Identification of Cement Pavement Defects Based on GPR Time-Frequency Features

Zhang Jun; Jiang Wentao; Yu Qiuqin; Li Youxin; Luo Tingyi

doi:10.20174/j.JUSE.2024.04.27

Chinese Journal of Underground Space and Engineering >

2024 , Vol. 20 >Issue 4: 1334 - 1344

DOI: https://doi.org/10.20174/j.JUSE.2024.04.27

Identification of Cement Pavement Defects Based on GPR Time-Frequency Features

Zhang Jun ,
Jiang Wentao ,
Yu Qiuqin ,
Li Youxin ,
Luo Tingyi

Expand

1. Key Laboratory for Road Construction Technology and Equipment of Ministry of Education, Chang'an University, Xi'an 710064, P.R. China;
2. Gunagxi Beitou Highway Construction and Investment Group Co.,Ltd., Nanning 530028, P.R. China

Received date: 2023-09-15

Online published: 2024-09-04

Fold

Abstract

The occurrence of void defects in cement pavement is inevitable and poses a threat to the structural safety of roads. It is urgently necessary to establish an accurate positioning method for void defect areas. Ground-penetrating radar (GPR) was used as a non-destructive testing tool to extract time-frequency features from GPR signals and construct a feature dataset for void defects through forward and inverse experiments. The feature set was then subjected to PCA dimensionality reduction, and SVM and ANN models were respectively established with PCA principal components as input and normal/void output to identify voids. The window energy method was proposed to determine the depth of the void area in the GPR signal of the void. The identification of voids was verified on actual pavement surfaces. The results showed that time-frequency features could characterize void defects, and the subset of data containing parts of the defects was more suitable for modeling and identification. The recognition accuracy of ANN was superior to that of SVM, and the window energy method could effectively locate the depth of the void area and had robustness against noise. In the indoor model, the average positioning error was 1.51%. The research results provide a scientific basis for accurate maintenance of road surfaces.

Key words： road engineering; cement pavement; NDT; void recognition; GPR

Cite this article

Zhang Jun , Jiang Wentao , Yu Qiuqin , Li Youxin , Luo Tingyi . Identification of Cement Pavement Defects Based on GPR Time-Frequency Features[J]. Chinese Journal of Underground Space and Engineering, 2024 , 20(4) : 1334 -1344 . DOI: 10.20174/j.JUSE.2024.04.27

References

[1]Zhao L,Zhang J,Jiao S, et al. Ground surface detection method using ground penetrating radar signal for sugarcane harvester base-cutter control[J]. Biosystems Engineering, 2022, 219: 103-123.
[2]Xie X,Qin H,Yu C, et al. An automatic recognition algorithm for GPR images of RC structure voids[J]. Journal of Applied Geophysics, 2013, 99: 125-134.
[3]熊俊楠,孙铭,彭超, 等. 基于探地雷达的城镇燃气 PE 管道探测方法[J]. 物探与化探, 2015, 39(5): 1079-1084. (Xiong Junnan, Sun Ming, Peng Chao, et al. Detection method of urban gas PE pipeline based on ground penetrating radar[J]. Geophysical and Geochemical Exploration, 2015, 39(5): 1079-1084. (in Chinese))
[4]Liu Z,Gu X,Wu W, et al. GPR-based detection of internal cracks in asphalt pavement: a combination method of DeepAugment data and object detection[J]. Measurement, 2022, 197: 111281.1-111281.10.
[5]余秋琴,罗婷倚,杨哲, 等. 基于 GPR 信号的水泥路面脱空特征表征方法[J]. 地下空间与工程学报, 2021,17(增2):902-911. (Yu Qiuqin, Luo Tingyi, Yang Zhe, et al. Characterization method of voids in cement pavement based on GPR signal [J]. Chinese Journal of Underground Space and Engineering, 2021,17(Supp.2):902-911. (in Chinese))
[6]吴秋霜,王齐仁,皮海康. 水泥混凝土路面脱空的探地雷达图像特征分析[J]. 煤田地质与勘探, 2018, 46(4): 181-185. (Wu Qiushuang, Wang Qiren, Pi Haikang. Ground penetrating radar image feature analysis of cement concrete pavement cavitation [J]. Coal Geology & Exploration, 2018, 46(4): 181-185. (in Chinese))
[7]Zhang J,Yang X,Li W, et al. Automatic detection of moisture damages in asphalt pavements from GPR data with deep CNN and IRS method[J]. Automation in Construction, 2020, 113: 103119.
[8]Zhang J,Lu Y,Yang Z, et al. Recognition of void defects in airport runways using ground-penetrating radar and shallow CNN[J]. Automation in Construction, 2022, 138: 104260.
[9]Zhang J,Zhang C,Lu Y, et al. In-situ recognition of moisture damage in bridge deck asphalt pavement with time-frequency features of GPR signal[J]. Construction and Building Materials, 2020, 244: 118295.
[10]Li H,Li N,Wu R, et al. GPR-RCNN: an algorithm of subsurface defect detection for airport runway based on GPR[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 3001-3008.
[11]Qin H,Zhang D,Tang Y, et al. Automatic recognition of tunnel lining elements from GPR images using deep convolutional networks with data augmentation[J]. Automation in Construction, 2021, 130: 103830.
[12]Alsharahi G,Bouami M F,Faize A, et al. Contribution of analysis and detection the risks appearing in roads using GPR method: a case study in Morocco[J]. Ain Shams Engineering Journal, 2021, 12(2): 1435-1450.
[13]杜豫川,都州扬,刘成龙. 基于极限梯度提升的公路深层病害雷达识别[J]. 同济大学学报(自然科学版), 2020, 48(12): 1742-1750. (Du Yuchuan, Du Zhouyang, Liu Chenglong. Radar Recognition of highway deep diseases based on extreme gradient boosting [J]. Journal of Tongji University(Natural Science), 2020, 48(12): 1742-1750. (in Chinese))
[14]任娟娟,杜威,叶文龙, 等. 基于 PSO-SVM 的板式无砟轨道 CA 砂浆脱空损伤识别[J]. 中南大学学报 (自然科学版), 2021,52(11):4021-4031. (Ren Juanjuan, Du Wei, Ye Wenlong, et al. Identification of CA mortar void damage in slab ballastless track based on PSO-SVM [J]. Journal of Central South University (Science and Technology), 2021,52(11):4021-4031. (in Chinese))
[15]葛如冰,孟凡强. 探地雷达检测路面脱空大小的模型试验[J]. 物探与化探, 2009, 33(5): 599-602. (Ge Rubing, Meng Fanqiang. Model test of ground penetrating radar detection of road void size[J]. Geophysical and Geochemical Exploration, 2009, 33(5): 599-602. (in Chinese))
[16]张春城,周正欧. 浅地层探地雷达自动目标检测与定位研究[J]. 电子与信息学报, 2005, 27(7): 1065-1068. (Zhang Chuncheng, Zhou Zheng'ou. Research on automatic target detection and localization of shallow ground penetrating radar[J]. Journal of Electronics and Information, 2005, 27(7): 1065-1068. (in Chinese))
[17]张军,张超,陶君, 等. 一种基于探地雷达信号时频统计特征的水损害识别方法[P].中国专利:CN109782274A, 2019-05-21. (Zhang Jun, Zhang Chao, Tao Jun, et al. A water damage identification method based on time-frequency statistical characteristics of ground penetrating radar signals[P]. China Patent:CN109782274A, 2019-05-21. (in Chinese))
[18]Widyarini T,Sentosa B. Aplikasi metode cross entropy untuk support vector machines[J].Jurnal Teknik Industri,2012,10(2): 150-157.
[19]牛晓颖,邵利敏,赵志磊, 等. 基于 BP-ANN 的草莓品种近红外光谱无损鉴别方法研究[J]. 光谱学与光谱分析, 2012, 32(8): 2095-2099. (Niu Xiao-ying, Shao Limin, Zhao Zhilei, et al. Research on non-destructive identification of strawberry varieties by near-infrared spectroscopy based on BP-ANN [J]. Spectroscopy and Spectral Analysis, 2012, 32(8): 2095-2099. (in Chinese))
[20]张军,陈思茹,张子琛, 等. 基于 GPR 和 FK 法的桥面隐性病害无损检测方法[J]. 中国公路学报, 2016, 29(7): 110. (Zhang Jun, Chen Siru, Zhang Zichen, et al. Nondestructive detection method for bridge deck recessive damage based on GPR and FK methods [J]. Journal of China Highway, 2016, 29(7): 110. (in Chinese))

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References