•  
  •  
 

Abstract

To effectively identify the damage degree of concrete bridge structures and timely evaluate the structural state, this paper conducted damage model experiments on partially prestressed concrete cable-stayed bridges based on convolutional neural networks (CNNs). By analyzing the acoustic emission waveform signals of the test beams under different damage states, CNN was adopted to identify and predict the degree of damage to the test beams. Firstly, a CNN architecture consisting of convolutional layers, pooling layers, fully connected layers, and a SoftMax layer was constructed. Then, the test beam was loaded to the limit state for three times in stages to obtain three sets of acoustic emission waveform signals in the same loading conditions. Meanwhile, the first two sets of acoustic emission signals were input into the previously built CNN model and trained to obtain a CNN identification system. The third set of acoustic emission signals was employed by the identification system to predict the damage state of the test beam, thus verifying the effectiveness of the identification method. The results show that the damage degree of the test beam is successfully predicted based on CNN and acoustic emission technology, with the comprehensive accuracy of 96.71% for 3104 acoustic emission signals. The network architecture with two convolutional layers and two fully connected layers has the optimal prediction performance. Additionally, compared to traditional BP neural networks, the accuracy of CNN is 5%-10% higher.

Publication Date

8-18-2022

DOI

10.14048/j.issn.1671-2579.2022.04.012

First Page

69

Last Page

75

Submission Date

May 2025

Reference

[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. [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] MAYUNGA S D, BAKAONE M. Dynamic deformation monitoring of lotsane bridge using global positioning systems (GPS) and linear variable differential transducers (LVDT)[J]. Journal of Data Analysis and Information Processing, 2021, 9(1): 30-50. [5] AL-SALIH H, JUNO M, COLLINS W, et al. Evaluation of a digital image correlation bridge inspection methodology on complex distortion-induced fatigue cracking[J]. Procedia Structural Integrity, 2019, 17: 682-689. [6] CHEN G F, LIANG Q, ZHONG W T, et al. Homography-based measurement of bridge vibration using UAV and DIC method[J]. Measurement, 2021, 170: 108683. [7] ANAY R, LANE A, JÁUREGUI D 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(3). [8] ROYLESR.Acoustic Emission Monitoring of Masonry Arch Bridges British[J].Journal of Non-Destructive Testing,1991,33(7):339-343. [9] HICKH,WILIERIF,WinterE,etal.Acoustic Emission Measurements on Bridges[J].Journal of Acoustic Emission,1992,10(3-4):67-70. [10] AMIR Nasrollahi,DENG Wen,MA Zhaoyun,et al. Multimodal Structural Health Monitoring Based on Active and Passive Sensing[J].Structural Health Monitoring,2018,17(2):395-409. [11] KIM Y M, HAN G, KIM H, et al. An integrated approach to real-time acoustic emission damage source localization in piled raft foundations[J]. Applied Sciences, 2020, 10(23): 8727. [12] TONELLI D, LUCHETTA M, ROSSI F, et al. Structural health monitoring based on acoustic emissions: validation on a prestressed concrete bridge tested to failure[J]. Sensors, 2020, 20(24): 7272. [14] 袁明, 黄练, 彭卓, 等. 基于声发射技术的混凝土梁桥弯剪受力状态下损伤试验[J]. 长安大学学报(自然科学版), 2019, 39(2): 73-81. YUAN Ming, HUANG Lian, PENG Zhuo, et al. Experimental investigation of static damage of concrete beam under bending-shear based on acoustic emission technology[J]. Journal of Chang’an University (Natural Science Edition), 2019, 39(2): 73-81. [15] 陈兵, 姚武, 吴科如. 声发射技术在混凝土研究中的应用[J]. 无损检测, 2000, 22(9): 387-390, 396. CHEN Bing, YAO Wu, WU Keru. Application of acoustic emission technique to the study of concrete[J]. Nonde Structive Testing, 2000, 22(9): 387-390, 396. [16] LIEBOLDF,MAAS H G.Strategy for Crack Width Measurement of Multile Crack atterns in Civil Engineering Material Testing Using a Monocular Image Sequence Analysis[J].FG-Journal of hoto grammetry, Remote Sensing and Geo in formation Science,2020,88 (3-4):1-20. [17] CASTORENA-GONZÁLEZ J H, MARTIN U, GAONA-TIBURCIO C, et al. Modeling steel corrosion failure in reinforced concrete by cover crack width 3D FEM analysis[J]. Frontiers in Materials, 2020, 7: 41. [18] NOGALES A, DE LA FUENTE A. Crack width design approach for fibre reinforced concrete tunnel segments for TBM thrust loads[J]. Tunnelling and Underground Space Technology, 2020, 98: 103342. [19] ISLAMA. B. M. Saiful. Computer Aided Failure Prediction of Reinforced Concrete Beam[J].Computers and Concrete,2020,25(1):67-73. [20] 王岩, 张友桃, 胡鸿翔, 等. 基于声发射和人工神经网络的混凝土损伤程度识别[J]. 建筑材料学报, 2014, 17(4): 672-676. WANG Yan, ZHANG Youtao, HU Hongxiang, et al. Identification of damage degree of concrete by acoustic emission and artificial neural network[J]. Journal of Building Materials, 2014, 17(4): 672-676. [21] 张瑞程, 王新颖, 胡磊磊, 等. 基于一维卷积神经网络的燃气管道泄漏声发射信号识别[J]. 中国安全生产科学技术, 2021, 17(2): 104-109. [22] 董靖川, 徐明达, 王太勇, 等. 分布式卷积神经网络在刀具磨损量预测中的应用[J]. 机械科学与技术, 2020, 39(3): 329-335.DONG Jingchuan, XU Mingda, WANG Taiyong, et al. Application of distributed convolutional neural network in wear prediction of tool[J]. Mechanical Science and Technology for Aerospace Engineering, 2020, 39(3): 329-335. [23] SARRAFI A, MAO Z, NIEZRECKI C, et al. Vibration-based damage detection in wind turbine blades using Phase-based Motion Estimation and motion magnification[J]. Journal of Sound and Vibration, 2018, 421: 300-318. [24] SARRAFI Aral,ZHU Mao.Structural Oerating Deflection Shae Estimation via a Hybrid Computer-Vision Algorithm[].Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring,2018. [25] MOHAMMADI-GHAZI R, MARZOUK Y M, BÜYÜKÖZTÜRK O. Conditional classifiers and boosted conditional Gaussian mixture model for novelty detection[J]. Pattern Recognition, 2018, 81: 601-614. [26] GRIFFEL D H. Ten lectures on wavelets, by ingrid daubechies. pp 357. $37.50.1992. ISBN 0-89871-274-2 (SIAM)[J]. The Mathematical Gazette, 1995, 79(484): 224-227. [27] DAVIDF. Walnut. An Introduction to Wavelet Analysis [M].Birkhäuser,Boston,MA,2004. [28] 卢绍鸿. 广州南二环李家沙大桥设计[J]. 公路工程, 2013, 38(4): 137-139, 182.LU Shaohong. The design of Li Jiasha bridge in second south ring road of Guangzhou[J]. Highway Engineering, 2013, 38(4): 137-139, 182. [29] 刘昀, 颜东煌. 部分预应力混凝土斜拉桥设计的合理性分析[J]. 中外公路, 2015, 35(2): 83-86. LIU Yun, YAN Donghuang. Rationality analysis of partially prestressed concrete cable-stayed bridge design[J]. Journal of China & Foreign Highway, 2015, 35(2): 83-86. [30] 颜东煌, 邹恺为, 袁明, 等. 采用PPC设计的斜拉桥模型疲劳试验研究[J]. 中外公路, 2021, 41(1): 59-63. YAN Donghuang, ZOU Kaiwei, YUAN Ming, et al. Experimental research on fatigue model of PPC cable-stayed bridges[J]. Journal of China & Foreign Highway, 2021, 41(1): 59-63. [31] 吴胜兴, 王岩, 李佳, 等. 混凝土静态轴拉声发射试验相关参数研究[J]. 振动与冲击, 2011, 30(5): 196-204.WU Shengxing, WANG Yan, LI Jia, et al. Parameters of acoustic emission test of concrete under static uniaxial tension[J]. Journal of Vibration and Shock, 2011, 30(5): 196-204.

Download

Share

COinS