Page 152 - 《爆炸与冲击》2026年第5期
P. 152
第 46 卷 第 5 期 爆 炸 与 冲 击 Vol. 46, No. 5
2026 年 5 月 EXPLOSION AND SHOCK WAVES May, 2026
DOI:10.11883/bzycj-2025-0179
图学习驱动的爆炸冲击钢筋混凝土柱
结构响应的建模与预测 *
潘刘娟 ,张雍奇 ,王祉乔 ,王名川 ,何 勇 ,胡 杰 ,吴威涛 ,彭江舟 1
1
2
3
1
1
1
2
(1. 南京理工大学机械工程学院,江苏 南京 210094;
2. 南京理工大学中法工程师学院,江苏 南京 210094;
3. 南京理工大学安全科学与工程学院,江苏 南京 210094)
摘要: 爆炸冲击下钢筋混凝土构件结构响应的高效准确预测对抢修决策、结构加固与防护设计具有关键意义。
现有结构响应快速计算方法,例如解析模型、轻量级数据驱动方法,虽具备较高计算效率,但在三维结构响应场计算
方面精度受限。提出了一种基于图神经网络(graph neural networks,GNN)的钢筋混凝土柱毁伤快速预测模型,通过
GNN 中的领域节点聚合机制高效传递结构内部的力学关联信息,从而在爆炸荷载输入与三维构件结构响应之间建立
端到端映射,实现对柱体毁伤状态的快速预测。进一步引入多工况特征耦合训练策略,使模型具备适应不同配筋率、
爆炸当量和起爆位置等工况的预测能力,显著提升了模型的跨工况泛用性能。结果表明,该模型单次预测耗时仅 55 ms,
较传统方法速度提升 4 个数量级,预测误差低于 3.33%,在多种爆炸工况下均实现高精度毁伤预测。该研究展示了 GNN
方法在爆炸毁伤预测中的应用潜力,为爆炸冲击结构毁伤的快速评估与防护优化提供创新技术路径。
关键词: 爆炸荷载;钢筋混凝土构件;毁伤效应;深度学习;图神经网络
中图分类号: O342 国标学科代码: 13015 文献标志码: A
Modeling and prediction of blast-Induced response in
RC columns using graph neural networks
1
1
2
1
PAN Liujuan , ZHANG Yongqi , WANG Zhiqiao , WANG Mingchuan ,
3
1
2
HE Yong , HU Jie , WU Weitao , PENG Jiangzhou 1
(1. School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, Jiangsu, China;
2. Sino-French Engineer School, Nanjing University of Science and Technology, Nanjing 210094, Jiangsu, China;
3. School of Safety Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, Jiangsu, China)
Abstract: The efficient and accurate prediction of structural responses in reinforced concrete components under blast loading
plays a critical role in emergency repair decision, structural strengthening, and protective design. Existing rapid methods for
calculating structural response, such as analytical models and lightweight data-driven approaches, are computationally
efficient. However, they are limited in accurately resolving three-dimensional structural response fields. A Graph Neural
Network (GNN)-based model for the rapid prediction of damage in reinforced concrete (RC) columns was proposed in this
paper. By leveraging the neighborhood node aggregation mechanism of GNNs, the model efficiently transmits mechanical
correlation information within the structure. This allows the model to establish an end-to-end mapping between blast load
inputs and the 3D structural response of the component, enabling rapid prediction of the column’s damage state. Furthermore, a
multi-scenario feature coupling training strategy is introduced to significantly enhance the model’s generalization capability.
* 收稿日期: 2025-06-17;修回日期: 2025-10-27
基金项目: 中国博士后基金(2025M774265);江苏省自然科学基金(BK20241439)
第一作者: 潘刘娟(2001- ),女,博士研究生,panliujuan@njust.edu.cn
通信作者: 彭江舟(1996- ),男,博士,博士后,pengjz@njust.edu.cn
051435-1

