Evaluation of bridge decks with overlays using impact echo, a deep learning approach

Abstract In this paper, the feasibility of using deep learning models (DLMs) for evaluation of bridges with overlay systems is investigated. Several laboratory-made concrete specimens with artificial subsurface defects and overlay systems (bonded and debonded) made of cement and asphalt overlay materials were tested using impact echo (IE). One-dimensional (1D) and two-dimensional (2D) convolutional neural networks (CNNs) were developed, trained, and tested on the IE data. The proposed 1D CNN was the most successful in detecting debonding and subsurface defects; it achieved an average accuracy of 0.68 on the cement overlay specimens and 0.58 for asphalt overlay specimens. Maps of the defects and debonding were generated using the DLMs and were compared to the conventional method for analyzing the IE data. The 1D CNN produced the most accurate defect maps while successfully detected sound, debonded, and defected regions, particularly on the specimens with cement overlay.

[1]  Dongming Zhang,et al.  Deep learning based image recognition for crack and leakage defects of metro shield tunnel , 2018, Tunnelling and Underground Space Technology.

[2]  Eric R. Burke,et al.  Segmenting delaminations in carbon fiber reinforced polymer composite CT using convolutional neural networks , 2016 .

[3]  Lina J. Karam,et al.  A Study and Comparison of Human and Deep Learning Recognition Performance under Visual Distortions , 2017, 2017 26th International Conference on Computer Communication and Networks (ICCCN).

[4]  Gaoliang Peng,et al.  A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load , 2018, Mechanical Systems and Signal Processing.

[5]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Sangwook Lee,et al.  Bridge inspection practices using non-destructive testing methods , 2015 .

[7]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[8]  Mohammad R. Jahanshahi,et al.  Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection , 2018 .

[9]  Arvin Ebrahimkhanlou,et al.  Single-sensor acoustic emission source localization in plate-like structures: a deep learning approach , 2018, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[10]  Jinyoung Kim,et al.  Method for attenuation assessment of GPR data from concrete bridge decks , 2017 .

[11]  Nenad Gucunski,et al.  Delamination and concrete quality assessment of concrete bridge decks using a fully autonomous RABIT platform , 2015 .

[12]  Jong-Myon Kim,et al.  Reliable fault diagnosis of bearings with varying rotational speeds using envelope spectrum and convolution neural networks , 2018, Soft Comput..

[13]  Tarek Zayed,et al.  Method for Analyzing Time-Series GPR Data of Concrete Bridge Decks , 2015 .

[14]  Robert J. Thomas,et al.  Fatigue Crack Detection Using Unmanned Aerial Systems in Fracture Critical Inspection of Steel Bridges , 2018, Journal of Bridge Engineering.

[15]  Oral Büyüköztürk,et al.  Autonomous Structural Visual Inspection Using Region‐Based Deep Learning for Detecting Multiple Damage Types , 2018, Comput. Aided Civ. Infrastructure Eng..

[16]  Shuicheng Yan,et al.  Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[17]  Arvin Ebrahimkhanlou,et al.  Single-Sensor Acoustic Emission Source Localization in Plate-Like Structures Using Deep Learning , 2018 .

[18]  Kincho H. Law,et al.  Automatic localization of casting defects with convolutional neural networks , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[19]  Robert J. Thomas,et al.  Benchmarking Image Processing Algorithms for Unmanned Aerial System-Assisted Crack Detection in Concrete Structures , 2019, Infrastructures.

[20]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.

[21]  Nenad Gucunski,et al.  An algorithm for automatic localization and detection of rebars from GPR data of concrete bridge decks , 2018 .

[22]  Heng Liu,et al.  Image-driven structural steel damage condition assessment method using deep learning algorithm , 2019, Measurement.

[23]  Hajin Choi,et al.  Laboratory assessment of nine methods for nondestructive evaluation of concrete bridge decks with overlays , 2018, Construction and Building Materials.

[24]  Nikolas Kalos,et al.  Bridge Inspection Practices Using Nondestructive Testing Methods for Concrete Structure , 2014 .

[25]  Young-Jin Cha,et al.  Automated air-coupled impact echo based non-destructive testing using machine learning , 2018, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[26]  Shibin Lin,et al.  Evaluation of the Impact Echo Method for Concrete Bridge Decks with Asphalt Overlays , 2019 .

[27]  Calvin Coopmans,et al.  Challenges in bridge inspection using small unmanned aerial systems: Results and lessons learned , 2017, 2017 International Conference on Unmanned Aircraft Systems (ICUAS).

[28]  Robert J. Thomas,et al.  Deep Learning Neural Networks for sUAS-Assisted Structural Inspections: Feasibility and Application , 2018, 2018 International Conference on Unmanned Aircraft Systems (ICUAS).

[29]  Parisa Shokouhi,et al.  Multi sensor data fusion approach for automatic honeycomb detection in concrete , 2015 .

[30]  Kristin J. Dana,et al.  Automated GPR Rebar Analysis for Robotic Bridge Deck Evaluation , 2016, IEEE Transactions on Cybernetics.

[31]  Lance E. Besaw,et al.  Deep convolutional neural networks for classifying GPR B-scans , 2015, Defense + Security Symposium.

[32]  Boualem Boashash,et al.  1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data , 2018, Neurocomputing.

[33]  Marc Maguire,et al.  Bridge inspection: human performance, unmanned aerial systems and automation , 2018, Journal of Civil Structural Health Monitoring.

[34]  Nicholas J. Carino,et al.  The Impact-Echo Method: An Overview , 2001 .

[35]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[36]  David Lattanzi,et al.  Review of Robotic Infrastructure Inspection Systems , 2017 .

[37]  Robert J. Thomas,et al.  Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete , 2018, Construction and Building Materials.

[38]  Miki Haseyama,et al.  Convolutional sparse coding‐based deep random vector functional link network for distress classification of road structures , 2019, Comput. Aided Civ. Infrastructure Eng..

[39]  Norbert J. Delatte,et al.  INVESTIGATING PERFORMANCE OF BONDED CONCRETE OVERLAYS , 1998 .

[40]  Salvatore Salamone,et al.  A generalizable deep learning framework for localizing and characterizing acoustic emission sources in riveted metallic panels , 2019, Mechanical Systems and Signal Processing.

[41]  Wei Li,et al.  Detection of sealed and unsealed cracks with complex backgrounds using deep convolutional neural network , 2019, Automation in Construction.