Intelligent identification of nonlinear parameters in negative stiffness mechanism using SCINet
Physica Scripta · 08.05.2026 · 101 (18) · 185001
DOI: 10.1088/1402-4896/ae6490 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 06.05.2026. Verfasst von Yuxin Zhao und 4 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: Jiangsu Natural Science Foundation, Science foundation of Key Laboratory of Structure and Thermal Protection for High-Speed Aircraft of Ministry of Education, National Natural Science Foundation of China.
Abstract (Originalsprache)
The negative stiffness mechanism is extensively utilized in aerospace vibration isolation systems owing to its high load-bearing capacity, minimal deformation, and excellent control performance. However, the strong nonlinear behavior inherent poses significant challenges for accurate structural parameter identification. To address the above issue, this paper proposes a parameter identification method for negative stiffness systems based on the novel SCINet deep learning framework. The model incorporates a binary tree-style block interaction architecture that enables hierarchical decomposition of signal features. By integrating both self-learning and mutual-learning mechanisms, the framework enhances sensitivity to nonlinear characteristics. Each sub-block retains a global receptive field, which effectively mitigates the influence of noise on identification accuracy. Furthermore, we introduced pre-training and transfer learning techniques to address the common issue of data scarcity in practical engineering applications. By transferring features across datasets, the method reduces dependence on data from a single task, thereby enhancing the model’s robustness. Comparative experiments with baseline models confirm the proposed method’s superiority in terms of accuracy, robustness, and effectiveness. Simulation results demonstrate that the method can accurately identify nonlinear parameters and maintain high robustness under complex conditions, including Coulomb friction–viscous damping coupling. Finally, the method is tested in negative stiffness mechanism experiments to validate its engineering applicability. These findings provide reliable parameter calibration support for the optimal design of nonlinear buffering systems.
Förderung
- Jiangsu Natural Science Foundation
- Science foundation of Key Laboratory of Structure and Thermal Protection for High-Speed Aircraft of Ministry of Education
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Zhao, Y., Zhao, Y., Marchesiello, S., Anastasio, D., & Zhu, R. (2026). Intelligent identification of nonlinear parameters in negative stiffness mechanism using SCINet. Physica Scripta, 101(18), 185001. https://doi.org/10.1088/1402-4896/ae6490
Vancouver
Zhao Y, Zhao Y, Marchesiello S, Anastasio D, Zhu R. Intelligent identification of nonlinear parameters in negative stiffness mechanism using SCINet. Physica Scripta. 2026;101(18):185001. doi:10.1088/1402-4896/ae6490
BibTeX
@article{Zhao2026,
author = {Zhao, Yuxin and Zhao, Yudie and Marchesiello, Stefano and Anastasio, Dario and Zhu, Rui},
title = {Intelligent identification of nonlinear parameters in negative stiffness mechanism using SCINet},
journal = {Physica Scripta},
year = {2026},
volume = {101},
number = {18},
pages = {185001},
doi = {10.1088/1402-4896/ae6490}
}
EUVIMED