Study on the deformation mode domain of shrink energy-absorbing structures based on curve feature classification method
Shrink energy-absorbing structures play a key role in engineering applications by absorbing impact energy and ensuring passenger safety. However, inappropriate structural parameters and contact conditions can lead to buckling instability or folding collapse, which reduces the energy absorption efficiency. For this purpose, a deformation mode classification method based on the curve feature was proposed. A Long Short Term Memory (LSTM) network was used to predict the crushing force curve, followed by feature extraction and mode classification to establish the mapping relationships from design parameters to deformation modes. The deformation mode domain was then constructed using the classification model for data expansion, and its boundaries were precisely defined using surface fitting techniques. The critical cone angles of the shrink deformation mode at different friction coefficients were obtained by two-dimensional analysis. In addition, a structural design strategy was also proposed to maximize the specific energy absorption (SEA) of the structure under the shrink deformation mode. The results show that the classification method can effectively predict the deformation modes with 97 % accuracy. Further analysis of the deformation mode domain reveals that the critical cone angle of the shrink deformation mode decreases with the increase of the friction coefficient. Overall, this study predicts the deformation modes of shrink energy-absorbing structures and analyzes the variation of the critical cone angle, providing important guidance for structural optimization and improving energy absorption efficiency. • The curve prediction network based on LSTM is established. • The deformation mode classification method based on the crushing curve feature is proposed. • The deformation mode domain of the shrink energy-absorbing structures is discussed. • The critical cone angle of the shrink deformation mode at different friction coefficients is obtained.
Authors
- Shuguang Yao (ORCID: https://orcid.org/0000-0002-1949-7921)
- Xu Ping (ORCID: https://orcid.org/0000-0003-4857-6466)
- Bo Wang (ORCID: https://orcid.org/0000-0002-3973-9377)
- Xin Zheng (ORCID: https://orcid.org/0009-0009-7103-1334)
- Jiaxing He (ORCID: https://orcid.org/0000-0001-5261-1426)
- Jie Xing (ORCID: https://orcid.org/0000-0002-9822-5368)
Institutions
- Central South University (CN)
- Ministry of Transport (CN)
- State Key Laboratory of Vehicle NVH and Safety Technology (CN)
Publication Details
- Journal
- Engineering Applications of Artificial Intelligence
- Published
- 2025-04-11
- DOI
- https://doi.org/10.1016/j.engappai.2025.110779
- Citations
- 1
- Primary Topic
- Cellular and Composite Structures
- Type
- article
- Field-Weighted Citation Impact
- 0.71