Abdel Wahab (UGent)
(2024) ADVANCES IN ENGINEERING SOFTWARE. 188.
Author
Organization
Abstract
Ultrasonic Nanocrystalline Surface Modification (UNSM) offers an efficient and cost-effective approach for enhancing material mechanical properties by inducing Severe Plastic Deformation (SPD). It leads to grain refinement and substantial residual stress generation beneath the workpiece surface. This study investigates the influence of key modification parameters, specifically static load, vibration amplitude, and strike tip size on compressive residual stress (CRS) distribution. A Finite Element Method (FEM)-based model for the UNSM process is developed, and validated against experimental outcomes, yielding a dataset of 45 unique cases across various modification scenarios. The Balancing Composite Motion Optimization (BCMO), as a meta-heuristic algorithm is used to optimize the hyperparameters of the Support Vector Regression (SVR) model. Additionally, the performance of Artificial Neural Network (ANN), Polynomial Chaotic Extension (PCE), and Kriging algorithms is evaluated in parallel. Among these Machine Learning (ML) models, the SVR-BCMO emerges as a pioneer for its accuracy in estimating residual stress. A sensitivity analysis employing Sobol' indices further clarifies the distinct impact of each input parameter on residual stress distribution resulting from UNSM. In essence, this research offers a tool for rapidly estimating residual stress, even in cases of limited datasets. Furthermore, the findings help in making prompt decisions regarding of UNSM conditions. This is achieved by elucidating the effect of each input parameter and facilitating the determination of residual stresses in specific scenarios.
Keywords
Ultrasonic Nanocrystalline Surface, Modification, Residual stress, Finite Element Method, Machine Learning, Balancing Composite Motion Optimization, Sensitivity analysis, FATIGUE-CRACK GROWTH, GRAIN-SIZE, MECHANICAL-PROPERTIES, WEAR-RESISTANCE, FRETTING WEAR, MICROSTRUCTURE, BEHAVIORS, TITANIUM, LIFE

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 5.71 MB
  • Download
    Paper 2 ChaoLi maw R2 maw-v1 clean.docx
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • Word
    • |
    • 9.34 MB

Citation

Please use this url to cite or link to this publication:

MLA
Li, Chao, et al. “Prediction of Residual Stress Distribution Induced by Ultrasonic Nanocrystalline Surface Modification Using Machine Learning.” ADVANCES IN ENGINEERING SOFTWARE, vol. 188, 2024, doi:10.1016/j.advengsoft.2023.103570.
APA
Li, C., Amanov, A., Li, Y., Wang, C., Wang, D., & Abdel Wahab, M. (2024). Prediction of residual stress distribution induced by ultrasonic nanocrystalline surface modification using machine learning. ADVANCES IN ENGINEERING SOFTWARE, 188. https://doi.org/10.1016/j.advengsoft.2023.103570
Chicago author-date
Li, Chao, Auezhan Amanov, Yifei Li, Can Wang, Dagang Wang, and Magd Abdel Wahab. 2024. “Prediction of Residual Stress Distribution Induced by Ultrasonic Nanocrystalline Surface Modification Using Machine Learning.” ADVANCES IN ENGINEERING SOFTWARE 188. https://doi.org/10.1016/j.advengsoft.2023.103570.
Chicago author-date (all authors)
Li, Chao, Auezhan Amanov, Yifei Li, Can Wang, Dagang Wang, and Magd Abdel Wahab. 2024. “Prediction of Residual Stress Distribution Induced by Ultrasonic Nanocrystalline Surface Modification Using Machine Learning.” ADVANCES IN ENGINEERING SOFTWARE 188. doi:10.1016/j.advengsoft.2023.103570.
Vancouver
1.
Li C, Amanov A, Li Y, Wang C, Wang D, Abdel Wahab M. Prediction of residual stress distribution induced by ultrasonic nanocrystalline surface modification using machine learning. ADVANCES IN ENGINEERING SOFTWARE. 2024;188.
IEEE
[1]
C. Li, A. Amanov, Y. Li, C. Wang, D. Wang, and M. Abdel Wahab, “Prediction of residual stress distribution induced by ultrasonic nanocrystalline surface modification using machine learning,” ADVANCES IN ENGINEERING SOFTWARE, vol. 188, 2024.
@article{01J7GGMVVV0CS4Q6518X4C038A,
  abstract     = {{Ultrasonic Nanocrystalline Surface Modification (UNSM) offers an efficient and cost-effective approach for enhancing material mechanical properties by inducing Severe Plastic Deformation (SPD). It leads to grain refinement and substantial residual stress generation beneath the workpiece surface. This study investigates the influence of key modification parameters, specifically static load, vibration amplitude, and strike tip size on compressive residual stress (CRS) distribution. A Finite Element Method (FEM)-based model for the UNSM process is developed, and validated against experimental outcomes, yielding a dataset of 45 unique cases across various modification scenarios. The Balancing Composite Motion Optimization (BCMO), as a meta-heuristic algorithm is used to optimize the hyperparameters of the Support Vector Regression (SVR) model. Additionally, the performance of Artificial Neural Network (ANN), Polynomial Chaotic Extension (PCE), and Kriging algorithms is evaluated in parallel. Among these Machine Learning (ML) models, the SVR-BCMO emerges as a pioneer for its accuracy in estimating residual stress. A sensitivity analysis employing Sobol' indices further clarifies the distinct impact of each input parameter on residual stress distribution resulting from UNSM. In essence, this research offers a tool for rapidly estimating residual stress, even in cases of limited datasets. Furthermore, the findings help in making prompt decisions regarding of UNSM conditions. This is achieved by elucidating the effect of each input parameter and facilitating the determination of residual stresses in specific scenarios.}},
  articleno    = {{103570}},
  author       = {{Li, Chao and Amanov, Auezhan and Li, Yifei and Wang, Can and Wang, Dagang and Abdel Wahab, Magd}},
  issn         = {{0965-9978}},
  journal      = {{ADVANCES IN ENGINEERING SOFTWARE}},
  keywords     = {{Ultrasonic Nanocrystalline Surface,Modification,Residual stress,Finite Element Method,Machine Learning,Balancing Composite Motion Optimization,Sensitivity analysis,FATIGUE-CRACK GROWTH,GRAIN-SIZE,MECHANICAL-PROPERTIES,WEAR-RESISTANCE,FRETTING WEAR,MICROSTRUCTURE,BEHAVIORS,TITANIUM,LIFE}},
  language     = {{eng}},
  pages        = {{16}},
  title        = {{Prediction of residual stress distribution induced by ultrasonic nanocrystalline surface modification using machine learning}},
  url          = {{http://doi.org/10.1016/j.advengsoft.2023.103570}},
  volume       = {{188}},
  year         = {{2024}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: