[1]颜东煌,袁臻,王烁.基于回归模型和声发射的混凝土裂纹坐标定位研究[J].长安大学学报(自然科学版),2026,46(2):57-72.[doi:10.19721/j.cnki.1671-8879.2026.02.005]
　YAN Dong-huang,YUAN Zhen,WANG Shuo.Research on coordinate localization of concrete cracks based on regression model and acoustic emission[J].Journal of Chang’an University (Natural Science Edition),2026,46(2):57-72.[doi:10.19721/j.cnki.1671-8879.2026.02.005]
点击复制

基于回归模型和声发射的混凝土裂纹坐标定位研究()
分享到：

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
第46卷
期数:
2026年2期
页码:
57-72
栏目:
桥梁与隧道工程
出版日期:
2026-04-18

文章信息/Info

Title:
Research on coordinate localization of concrete cracks based on regression model and acoustic emission
文章编号:
1671-8879(2026)02-0057-16
作者:
颜东煌; 袁臻; 王烁
(长沙理工大学 土木工程学院,湖南 长沙 410114)
Author(s):
YAN Dong-huang;  YUAN Zhen;  WANG Shuo
(School of Civil Engineering, Changsha University of Science and Technology,Changsha 410114, Hunan, China)
关键词:
桥梁工程;  裂纹检测;  卷积神经网络;  混凝土;  声发射;  回归模型
Keywords:
bridge engineering;  crack detection;  convolutional neural network;  concrete;  acoustic emission;  regression model
分类号:
U448.34
DOI:
10.19721/j.cnki.1671-8879.2026.02.005
文献标志码:
A
摘要:
为实现钢筋混凝土梁裂纹源的高精度定位,基于声发射技术与深度学习回归模型进行研究。基于模拟裂纹源与真实裂纹源的声发射信号,设计包含卷积层、池化层、展平层、全连接层和随机失活层的深度回归神经网络,直接预测裂纹源的空间坐标。利用模拟信号对网络进行训练与参数优化,并结合真实裂纹信号验证模型的定位性能。结果表明:提出模型在钢筋混凝土结构中的平均定位误差为2.51 cm,表现出良好的定位精度; 在敏感性分析中,模型在裂纹开展初期和中期均表现出较高的定位准确性; 随着裂纹扩展至后期,由于信号复杂性增加以及微裂纹的叠加效应,模型预测误差有所上升,定位精度出现一定下降; 针对不同噪声水平的鲁棒性分析显示,模型在低信噪比条件下仍能保持稳定的定位性能; 通过引入欧几里得距离作为损失函数,显著提高了模型对复杂材料的适应能力及其对裂纹位置预测的精度。研究结果表明该模型在钢筋混凝土裂纹源定位中具有良好的应用潜力。
Abstract:
To achieve high-precision localization of crack sources in reinforced concrete beams, this study investigated the use of acoustic emission(AE)technology combined with a deep learning regression model. Based on AE signals from both simulated and real crack sources, a deep regression neural network consisting of convolutional layers, pooling layers, flattening layers, fully connected layers, and dropout layers was designed to directly predict the spatial coordinates of crack sources. The network was trained and optimized by using simulated signals, and its localization performance was validated with real crack signals. The results show that the model achieves an average localization error of 2.51 cm in reinforced concrete structures, demonstrating good localization accuracy. In sensitivity analysis, the model exhibits high localization accuracy in the early and middle-stages of crack propagation. However, as the crack extends into the later stages, the complexity of the signals increases and the overlap of microcracks affects the model, leading to an increase in prediction errors and a decrease in localization accuracy. Robustness analysis under different noise levels shows that the model can maintain stable localization performance even under low signal-to-noise ratio(SNR)conditions. Furthermore, by introducing Euclidean distance as the loss function, the model's ability to adapt to complex materials and its accuracy in predicting crack locations are significantly improved. The findings suggest that the model has good potential for application in the localization of crack sources in reinforced concrete structures.1 tab, 22 figs, 30 refs.

参考文献/References:

[1] YUAN M, YAN D H, ZHONG H, et al. Experimental investigation of high-cycle fatigue behavior for prestressed concrete box-girders[J].Construction and Building Materials 2017, 157: 424-437.
[2]PENG J X, HU S W, ZHANG J R, et al. Influence of cracks on chloride diffusivity in concrete: A five-phase mesoscale model approach[J]. Construction and Building Materials, 2019, 197: 587-596.
[3]BERTOLINI L. Steel corrosion and service life of reinforced concrete structures[J]. Structure and Infrastructure Engineering, 2008, 4(2): 123-137.
[4]HAYDER A, MARY J, WILLIAM C, et al. Sutley, evaluation of a digital image correlation bridge inspection methodology on complex distortion-induced fatigue cracking[J]. Procedia Structural Integrity, 2019, 17: 682-689.
[5]CHEN G, LIANG Q, ZHONG W T, et al. Homography-based measurement of bridge vibration using UAV and DIC method[J]. Measurement, 2021, 170: 108683.
[6]TIAN F, HAO Y, ZOU Z, et al. An ultrasonic pulse-echo method to detect internal defects in epoxy composite insulation[J]. Energies, 2019, 12(24): 4804.
[7]周 娥,王晓勇.干耦合穿透法在橡胶复合材料无损检测中的应用研究[J].航天制造技术,2017(2):47-49.
ZHOU E, WANG Xiao-yong. Application of dry coupled penetration method in nondestructive testing of rubber composites[J]. Aerospace Manufacturing Technology, 2017(2): 47-49.
[8]ANAY R, ABRAM L, DAVID V, et al. On-site acoustic-emission monitoring for a prestressed concrete BT-54 AASHTO girder bridge[J]. Journal of Performance of Constructed Facilities 2020, 34: 04020034.
[9]HANNES H H, WINTER W E F, SIMACEK W. Acoustic emission measurements on bridges[J]. Journal of Acoustic Emission, 1991, 10: 67-70.
[10]ROYLES R. Acoustic emission monitoring of masonry arch bridges[J]. British Journal of Non-Destructive Testing, 1991, 33: 339-343.
[11]TOBIAS A. Acoustic-emission source location in two dimensions by an array of three sensors[J]. Non-destructive Testing, 1976, 9(1): 9-12.
[12]LIANG D, YUAN S, LIU M. Distributed coordination algorithm for impact location of preciseness and real-time on composite structures[J]. Measurement, 2013, 46(1): 527-536.
[13]MCLASKEY G C, GLASER S D, GROSSE C U. Beamforming array techniques for acoustic emission monitoring of large concrete structures[J]. Journal of Sound and Vibration, 2010, 329(12): 2384-2394.
[14]冯全明,陈 智,李冬生.基于波束成形网阵的声源定位及影响因素探究[J].预应力技术,2015,19(2):23-27.
FENG Quan-ming, CHEN Zhi, LI Dong-sheng. Exploration of sound source localization and influencing factors based on beamforming array. Prestress Technology[J]. prestressing technology, 2015, 19(2): 23-27.
[15]CAPRINO G. Acoustic emission source location in unidirectional carbon-fiber-reinforced plastic plates with virtually trained artificial neural networks[J]. Journal of Applied Polymer Science, 2011, 122(6): 3506-3513.
[16]LIU Z H. Acoustic emission source localization with generalized regression neural network based on time difference mapping method[J]. Experimental Mechanics, 2020, 60: 1-16.
[17]吴 鑫,赵红霞,罗筱毓,等.基于BP神经网络的岩石损伤声发射事件源定位研究[J].中国安全生产科学技术,2021,17(8):36-42.
WU Xin, ZHAO Hong-xia, LUO Xiao-yu. Study on acoustic emission event source location of rock damage based on BP neural network[J]. China's Safety Production Science and Technology, 2021, 17(8): 36-42.
[18]CIAMPA F, MEO M. A new algorithm for acoustic emission localization and flexural group velocity determination in anisotropic structures[J]. Composites Part A: Applied Science and Manufacturing, 2010, 41(12): 1777-1786.
[19]MOSTAFAVI A, CHA Y J. Deep learning-based active noise control on construction sites[J]. Automation in Construction, 2023, 151: 104885.
[20]BARBOSH M, DUNPHY K, SADHU A. Time-frequency assisted deep learning for crack localization using acoustic emission data[C]// Springer. Civil Engineering. Amsterdam: Springer, 2022: 244.
[21]ZHOU Y B, LIANG M F, YUE X L. Deep residual learning for acoustic emission source localization in a steel-concrete composite slab[J]. Construction and Building Materials, 2024, 411: 618-950.
[22]鞠文卿.碳纤维复合材料结构损伤声发射定位与识别方法研究[D].北京:北京化工大学,2024.
JU Wen-qing. Research on acoustic emission localization and identification method of damage of carbon fiber composite structures[D]. Beijing: Beijing University of Chemical Technology, 2024.
[23]YE G Y, XU K J, WU W K. Multi-variable classification model for valve internal leakage based on acoustic emission time-frequency domain characteristics and random forest[J]. Review of Scientific Instruments, 2021, 92(2): 025108.
[24]WON J, OH H, SAKONG J. Research on the acoustic emission source localization methodology in composite materials based on artificial intelligence[J]. ArXiv, 2024, 407: 5405.
[25]HESSER D F, MOSTAFAVI S, KOCUR G K, et al. Identification of acoustic emission sources for structural health monitoring applications based on convolutional neural networks and deep transfer learning[J]. Neurocomputing, 2021, 453: 1-12.
[26]LIU Z H, PENG Q L, LI X, et al. Acoustic emission source localization with generalized regression neural network based on time difference mapping method[J]. Experimental Mechanics, 2020, 60: 679-694.
[27]SAUSE M G R. Investigation of pencil-lead breaks as acoustic emission sources[J]. Journal of Acoustic Emission, 2011, 29: 184-196.
[28]骆勇鹏,王林堃,廖飞宇,等.基于一维卷积神经网络的结构损伤识别[J].地震工程与工程振动,2021,41(4):145-156.
LUO Yong-peng, WANG Lin-kun, LIAO Fei-yu. Vibration-based structural damage identification by 1-dimensional convolutional neural network[J].Earthquake Engineering and Engineering Vibration 2021, 41(4): 145-156.
[29]杨 渊,练继建,周观根,等. 基于一维卷积神经网络的钢桁架结构损伤识别[C]//第二十届全国现代结构工程学术研讨会论文集编委会.第二十届全国现代结构工程学术研讨会论文集.天津:天津大学出版社,2020:66-69.
YANG Yuan, LIAN Ji-jian, ZHOU Guan-gen. 1D CNN-based damage detection of truss structure[C]// Editorial Board of the Proceedings of the 20th National Symposium on Modern Structural Engineering. Proceedings of the 20th National Symposium on Modern Structural Engineering, Tianjin: Tianjin University Press, 2020: 66-69.
[30]熊青松,熊海贝,袁 程,等.基于多通道一维卷积神经网络的建筑结构损伤识别[J].振动与冲击,2024,43(24):216-224.
XIONG Qing-song, XIONG Hai-bei, YUAN Cheng, et al. Damage recognition of building structures based on multi-channel one-dimensional convolutional neural network[J].Vibration and Shock, 2024, 43(24): 216-224.

相似文献/References:

[1]李宇,朱晞,杨庆山,等.高墩大跨桥梁结构的脆弱性分析[J].长安大学学报(自然科学版),2012,32(01):0.
[2]高亮,刘健新,张丹,等.桁架桥主梁三分力系数试验[J].长安大学学报(自然科学版),2012,32(01):0.
[3]刘旭政,王丰平,黄平明,等.斜拉桥各构件校验系数的常值范围[J].长安大学学报(自然科学版),2012,32(01):0.
[4]尚维波,张春宁.高墩刚构桥系梁抗震分析[J].长安大学学报(自然科学版),2012,32(01):0.
[5]邬晓光,李冀弘,宋伟伟.基于改进响应面法的在役PC桥梁承载力可靠性[J].长安大学学报(自然科学版),2012,32(03):53.
　WU Xiao-guang,LI Ji-hong,SONG Wei-wei.Reliability of existing PC bridge based on improved response surface method[J].Journal of Chang’an University (Natural Science Edition),2012,32(2):53.
[6]石雄伟,袁卓亚,马毓泉,等.钢板-混凝土组合加固预应力混凝土箱梁[J].长安大学学报(自然科学版),2012,32(03):58.
　SHI Xiong-wei,YUAN Zhuo-ya,MA Yu-quan,et al.Prestressed concrete box girder strengthened with comsposition of steel plate and concrete[J].Journal of Chang’an University (Natural Science Edition),2012,32(2):58.
[7]李传习,陶 伟,董创文.斜交墩截面刚度与弯曲正应力[J].长安大学学报(自然科学版),2012,32(03):63.
　LI Chuan-xi,TAO Wei,DONG Chuang-wen.Sectional stiffness and bending normal stress of oblique pier[J].Journal of Chang’an University (Natural Science Edition),2012,32(2):63.
[8]邓继华,邵旭东.带铰平面梁元几何非线性有限元分析[J].长安大学学报(自然科学版),2012,32(03):68.
　DENG Ji-hua,SHAO Xu-dong.Geometric nonlinear finite element analysis of plane beam element with hinge[J].Journal of Chang’an University (Natural Science Edition),2012,32(2):68.
[9]蒲广宁,赵 煜,宋一凡.减梁增肋法加固空心板桥的力学性能[J].长安大学学报(自然科学版),2012,32(06):38.
　PU Guang-ning,ZHAO Yu,SONG Yi-fan.Mechanical properties of strengthening hollow slab bridge based on beam-reduction and rib-addition method[J].Journal of Chang’an University (Natural Science Edition),2012,32(2):38.
[10]党 栋,贺拴海,周勇军,等.基于车辆统计数据的汽车荷载标准值取值与评估[J].长安大学学报(自然科学版),2012,32(06):44.
　DANG Dong,HE Shuan-hai,ZHOU Yong-jun,et al.Choosing and assessment for the standard of vehicle load based on vehicle statistical data[J].Journal of Chang’an University (Natural Science Edition),2012,32(2):44.

备注/Memo

备注/Memo:
收稿日期:2025-08-23
基金项目:国家自然科学基金项目(52278141)
作者简介:颜东煌(1961-),男,湖南娄底人,教授,工学博士,从事大跨度桥梁的施工控制理论与应用研究,E-mail:yandonghuang@126.com。
更新日期/Last Update: 2026-04-20