EUVIMEDEUVIMED entdecken
Crossref

Digital Twin for High-Precision Structural Strength Monitoring: Enhanced Multi-Source Data Fusion by Gradient Boosting

Kuo Tian, Zhiyong Sun, Ziyu Xu, Chong Liu

Journal of Applied Mechanics · 01.12.2026 · 93 (12)

DOI: 10.1115/1.4072738 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Mechanics, online erschienen am 28.10.2026. Verfasst von Kuo Tian und 3 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Significant magnitude discrepancies between simulated data and real measured data undermine the accuracy of multi-source data fusion in digital twin modeling. To address this limitation, a novel digital twin modeling method via enhanced multi-source data fusion by gradient boosting (DT-EMSDF-GB) is proposed for high-precision structural strength monitoring. The method comprises two stages, both leveraging gradient boosting algorithms. In the off-line stage, a pretrained model is constructed using massive simulated data with the gradient boosting decision tree method, ensuring computational efficiency. In the on-line stage, the residual values between the response values of real measured data and the prediction values of the pretrained model are first calculated. Subsequently, a gradient boosting-based support vector regression method is introduced to establish a residual model, which iteratively approximates these residual values. This helps address challenges of overfitting and large prediction bias under sparse real measured data. Finally, a digital twin is established by integrating the pretrained and residual models through an additive scaling function. To validate the effectiveness, an experiment is conducted on a hierarchical stiffened plate under axial compression. Results indicate that compared to other machine learning methods, the proposed method achieves an average 32% improvement in global prediction accuracy and a 72% enhancement in local prediction accuracy for the most critical areas. Notably, the proposed method reduces the off-line pretraining time by more than one order of magnitude compared with radial basis function and deep neural network methods, exhibiting the highest computational efficiency.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Tian, K., Sun, Z., Xu, Z., & Liu, C. (2026). Digital Twin for High-Precision Structural Strength Monitoring: Enhanced Multi-Source Data Fusion by Gradient Boosting. Journal of Applied Mechanics, 93(12). https://doi.org/10.1115/1.4072738

Vancouver

Tian K, Sun Z, Xu Z, Liu C. Digital Twin for High-Precision Structural Strength Monitoring: Enhanced Multi-Source Data Fusion by Gradient Boosting. Journal of Applied Mechanics. 2026;93(12). doi:10.1115/1.4072738

BibTeX
@article{Tian2026,
  author = {Tian, Kuo and Sun, Zhiyong and Xu, Ziyu and Liu, Chong},
  title = {Digital Twin for High-Precision Structural Strength Monitoring: Enhanced Multi-Source Data Fusion by Gradient Boosting},
  journal = {Journal of Applied Mechanics},
  year = {2026},
  volume = {93},
  number = {12},
  doi = {10.1115/1.4072738}
}
Kostenlos starten →