An Inversion Algorithm for the Dynamic Modulus of Concrete Pavement Structures Based on a Convolutional Neural Network

被引:3
|
作者
Chen, Gongfa [1 ]
Chen, Xuedi [1 ]
Yang, Linqing [2 ,3 ]
Han, Zejun [2 ]
Bassir, David [4 ,5 ]
机构
[1] Guangdong Univ Technol, Sch Civil & Transportat Engn, Guangzhou 510006, Peoples R China
[2] Sun Yat Sen Univ, Sch Civil Engn, Guangzhou 510275, Peoples R China
[3] Guangzhou Inst Sci & Technol, Sch Architectural Engn, Guangzhou 510540, Peoples R China
[4] Univ Paris Saclay, Ctr Borelli, ENS, F-91190 Gif sur yvette, France
[5] UTBM, IRAMAT, CNRS, UMR 7065, Rue Leupe, F-90010 Belfort, France
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 02期
关键词
pavement structure; dynamic modulus; convolution neural network; inversion algorithm; falling weight deflectometer; EFFICIENT PARAMETER-IDENTIFICATION; SPECTRAL ELEMENT TECHNIQUE; GREENS-FUNCTIONS; LAYERED MEDIA; SIMULATION; TESTS; MODEL;
D O I
10.3390/app13021192
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Based on the spectral element method (SEM) and a convolutional neural network (CNN), an inversion algorithm for the dynamic modulus of concrete pavement structures is proposed in this paper. In order to evaluate the service performance of pavement structures more systematically and accurately via the existing testing techniques using a falling weight deflectometer (FWD), it is necessary to obtain accurate dynamic modulus parameters of the structures. In this work, an inversion algorithm for predicting the dynamic modulus is established by using a CNN which is trained with the dynamic response samples of a multi-layered concrete pavement structure obtained through SEM. The gradient descent method is used to adjust the weight parameters in the network layer by layer in reverse. As a result, the accuracy of the CNN can be improved via iterative training. With the proposed algorithm, more accurate results of the dynamic modulus of pavement structures are obtained. The accuracy and numerical stability of the proposed algorithm are verified by several numerical examples. The dynamic modulus and thickness of concrete pavement structure layers can be accurately predicted by the CNN trained with a certain number of training samples based on the displacement curve of the deflection basin from the falling weight deflectometer. The proposed method can provide a reliable testing tool for the FWD technique of pavement structures.
引用
收藏
页数:18
相关论文
共 50 条
  • [31] Convolutional neural network for pothole detection in asphalt pavement
    Ye, Wanli
    Jiang, Wei
    Tong, Zheng
    Yuan, Dongdong
    Xiao, Jingjing
    ROAD MATERIALS AND PAVEMENT DESIGN, 2021, 22 (01) : 42 - 58
  • [32] Asphalt Pavement Crack Detection Based on Convolutional Neural Network and Infrared Thermography
    Liu, Fangyu
    Liu, Jian
    Wang, Linbing
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (11) : 22145 - 22155
  • [33] Intelligent Detection Model Based on a Fully Convolutional Neural Network for Pavement Cracks
    Ma, Duo
    Fang, Hongyuan
    Xue, Binghan
    Wang, Fuming
    Msekh, Mohammed A.
    Chan, Chiu Ling
    CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES, 2020, 123 (03): : 1267 - 1291
  • [34] Surface Crack Detection using Deep Convolutional Neural Network in Concrete Structures
    Rahai, Alireza
    Rahai, Mohammad
    Iraniparast, Mostafa
    Ghatee, Mehdi
    2022 IEEE 5TH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING APPLICATIONS AND SYSTEMS, IPAS, 2022,
  • [35] A fast inversion method for array laterolog based on convolutional neural network and hybrid MPGA-LM algorithm
    Wu YiZhi
    Fan YiRen
    Wu ZhenGuan
    Deng ShaoGui
    Zhang Pan
    Chen ShiYu
    Yin ZhongXu
    CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION, 2021, 64 (09): : 3410 - 3425
  • [36] Inversion Restoring Algorithm for Whiskbroom Scanning Images Synthesized with Deep Convolutional Neural Network
    Xu Chao
    Jin Guang
    Yang Xiubin
    Xu Tingting
    Chang Lin
    ACTA OPTICA SINICA, 2019, 39 (12)
  • [37] Convolutional Neural Network-Based Pavement Crack Segmentation Using Pyramid Attention Network
    Wang, Wenjun
    Su, Chao
    IEEE ACCESS, 2020, 8 : 206548 - 206558
  • [38] Zoning Modulus Inversion Method for Concrete Dams Based on Chaos Genetic Optimization Algorithm
    Gu, Hao
    Wu, Zhongru
    Huang, Xiaofei
    Song, Jintao
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2015, 2015
  • [39] CRACK DETECTION IN HISTORICAL STRUCTURES BASED ON CONVOLUTIONAL NEURAL NETWORK
    Chaiyasarn, Krisada
    Sharma, Mayank
    Ali, Luqman
    Khan, Wasif
    Poovarodom, Nakhon
    INTERNATIONAL JOURNAL OF GEOMATE, 2018, 15 (51): : 240 - 251
  • [40] Tree Crown Delineation Algorithm Based on a Convolutional Neural Network
    Braga, Jose R. G.
    Peripato, Vinicius
    Dalagnol, Ricardo
    Ferreira, Matheus P.
    Tarabalka, Yuliya
    Aragao, Luiz E. O. C.
    de Campos Velho, Haroldo E.
    Shiguemori, Elcio H.
    Wagner, Fabien H.
    REMOTE SENSING, 2020, 12 (08)