基于G-S-G的混凝土结构裂缝识别及监测方法

李可心1,王钧1,戚大伟2

振动与冲击 ›› 2020, Vol. 39 ›› Issue (11) : 101-108.

PDF(1806 KB)
PDF(1806 KB)
振动与冲击 ›› 2020, Vol. 39 ›› Issue (11) : 101-108.
论文

基于G-S-G的混凝土结构裂缝识别及监测方法

  • 李可心1,王钧1,戚大伟2
作者信息 +

Research on crack identification and monitoring method of concrete structure based on G-S-G

  • LI Kexin1, WANG Jun1, QI Dawei2
Author information +
文章历史 +

摘要

为解决复杂约束条件下现代混凝土结构裂缝的精准监测问题,提出基于G-S-G混凝土结构裂缝智能识别及监测方法。将灰度共生矩阵理论(GLCM)和自组织特征映射神经网络(SOM)模型结合,并通过数字图像处理技术(DIP)及数字特征筛选法(DFS)辅助分析,研究提高混凝土结构裂缝识别及监测精度的智能方法;并基于工程实例(柱的偏心受压试验),验证方法的可行性及准确性。结果表明,在有限的样本空间下,基于GLCM-SOM的裂缝识别模型,通过构建的标准特征样本集(角二阶矩(ASM)、熵(ENT)等)排除环境因素及孔洞、凹陷等缺陷的干扰,获得较高的识别精度;基于SOM-GLCM的裂缝监测数据显示,筛选出的相关(COR)和聚类阴影(CLS)损伤特性指标与裂缝的发展情况具有良好的线性关系,可作为裂缝延展趋势的敏感特性指标。提出的G-S-G裂缝检测方法,充分结合GLCM与SOM各自的独特优势,建立起精准识别裂缝损伤的网络模型,并对裂缝的发展趋势进行有效监测。研究有助于实现现代混凝土结构裂缝损伤的高精度智能化健康监测。

Abstract

In order to solve the problem of accurate monitoring of cracks in modern concrete structures under complex constraints, an intelligent monitoring method for cracks in concrete structures based on G-S-G is proposed. Combining the gray level co-occurrence matrix theory (GLCM) and the self-organizing feature mapping neural network (SOM) model, and through the digital image processing technology (DIP) and digital feature screening (DFS) analysis to study the intelligent methods that can improve the crack identification and monitoring accuracy of concrete structures. The feasibility and accuracy of the method are verified by the eccentric compression test of the column. The results show that under the limited sample space, the crack identification model based on GLCM-SOM can eliminate the interference of environmental factors and defects such as holes and depressions through the construction of six standard feature samples (P1-P6 in Tab.1).Therefore, obtaining higher recognition accuracy. The crack monitoring data based on SOM-GLCM shows that the selected damage characteristics index has a good linear relationship with the development of cracks (as shown in Fig.12). Therefore, COR and CLS can be used as sensitive indicators of crack propagation trends. The proposed G-S-G method fully combines the unique advantages of GLCM and SOM to establish a network model for accurately identifying crack damage and effectively monitor the development trend of cracks. This research process can help to achieve high-precision and intelligent health monitoring of crack damage in modern concrete structures.

关键词

结构损伤检测 / 数字图像处理 / 自组织特征映射神经网络 / 灰度共生矩阵 / 损伤指标 / 裂缝监测

Key words

structural damage detection / digital image processing / self-organization map / gray level co-occurrence matrix / damage index / crack monitoring

引用本文

导出引用
李可心1,王钧1,戚大伟2. 基于G-S-G的混凝土结构裂缝识别及监测方法[J]. 振动与冲击, 2020, 39(11): 101-108
LI Kexin1, WANG Jun1, QI Dawei2. Research on crack identification and monitoring method of concrete structure based on G-S-G[J]. Journal of Vibration and Shock, 2020, 39(11): 101-108

参考文献

[1]  徐秀丽,张勇,李雪红,李枝军,张建东.基于声发射和深度置信网络的钢筋混凝土梁损伤识别方法研究[J].建筑结构学报,2018,39(S2):400-407.
XU Xiuli,ZHANG Yong,et al..Study on damage identification method of reinforced concrete beam based on acoustic emission and deep belief nets[J].Journal of Building Structures,2018,39(S2):400-407.
[2]  项贻强,郏亚坤.基于小波总能量相对变化的结构损伤识别[J].振动与冲击,2017,36(14):38-44.
XIANG Yiqiang, JIA Yakun. Damage detection method for structures based on the relative variation of wavelet total energy [J]. JOURNAL OF VIBRATION AND SHOCK, ,2017,36(14):38-44.
[3] 王耀东,朱力强,史红梅,方恩权,杨玲芝.基于局部图像纹理计算的隧道裂缝视觉检测技术[J].铁道学报,2018,40(02):82-90.
Wang Yaodong,Zhu Liang,et al.Vision detection of tunnel cracks based on loca image texture calculation[J].铁道学报,2018,40(02):82-90.
[4]  李胜利,石鸿帅,毋光明,王东炜.声发射技术在混凝土空心板桥裂缝检测中的应用[J].桥梁建设,2017,47(05):83-88.
Li Shengli,Shi Hongshuai,et al.Application of acoustic emission technique to crack detection of concrete hollow slab bridges[J].Bridge construction,2017,47(05):83-88.
[5]  李雪松,马宏伟,林逸洲.基于卷积神经网络的结构损伤识别[J].振动与冲击,2019,38(01):159-167.
LI Xuesong, MA Hongwei, et al. Structural damage identification based on convolution neural network, JOURNAL OF VIBRATION AND SHOCK, 2019, 38(01):159-167.
[6]  Bao Y , Tang Z , Li H , et al. Computer vision and deep learning–based data anomaly detection method for structural health monitoring[J]. Structural Health Monitoring: An International Journal, 2018:147592171875740.
[7]  Amezquita-Sanchez J P, Adeli H . Signal Processing Techniques for Vibration-Based Health Monitoring of Smart Structures [J]. Archives of Computational Methods in Engineering, 2016, 23(1):1-15.
[8]  Feng D , Feng M Q . Experimental validation of cost-effective vision-based structural health monitoring [J]. Mechanical Systems and Signal Processing, 2017, 88:199-211.
[9]  Frangopol D M , Soliman M . Life-cycle of structural systems: recent achievements and future directions [J]. Structure and Infrastructure Engineering, 2015:1-20.
[10] Qingzhao K , Rachel R , Pedro S , et al. Cyclic Crack Monitoring of a Reinforced Concrete Column under Simulated Pseudo-Dynamic Loading Using Piezoceramic-Based Smart Aggregates[J]. Applied Sciences, 2016, 6(11):341-345.
[11] Cha Y J, Choi W, Büyüküztürk, Oral. Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks [J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5):361-370
[12]  韩晓健,赵志成.基于计算机视觉技术的结构表面裂缝检测方法研究[J].建筑结构学报,2018,39(S1):418-427.
HAN Xiaojian,ZHAO Zhicheng,Structural surface crack detection method based on computer vision technology [J].Journal of Building Structures,2018,39(S1):418-427.
[13] Chen J H, Su M C, Cao R , et al. A self organizing map optimization based image recognition and processing model for bridge crack inspection [J]. Automation in Construction, 2016:S092658051630187X.
[14] Hyun-Woo C, Hyuk-Jin Y, Jae-Chan Y. Analysis of Crack Image Recognition Characteristics in Concrete Structures Depending on the Illumination and Image Acquisition Distance through Outdoor Experiments [J]. Sensors, 2016, 16(10):1646-1650.
[15] Baoxian W, Weigang Z , Po G , et al. Crack Damage Detection Method via Multiple Visual Features and Efficient Multi-Task Learning Model[J]. Sensors, 2018, 18(6):1796-1799.
[16] 张强,顾颉颖,刘峻铭,刘志恒,田莹.基于小波包与SOM神经网络的截齿磨损状态识别[J].煤炭学报,2018,43(07):2077-2083.
ZHANG Qiang,GU Jieying, et al. Pick wear condition identification based on wavelet packet and SOM neural network [J].Journal of China coal society, 2018, 43(07):2077-2083.
[17] 张西宁,雷威,唐春华,向宙.一种基于分子结构设计理论的聚类分析方法[J].振动与冲击,2018,37(15):78-83+103.
ZHANG Xining, LEI Wei , et al. A clustering analysis method based on theory of molecular structure design [J]. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(15):78-83+103.

PDF(1806 KB)

Accesses

Citation

Detail

段落导航
相关文章

/