•  
  •  
 

Abstract

To explore the intelligent detection and monitoring methods of pavement performance, this paper utilized the self-developed driving data collection app to collect vibration acceleration and other data of the pavement during driving, and carried out the feasibility study of evaluating the pavement rutting by driving vibration. Firstly, the collected vibration acceleration data was processed for noise reduction, and the driving vibration characteristics in different working conditions were analyzed. Secondly, seven time domain indicators with high correlation between vibration acceleration and the rutting were extracted as the initial set of indicators, and the seven indicators were downscaled into two independent principal components by principal component analysis. Finally, the two principal components and the speed were adopted as the evaluation indexes to build a rutting evaluation model based on convolutional neural networks (CNNs). The results show that the average absolute error of rutting evaluation conducted by the proposed method is 1.03 mm, with the average relative error of 16.4%. The built model can provide more accurate evaluation of the pavement rutting, which can provide certain references for real-time monitoring of the pavement rutting by employing big data.

Publication Date

9-14-2023

DOI

10.14048/j.issn.1671-2579.2023.04.008

First Page

45

Last Page

51

Submission Date

March 2025

Reference

[1] 崔文社, 陶晶, 张争奇, 等. 高速公路沥青路面车辙成因试验[J]. 长安大学学报(自然科学版), 2009, 29(4): 8-12. CUI Wenshe, TAO Jing, ZHANG Zhengqi, et al. Test on rut causes of expressway asphalt pavement[J]. Journal of Chang’an University (Natural Science Edition), 2009, 29(4): 8-12. [2] XU T, HUANG X M. Investigation into causes of in-place rutting in asphalt pavement[J]. Construction and Building Materials, 2012, 28(1): 525-530. [3] 马建, 赵祥模, 贺拴海, 等. 路面检测技术综述[J]. 交通运输工程学报, 2017, 17(5): 121-137. MA Jian, ZHAO Xiangmo, HE Shuanhai, et al. Review of pavement detection technology[J]. Journal of Traffic and Transportation Engineering, 2017, 17(5): 121-137. [4] 汪恩军, 陈先桥, 初秀民, 等. 车辙检测中超声测距数据采集方法[J]. 武汉理工大学学报, 2008, 30(1): 138-141. WANG Enjun, CHEN Xianqiao, CHU Xiumin, et al. Data acquisition method by ultrasonic wave distance measurement for rut detection[J]. Journal of Wuhan University of Technology, 2008, 30(1): 138-141. [5] 司永伟. 集成式多点激光路面车辙检测技术研究[D]. 西安: 长安大学, 2018. SI Yongwei. Integrated multi-point laser pavement rutting detection technology research. Xi’an: Changan University, 2018. [6] ZHANG Y, GAO T T. VC-based rutting digital imaging automatic detection technology research and design for road construction[J]. Advanced Materials Research, 2012, 461: 370-372. [7] WANG C, TAN Q, GUO R. Design and optimization of a linear laser beam[J].Lasers in Engineering,2014,27(5/6):373‑381. [8] 郎洪, 陆键, 陈圣迪, 等. 考虑病害三维特征的沥青路面车辙异常检验方法[J]. 东南大学学报(自然科学版), 2020, 50(3): 454-462. LANG Hong, LU Jian, CHEN Shengdi, et al. Asphalt pavement rutting anomaly inspection method considering 3D characteristics of distress[J]. Journal of Southeast University (Natural Science Edition), 2020, 50(3): 454-462. [9] KAGE T, MATSUSHIMA K. Method of rut detection using lasers and in-vehicle stereo camera[C]//2015 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS). Okinawa, Japan. IEEE, 2015: 48-53. [10] 王端宜, 陈颗. 智能手机在路况调查中的应用研究综述[J]. 公路工程, 2017, 42(5): 97-101. WANG Duanyi, CHEN Ke. Research review of smartphone applications in pavement condition survey[J]. Highway Engineering, 2017, 42(5): 97-101. [11] 张金喜, 王琳, 周同举, 等. 基于行车振动的路面平整度智能检测方法研究[J]. 中外公路, 2020, 40(1): 31-36. ZHANG Jinxi, WANG Lin, ZHOU Tongju, et al. Study on intelligent detection method of pavement roughness based on vibration of moving vehicles[J]. Journal of China & Foreign Highway, 2020, 40(1): 31-36. [12] ISLAM S, BUTTLAR W G, ALDUNATE R G, et al. Measurement of pavement roughness using android-based smartphone application[J]. Transportation Research Record: Journal of the Transportation Research Board, 2014, 2457(1): 30-38. [13] WANG H J, HUO N, LI J H, et al. A road quality detection method based on the mahalanobis-taguchi system[J]. IEEE Access, 2018, 6: 29078-29087. [14] SOUZA V M A, GIUSTI R, BATISTA A J L. Asfault: a low-cost system to evaluate pavement conditions in real-time using smartphones and machine learning[J]. Pervasive and Mobile Computing, 2018, 51: 121-137. [15] 王琳.基于行车数据的路面性能智能识别方法研究[D].北京：北京工业大学，2019. WANG Lin. Research on intelligent identification method of pavement performance based on travelling data [D]. Beijing: Beijing Institute of Technology, 2019. [16] 李明鑫, 吴定祥, 唐立军. 卡尔曼滤波在电梯振动检测中的应用[J]. 单片机与嵌入式系统应用, 2019, 19(8): 57-59+64. LI Mingxin, WU Dingxiang, TANG Lijun. Application of Kalman filter in elevator vibration detection[J]. Microcontrollers & Embedded Systems, 2019, 19(8): 57-59+64. [17] 陈雨人, 付云天, 汪凡. 基于支持向量回归的视距计算模型建立和应用[J]. 中国公路学报, 2018, 31(4): 105-113. CHEN Yuren, FU Yuntian, WANG Fan. Establishment and application of sight distance computing model based on support vector regression[J]. China Journal of Highway and Transport, 2018, 31(4): 105-113. [18] 胡宏宇, 刘家瑞, 高菲, 等. 基于一维卷积神经网络的驾驶人身份识别方法[J]. 中国公路学报, 2020, 33(8): 195-203. HU Hongyu, LIU Jiarui, GAO Fei, et al. Driver identification based on 1-D convolutional neural networks[J]. China Journal of Highway and Transport, 2020, 33(8): 195-203. [19] KIRANYAZ S, ZABIHI M, RAD A B, et al. Real-time phonocardiogram anomaly detection by adaptive 1D Convolutional Neural Networks[J]. Neurocomputing, 2020, 411: 291-301.

Download

Share

COinS