基于砌体结构图像识别的古石拱桥建模策略

沈殷; 韩俊诚; 戴仕炳; 王钰

doi:10.3969/j.issn.0258-2724.20250233

基于砌体结构图像识别的古石拱桥建模策略

doi: 10.3969/j.issn.0258-2724.20250233

沈殷^1,,
韩俊诚¹,
戴仕炳^2, ,,
王钰¹

1.
同济大学土木工程学院，上海 200092
2.
同济大学建筑与城市规划学院，上海 200092

基金项目: 国家重点研发计划（2023YFF0906104）

详细信息

作者简介:
沈殷（1977—），女，副教授，研究方向为桥梁与隧道工程，E-mail：shenyin@tongji.edu.cn

通讯作者:
戴仕炳（1963—），男，教授，研究方向为历史建筑保护工程，E-mail：daishibing@tongji.edu.cn

中图分类号: U448.32
计量
- 文章访问数: 329
- HTML全文浏览量: 249
- PDF下载量: 45
- 被引次数: 0
出版历程
- 收稿日期: 2025-04-29
- 修回日期: 2025-10-12
- 刊出日期: 2025-10-23

Research on Modeling Strategy of Ancient Stone Arch Bridges Based on Masonry Structure Gap Image Recognition

1.
College of Civil Engineering, Tongji University, Shanghai 200092, China
2.
College of Architecture and Urban Planning, Tongji University, Shanghai 200092, China

摘要

摘要:
古石拱桥保护研究面临图纸缺乏、现场勘测困难和结构老化等多重挑战，导致精细化力学模型建构参数获取受阻，且砌块损伤状态难以准确模拟，限制了精细化力学模型的有效建立. 针对此，提出一种基于砌体结构缝隙图像识别的古石拱桥有限元建模策略. 首先，建立一个包含大量石拱桥砌块轮廓标签的数据集，采用YOLOv8卷积神经网络模型，对石拱桥图像进行各结构砌块轮廓的实例分割；其次，采用Douglas-Peucker算法对识别结果进行后处理，提取砌块的关键几何信息；最后，建立石拱桥的参数化建模流程，通过ABAQUS参数化建模脚本的开发，自动化生成与实际砌体结构精确匹配的分离式有限元模型，并通过建立砌块间的接触界面作用，进行后续有限元仿真分析. 研究结果表明：在自重及桥面荷载作用下，本文所建立的分离式有限元模型拱肋主应力峰值约为传统整体式有限元模型的1.2倍，且能够在砌体缺陷处呈现明显的应力集中现象，能够更准确地再现实际桥梁的砌块分布和局部缺陷，对揭示古桥砌体结构破坏机理具有显著优势，为古桥保护的力学仿真研究提供了新的视角和方法.
- 石拱桥 /
- 砌体桥梁 /
- 深度学习 /
- 分离式模型
Abstract:
The conservation of ancient stone arch bridges is severely hindered by drawing deficiency, difficult on-site survey, and structural deterioration. These obstacles make it difficult to acquire the geometric parameters required for refined mechanical models and to reproduce the real damage state of individual blocks. As a result, refined mechanical models can hardly be established effectively. To solve the problem, a finite-element (FE) modeling strategy of ancient stone arch bridges based on masonry structure gap image recognition is proposed. First, a dataset with a large number of labeled contours of blocks in stone arch bridges was constructed, and a trained YOLOv8 convolutional neural network was used for instance segmentation of the block contours on the bridge images. Second, the recognition results were post-processed with the Douglas–Peucker algorithm, and key geometric information of individual blocks was extracted. Finally, a parametric modeling procedure was developed: an ABAQUS parametric modeling script was developed to automatically generate a separate FE model that faithfully replicates the actual masonry structure, with contact interfaces defined between blocks for subsequent FE simulation analysis. The results show that under self-weight and deck loads, the peak principal stress in the arch rib predicted by the separate FE model is about 1.2 times that given by a conventional monolithic FE model, and conspicuous stress concentrations appear at masonry defects. The separate model can more accurately reproduce the block distribution and local defects of the actual bridge. It has significant advantages for revealing the damage mechanism of the masonry structure of ancient bridges, and provides a new perspective and method for the mechanical simulation study of ancient bridge protection.
- Arch bridges /
- Masonry bridges /
- Deep learning /
- Separate modeling

HTML全文

图 1 使用U-net对砌体进行砖石轮廓检测^[16]

Figure 1. Block contour detection of masonry structure by U-Net^[16]

下载: 全尺寸图片幻灯片

图 2 基于YOLOv5的裂缝检测^[20]

Figure 2. Crack detection based on YOLOv5^[20]

下载: 全尺寸图片幻灯片

图 3 砖石拱桥的结构特征

Figure 3. Structural characteristics of the masonry arch bridge

下载: 全尺寸图片幻灯片

图 4 双线性本构模型

Figure 4. Bilinear constitutive model

下载: 全尺寸图片幻灯片

图 5 数据集样本特征

Figure 5. Sample characteristics of the dataset

下载: 全尺寸图片幻灯片

图 6 预测模型结果

Figure 6. Predictive model results

下载: 全尺寸图片幻灯片

图 7 图像分割任务的P-R曲线

Figure 7. P-R curves for image segmentation task

下载: 全尺寸图片幻灯片

图 8 预测结果后处理示意

Figure 8. Schematic diagram of post-processing of prediction results

下载: 全尺寸图片幻灯片

图 9 实桥图像建立的砌块模型实例

Figure 9. Example of blocks lined up according to an actual bridge

下载: 全尺寸图片幻灯片

图 10 石拱桥建模策略流程

Figure 10. Flowchart of stone arch bridge modeling strategy

下载: 全尺寸图片幻灯片

图 11 自重荷载下拱肋主压应力

Figure 11. Principal compressive stress in arch rib under self-weight load

下载: 全尺寸图片幻灯片

图 12 自重荷载下主压应力分布

Figure 12. Principal compressive stress distribution under self-weight load

下载: 全尺寸图片幻灯片

表 1 训练集标签类型

Table 1. Training set label type

分类	标签名	力学作用	备注
拱	arch	主要承重构件
桥面板	plank	荷载加载平面
砖石	brick	传力构件	即山花墙的砌块
龙头石	dragon	桥台框架的重要构件	包括龙头石和天盘石
立柱	pillar	桥台框架的重要构件	又称对联石

下载: 导出CSV

表 2 模型训练超参数

Table 2. Hyperparameters for model training

训练次数/次	批量大小/个	LR
300	16	0.0005

下载: 导出CSV

表 3 砖石砌块的材料参数

Table 3. Material parameters of masonry blocks

弹性模量/ MPa	泊松比	密度/ （kg•m⁻³）	抗压强度/ MPa	抗拉强度/ MPa
5 650	0.3	2670	4.3	0.34

下载: 导出CSV

表 4 接触相互作用属性

Table 4. Contact interaction properties

G_IC/（N•mm⁻¹）	K_nn/（N•mm⁻³）	K_ss/（N•mm⁻³）	K_tt/（N•mm⁻³）
30	61.08	26.11	26.11

下载: 导出CSV

参考文献(25)

[1]	张承文, 淳庆, 花全均, 等. 基于元遗传算法的石拱桥传感器优化布置及评价方法研究[J]. 西南交通大学学报, 2026, 61(2): 561-571. ZHANG Chengwen, CHUN Qing, HUA Quanjun, et al. Optimal sensor placement and evaluation method of stone arch bridge based on meta-genetic algorithm[J]. Journal of Southwest Jiaotong University, 2026, 61(2): 561-571.
[2]	AYTULUN E, SOYOZ S, KARCIOGLU E. System identification and seismic performance assessment of a stone arch bridge[J]. Journal of Earthquake Engineering, 2022, 26(2): 723-743. doi: 10.1080/13632469.2019.1692740
[3]	LOURENCO P J B B. Computational strategies for masonry structures[D]. Delft: Technische Universiteit Delft, 1996.
[4]	岳增国, 金伟良, 傅军. 基于分离式模型的砌体结构有限元分析[C]//砌体结构理论与新型墙材应用. 长沙: 中国工程建设标准化协会砌体结构专业委员会, 2007: 79-83.
[5]	SILVA R, COSTA C, ARÊDE A, et al. Numerical simulations of experimental material testing in stone masonry arch railway bridges[J]. Structure and Infrastructure Engineering, 2024, 20(5): 633-652. doi: 10.1080/15732479.2022.2119585
[6]	张德宇, 王新宇, 施宵勇, 等. 基于ABAQUS的砌体结构抗剪性能有限元分析[J]. 厦门大学学报(自然科学版), 2021, 60(6): 1077-1082. doi: 10.6043/j.issn.0438-0479.202005003 ZHANG Deyu, WANG Xinyu, SHI Xiaoyong, et al. Finite element analysis of shear behavior of masonry structure based on ABAQUS[J]. Journal of Xiamen University (Natural Science), 2021, 60(6): 1077-1082. doi: 10.6043/j.issn.0438-0479.202005003
[7]	KARALAR M, ÇUFALI G. Structural assessment of historical stone bridges with the finite element method under dynamic effects of arch shape: the Antik Iscehisar Bridge[J]. Applied Sciences, 2023, 13(19): 10740. doi: 10.3390/app131910740
[8]	KESHMIRY A, HASSANI S, DACKERMANN U, et al. Assessment, repair, and retrofitting of masonry structures: a comprehensive review[J]. Construction and Building Materials, 2024, 442: 137380. doi: 10.1016/j.conbuildmat.2024.137380
[9]	谢明志, 樊丁萌, 蒋志鹏, 等. 基于计算机视觉的混凝土结构裂缝检测研究现状与展望[J/OL]. 西南交通大学学报, 2024: 1-20. (2024-09-14). https: //kns.cnki.net/KCMS/detail/detail.aspx?filename=XNJT20240913004&dbname=CJFD&dbcode=CJFQ.
[10]	LOVERDOS D, SARHOSIS V. Pixel-level block classification and crack detection from 3D reconstruction models of masonry structures using convolutional neural networks[J]. Engineering Structures, 2024, 310: 118113. doi: 10.1016/j.engstruct.2024.118113
[11]	朱前坤, 谢辰辉, 张琼, 等. 基于计算机视觉和深度学习的古桥裂缝识别方法[J]. 西南交通大学学报, 2026, 61(2): 529-540. ZHU Qiankun, XIE Chenhui, ZHANG Qiong, et al. Method for crack detection of ancient bridges based on computer vision and deep learning[J]. Journal of Southwest Jiaotong University, 2026, 61(2): 529-540.
[12]	余波. 基于深度学习的桥梁裂缝检测方法研究[D]. 西安: 西安科技大学, 2022.
[13]	ZHANG Y H. Application of BP neural network in structural damage diagnosis of bridge behind abutment[J]. Applied Mechanics and Materials, 2016, 847: 440-444. doi: 10.4028/www.scientific.net/AMM.847.440
[14]	马卫飞. 基于深度学习的桥梁裂缝检测算法研究[D]. 西安: 陕西师范大学, 2018.
[15]	RIVEIRO B, CONDE-CARNERO B, GONZÁLEZ-JORGE H, et al. Automatic creation of structural models from point cloud data: the case of masonry structures[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015, Ⅱ-3/W3: 3-9.
[16]	IBRAHIM Y, NAGY B, BENEDEK C. CNN-based watershed marker extraction for brick segmentation in masonry walls[C]//International Conference on Image Analysis and Recognition. Cham: Springer International Publishing, 2019: 332-344.
[17]	LOVERDOS D, SARHOSIS V. Automatic image-based brick segmentation and crack detection of masonry walls using machine learning[J]. Automation in Construction, 2022, 140: 104389. doi: 10.1016/j.autcon.2022.104389
[18]	LOVERDOS D, SARHOSIS V. Geometrical digital twins of masonry structures for documentation and structural assessment using machine learning[J]. Engineering Structures, 2023, 275: 115256. doi: 10.1016/j.engstruct.2022.115256
[19]	REDMON J, DIVVALA S, GIRSHICK R, et al. You Only Look Once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 779-788.
[20]	LIU Y, ZHOU T, XU J Y, et al. Rotating target detection method of concrete bridge crack based on YOLO v5[J]. Applied Sciences, 2023, 13(20): 11118.
[21]	李秋萍. 古桥结构体系及石拱桥的分析、监测评估与保护[D]. 杭州: 浙江大学, 2011.
[22]	李泽伟, 杨永清, 廖曼, 等. 基于计算机视觉与混合测量技术的结构裂缝识别方法[J]. 西南交通大学学报, 2025, 60(6): 1455-1464. doi: 10.3969/j.issn.0258-2724.20230700 LI Zewei, YANG Yongqing, LIAO Man,et al. Structural crack detection based on computer vision and hybrid measurement technology[J]. Structural crack detection based on computer vision and hybrid measurement technology, 2025, 60(6): 1455-1464. doi: 10.3969/j.issn.0258-2724.20230700
[23]	中交公路规划设计院. 公路圬工桥涵设计规范: JTG D61—2018[S]. 北京: 人民交通出版社, 2018.
[24]	王欣, 王忠凯. ABAQUS分离式模拟砌体墙性能[J]. 四川建筑科学研究, 2023, 49(3): 33-43. doi: 10.19794/j.cnki. 1008- 1933.2023.0031 WANG Xin, WANG Zhongkai. ABAQUS separate simulated masonry wall performance[J]. Sichuan Building Science, 2023, 49(3): 33-43. doi: 10.19794/j.cnki. 1008- 1933.2023.0031
[25]	RAPONE D, BRANDO G, SPACONE E. A discontinuum finite element modelling approach for reproducing the structural behavior of masonry walls[C]//14th World Congress in Computational Mechanics& ECCOMAS Congress 2020. Paris: [s.n.], 2020: 1-12.