CRACK DEPTH DETECTION OF MASSIVE STRUCTURES BASED ON DATA-DRIVEN ALGORITHM
-
摘要: 裂缝是混凝土结构的主要病害，查明裂缝的深度能够为结构的耐久性和安全性评价提供可靠的信息，但同时也是混凝土结构检测的难点之一。提出了一种基于数据驱动的学习算法，通过考察波经过带缝结构传播的信号预测裂缝深度，采用扩展有限元法(Extended finite element methods, XFEM)和边界吸收层模型模拟了带缝大体积混凝土结构中的波传播过程，将接收点的观测信号和裂缝信息配对。基于人工神经网络的机器学习模型建立了基于XFEM数据集的裂缝深度预测模型。对于含未知裂缝信息的混凝土结构，通过测得的观测点信号，利用建立的机器学习模型实现裂缝深度的实时预测。通过2个数值算例验证了该算法的性能，结果表明所提出的数据驱动算法能够准确预测裂缝深度。Abstract: Cracks are the main diseases of concrete structures. Finding out the depth of cracks can provide reliable information for the durability and safety evaluation of structures, but it is also one of the difficulties in the detection of concrete structures. A data-driven learning algorithm is proposed to predict the crack depth by investigating the signal of wave propagation through the cracked structure. The wave propagation process in the cracked massive concrete structure is simulated by using the extended finite element methods (XFEM) and the boundary absorbing layer model, and the observation signal of the receiving point is paired with the crack information. Based on the machine learning model of artificial neural network, a fracture depth prediction model based on XFEM datasets is established. For the concrete structure with unknown crack information, through the measured observation point signals, the established machine learning model is utilized to realize the real-time prediction of crack depth. The performance of the algorithm is verified by two numerical examples. The results show that the proposed algorithm can accurately predict the crack depth.
-
-
![]()
图 8 两主频为fs=2.314 kHz和fp=3.660 kHz的输入信号
Figure 8. Input signal with two dominant frequencies fs=2.314 kHz and fp=3.660 kHz
![]()
图 11 2000次预测结果正态分布拟合图
Figure 11. Fitting diagram of normal distribution with 2000 predicted results
![]()
图 13 重力坝检测域几何尺寸及信号发射(接收)器布置 /m
Figure 13. Geometric dimension of gravity dam with detecting domain and arrangement of signal launcher (receiver)
![]()
图 15 两主频fs=225.92 Hz和fp=352.07 Hz的输入信号
Figure 15. Input signal with two dominant frequencies fs=225.92 Hz and fp=352.07 Hz
![]()
图 17 裂尖位置xT和yT的分布直方图
Figure 17. Distribution histogram of crack tip position xT and yT
![]()
图 19 2000次预测结果正态分布拟合图
Figure 19. Fitting diagram of normal distribution with 2000 predicted results
-
[1] 吴中如, 顾冲时. 重大水工混凝土结构病害检测与健康诊断 [M]. 北京: 高等教育出版社, 2005. WU Zhongru, GU Chongshi. Disease detection and health diagnosis of large hydraulic concrete structures [M]. Beijing: Higher Education Press, 2005. (in Chinese)
[2] 顾昊, 朱延涛, 顾冲时, 等. 混凝土坝健康状态态势诊断方法[J]. 水利学报, 2020, 51(8): 957 − 966. GU Hao, ZHU Yantao, GU Chongshi, et al. Tendency diagnostic method of the health state of concrete dam [J]. Shui Li Xue Bao, 2020, 51(8): 957 − 966. (in Chinese)
[3] 冯若愚, 陈瑛, 李志双. R波谱能量透射比法检测大体积混凝土裂缝研究[J]. 振动与冲击, 2016, 35(12): 221 − 225. FENG Ruoyu, CHEN Ying, LI Zhishuang. Cracks identification of mass concrete structures with R wave spectral energy transmission ratio method [J]. Journal of Vibration and Shock, 2016, 35(12): 221 − 225. (in Chinese)
[4] 王鹏, 韩庆邦, 姜学平, 等. 混凝土表面开口裂缝对近表面声波影响[J]. 声学技术, 2017, 36(3): 247 − 251. WANG Peng, HAN Qingbang, JIANG Xueping, et al. The influence of surface opening cracks on the sound wave near concrete surface [J]. Technical Acoustics, 2017, 36(3): 247 − 251. (in Chinese)
[5] LEE F W, CHAI H K, LIM K S. Characterizing concrete surface notch using Rayleigh wave phase velocity and wavelet parametric analyses [J]. Construction and Building Materials, 2017, 136: 627 − 642. doi: 10.1016/j.conbuildmat.2016.08.145
[6] 杜文卫, 江刚, 朱彬占. 基于瑞利波法对混凝土表面裂缝检测的数值研究[J]. 土木建筑与环境工程, 2018, 40(4): 151 − 158. DU Wenwei, JIANG Gang, ZHU Binzhan, et al. Numerical simulation on detection of concrete surface crack based on Rayleigh wave method [J]. Journal of Civil, Architectural & Environmental Engineering, 2018, 40(4): 151 − 158. (in Chinese)
[7] GHOSH D, BENIWAL S, GANGULI A, et al. Reference free imaging of subsurface cracks in concrete using Rayleigh waves [J]. Structural Control and Health Monitoring, 2018, 25(10): e2246.
[8] LACROIX F, NOËL M, MORADI F, et al. Nondestructive condition assessment of concrete slabs with artificial defects using wireless impact echo [J]. Journal of Performance of Constructed Facilities, 2021, 35(6): 04021072. doi: 10.1061/(ASCE)CF.1943-5509.0001651
[9] YU H F, LU L J, QIAO P Z. Localization and size quantification of surface crack of concrete based on Rayleigh wave attenuation model [J]. Construction and Building Materials, 2021, 280: 122437. doi: 10.1016/j.conbuildmat.2021.122437
[10] 陆林军, 余海帆, 乔丕忠. 基于应力波传播机理的混凝土无损检测研究综述[J]. 力学季刊, 2021, 42(2): 197 − 216. LU Linjun, YU Haifan, QIAO Pizhong. Nondestructive evaluation of concrete based on stress wave propagation mechanism: A review [J]. Chinese Quarterly of Mechanics, 2021, 42(2): 197 − 216. (in Chinese)
[11] CHEN H B, ZHOU M, GAN S Y, et al. Review of wave method-based non-destructive testing for steel-concrete composite structures: Multiscale simulation and multi-physics coupling analysis [J]. Construction and Building Materials, 2021, 302: 123832. doi: 10.1016/j.conbuildmat.2021.123832
[12] LIN S B, WANG Y J. Crack-depth estimation in concrete elements using ultrasonic shear-horizontal waves [J]. Journal of Performance of Constructed Facilities, 2020, 34(4): 04020064. doi: 10.1061/(ASCE)CF.1943-5509.0001473
[13] SUN H, WAISMAN H, BETTI R. A multiscale flaw detection algorithm based on XFEM [J]. International Journal for Numerical Methods in Engineering, 2014, 100: 477 − 503. doi: 10.1002/nme.4741
[14] ZHANG C, WANG C, LAHMER T, et al. A dynamic XFEM formulation for crack identification [J]. International Journal of Mechanics and Materials in Design, 2016, 12: 427 − 448. doi: 10.1007/s10999-015-9312-3
[15] 王佳萍, 杜成斌, 王翔, 等. 基于XFEM和改进人工蜂群算法的结构内部缺陷反演[J]. 工程力学, 2019, 36(9): 34 − 40. doi: 10.6052/j.issn.1000-4750.2017.11.0874 WANG Jiaping, DU Chengbin, WANG Xiang, et al. Inverse analysis of internal defects in structures using extended finite element method and improved artificial bee colony algorithm [J]. Engineering Mechanics, 2019, 36(9): 34 − 40. (in Chinese) doi: 10.6052/j.issn.1000-4750.2017.11.0874
[16] 江守燕, 赵林鑫, 杜成斌. 基于频率和模态保证准则的结构内部多缺陷反演[J]. 力学学报, 2019, 51(4): 1091 − 1100. doi: 10.6052/0459-1879-19-078 JIANG Shouyan, ZHAO Linxin, DU Chengbin. Identification of multiple flaws in structures based on frequency and model assurance criteria [J]. Chinese Journal of Theoretical and Applied Mechanics, 2019, 51(4): 1091 − 1100. (in Chinese) doi: 10.6052/0459-1879-19-078
[17] MA C, YU T, LICH LV, et al. Detection of multiple complicated flaw clusters by dynamic variable-node XFEM with a three-step detection algorithm [J]. European Journal of Mechanics - A/Solids, 2020, 82: 103980. doi: 10.1016/j.euromechsol.2020.103980
[18] 翁顺, 朱宏平. 基于有限元模型修正的土木结构损伤识别方法[J]. 工程力学, 2021, 38(3): 1 − 16. doi: 10.6052/j.issn.1000-4750.2020.06.ST02 WENG Shun, ZHU Hongping. Damage identification of civil structures based on finite element model updating [J]. Engineering Mechanics, 2021, 38(3): 1 − 16. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.06.ST02
[19] JUNG J, JEONG C, TACIROGLU E. Identification of a scatterer embedded in elastic heterogeneous media using dynamic XFEM [J]. Computer Methods in Applied Mechanics and Engineering, 2013, 259: 50 − 63. doi: 10.1016/j.cma.2013.03.001
[20] MUYIWA A, NGUYEN-TUAN L, WUTTKE F, et al. Damage identification in gravity dams using dynamic coupled hydro-mechanical XFEM [J]. International Journal of Mechanics and Materials in Design, 2018, 14(1): 157 − 175. doi: 10.1007/s10999-017-9367-4
[21] AGATHOS K, TATSIS K, NICOLI S, et al. Crack detection in Mindlin-Reissner plates under dynamic loads based on fusion of data and models [J]. Computers and Structures, 2021, 246: 106475. doi: 10.1016/j.compstruc.2020.106475
[22] 卓德兵, 曹晖. 基于小波时频图与轻量级卷积神经网络的螺栓连接损伤识别[J]. 工程力学, 2021, 38(9): 228 − 238. doi: 10.6052/j.issn.1000-4750.2021.02.0116 ZHUO Debing, CAO Hui. Damage identification of bolt connections based on wavelet time-frequency diagrams and lightweight [J]. Engineering Mechanics, 2021, 38(9): 228 − 238. (in Chinese) doi: 10.6052/j.issn.1000-4750.2021.02.0116
[23] LI X, LIU Z L, CUI S Q, et al. Predicting the effective mechanical property of heterogeneous materials by image based modeling and deep learning [J]. Computer Methods in Applied Mechanics and Engineering, 2019, 347: 735 − 753. doi: 10.1016/j.cma.2019.01.005
[24] FENG S Z, HAN X, MA Z J, et al. Data-driven algorithm for real-time fatigue life prediction of structures with stochastic parameters [J]. Computer Methods in Applied Mechanics and Engineering, 2020, 372: 113373. doi: 10.1016/j.cma.2020.113373
[25] JIANG S Y, ZHAO L X, DU C B. Combining dynamic XFEM with machine learning for detection of multiple flaws [J]. International Journal for Numerical Methods in Engineering, 2021, 122: 6253 − 6282. doi: 10.1002/nme.6791
[26] 韩小雷, 冯润平, 季静, 等. 基于深度学习的RC梁集中塑性铰模型参数研究[J]. 工程力学, 2021, 38(11): 160 − 169. doi: 10.6052/j.issn.1000-4750.2020.11.0793 HAN Xiaolei, FENG Runping, JI Jing, et al. Research on parameters of the RC bea m lumped plastic hinge model based on deep learning [J]. Engineering Mechanics, 2021, 38(11): 160 − 169. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.11.0793
[27] 李想, 严子铭, 柳占立, 等. 基于仿真和数据驱动的先进结构材料设计[J]. 力学进展, 2021, 51(1): 82 − 105. doi: 10.6052/1000-0992-20-012 LI Xiang, YAN Ziming, LIU Zhanli, et al. Advanced structural material design based on simulation and data-driven method [J]. Advances in Mechanics, 2021, 51(1): 82 − 105. (in Chinese) doi: 10.6052/1000-0992-20-012
[28] 赵林鑫, 江守燕, 杜成斌. 基于SBFEM和机器学习的薄板结构缺陷反演[J]. 工程力学, 2021, 38(6): 36 − 46. doi: 10.6052/j.issn.1000-4750.2020.06.0416 ZHAO Linxin, JIANG Shouyan, DU Chengbin. Flaws detection in thin plate structures based on SBFEM and machine learning [J]. Engineering Mechanics, 2021, 38(6): 36 − 46. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.06.0416
[29] 江守燕, 杜成斌. 一种XFEM 断裂分析的裂尖单元新型改进函数[J]. 力学学报, 2013, 45(1): 134 − 138. JIANG Shouyan, DU Chengbin. A novel enriched function of elements containing crack tip for fracture analysis in XFEM [J]. Chinese Journal of Theoretical and Applied Mechanics, 2013, 45(1): 134 − 138. (in Chinese)
[30] 江守燕, 杜成斌. 动载下缝端应力强度因子计算的扩展有限元法[J]. 应用数学和力学, 2013, 34(6): 586 − 597. doi: 10.3879/j.issn.1000-0887.2013.06.005 JIANG Shouyan, DU Chengbin. Evaluation on stress intensity factors at the crack tip under dynamic loads using extended finite element methods [J]. Applied Mathematics and Mechanics, 2013, 34(6): 586 − 597. (in Chinese) doi: 10.3879/j.issn.1000-0887.2013.06.005
[31] SEMBLAT J F, LENTI L, GANDOMZADEH A. A simple multi-directional absorbing layer method to simulate elastic wave propagation in unbounded domains [J]. International Journal for Numerical Methods in Engineering, 2011, 85(12): 1543 − 1563.
[32] WANG L, HUANG Y, LUO X, et al. Image deblurring with filters learned by extreme learning machine [J]. Neurocomputing, 2011, 74: 2464 − 2474. doi: 10.1016/j.neucom.2010.12.035
-
期刊类型引用(6)
1. 李厚萱，张洪，许博伟，夏润川，周建庭. 基于自发漏磁与WOA-XGBoost模型的钢绞线腐蚀程度检测. 中国公路学报. 2025(04): 98-109 . 
百度学术
2. 江守燕，邓王涛，孙立国，杜成斌. 数据驱动的半无限介质裂纹识别模型研究. 力学学报. 2024(06): 1727-1739 . 百度学术
3. 王飞阳. 脆性材料统一断裂相场方法及其裂缝宽度的确定. 工程力学. 2024(06): 1-8 . 本站查看
4. 袁程，熊青松，孔庆钊. 钢筋混凝土剪力墙抗震滞回性能的多元时序深度神经网络预测. 工程力学. 2024(06): 66-76 . 本站查看
5. 田辉，贾宇，汤雷，王玉磊，张盛行，李坡. 基于纳米磁性指示剂的混凝土裂缝深度可视化探测研究. 水利水电技术(中英文). 2024(S2): 616-624 . 百度学术
6. 唐和生，何展朋，廖洋洋，谢丽宇. 基于物理驱动深度迁移学习的薄板力学正反问题. 工程力学. 2023(08): 1-10 . 本站查看
其他类型引用(3)
下载:
计量
- 文章访问数: 497
- HTML全文浏览量: 234
- PDF下载量: 157
- 被引次数: 9
