Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Fully automated natural frequency identification based on deep-learning-enhanced computer vision and power spectral density transmissibility

Fully automated natural frequency identification based on deep-learning-enhanced computer vision... As image acquisition devices have outstanding potential for gathering vibration information, computer vision has received a lot of interest in structural health monitoring (SHM). In this work, a fully automated peak picking methodology based on computer vision in tandem with deep learning is proposed to realize vibration measurements and identify natural frequencies from the plot of the power spectral density transmissibility (PSDT). A deep-learning-enhanced image processing technology was used to extract the vibration signals with automatic active pixel selection, while a convolutional neural network was used to further process the vibration measurements so that the frequencies could be identified from PSDT-based functions. The proposed method was verified by three case studies, including the dynamic testing of two laboratory models and the field testing of the stay cable. The findings showed that the proposed deep-learning-enhanced approach has a high potential for use in SHM by automatically performing vibration measurement and frequency extraction. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Advances in Structural Engineering SAGE

Fully automated natural frequency identification based on deep-learning-enhanced computer vision and power spectral density transmissibility

Download PDF
16 pages

Loading next page...
 
/lp/sage/fully-automated-natural-frequency-identification-based-on-deep-1jbud7JTQN
Publisher
SAGE
Copyright
© The Author(s) 2022
ISSN
1369-4332
eISSN
2048-4011
DOI
10.1177/13694332221107572
Publisher site
See Article on Publisher Site

Abstract

As image acquisition devices have outstanding potential for gathering vibration information, computer vision has received a lot of interest in structural health monitoring (SHM). In this work, a fully automated peak picking methodology based on computer vision in tandem with deep learning is proposed to realize vibration measurements and identify natural frequencies from the plot of the power spectral density transmissibility (PSDT). A deep-learning-enhanced image processing technology was used to extract the vibration signals with automatic active pixel selection, while a convolutional neural network was used to further process the vibration measurements so that the frequencies could be identified from PSDT-based functions. The proposed method was verified by three case studies, including the dynamic testing of two laboratory models and the field testing of the stay cable. The findings showed that the proposed deep-learning-enhanced approach has a high potential for use in SHM by automatically performing vibration measurement and frequency extraction.

Journal

Advances in Structural Engineering – SAGE

Published: Oct 1, 2022

Keywords: optical flow; vibration measurement; computer vision; automated peak picking; deep learning

References

  • Review of optical flow technique for moving object detection
    Agarwal, A; Gupta, S; Singh, DK
  • Contour detection and hierarchical image segmentation
    Arbeláez, P; Maire, M; Fowlkes, C
  • Optical flow based moving object detection and tracking for traffic surveillance
    Aslani, S; Mahdavinasab, H
  • Photogrammetry and optical methods in structural dynamics – A review
    Baqersad, J; Poozesh, P; Niezrecki, C
  • Deep learning-based crack damage detection using convolutional neural networks
    Cha, Y-J; Choi, W; Büyüköztürk, O
  • Two-stage automated operational modal analysis based on power spectrum density transmissibility and support-vector machines
    Chen, Z-W; Liu, K-M; Yan, W-J
  • Optical symbolic substitution: edge detection using Prewitt, Sobel, and Roberts operators
    Cherri, AK; Karim, MA
  • Bayesian analysis of the phase II IASC-ASCE structural health monitoring experimental Benchmark data
    Ching, J; Beck, JL
  • Development of an automated wireless tension force estimation system for cable-stayed bridges
    Cho, S; Lynch, JP; Lee, J-J
  • A novel evolutionary algorithm inspired by the states of matter for template matching
    Cuevas, E; Echavarría, A; Zaldívar, D
  • The use of transmissibility measurements in output-only modal analysis
    Devriendt, C; Guillaume, P
  • Accuracy evaluation of sub-pixel structural vibration measurements through optical flow analysis of a video sequence
    Diamond, DH; Heyns, PS; Oberholster, AJ
  • On the canny edge detector
    Ding, L; Goshtasby, A
  • A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks
    Dung, CV; Sekiya, H; Hirano, S
  • A vision-based sensor for noncontact structural displacement measurement
    Feng, D; Feng, M; Ozer, E
  • Kiwifruit detection in field images using Faster R-CNN with ZFNet
    Fu, L; Feng, Y; Majeed, Y
  • Non-contact vibration sensor using deep learning and image processing
    Guo, J; Wu, X; Liu, J
  • Markers tracking and extracting structural vibration utilizing randomized hough transform
    Havaran, A; Mahmoudi, M
  • 3D digital image correlation methods for full-field vibration measurement
    Helfrick, MN; Niezrecki, C; Avitabile, P
  • Automated wireless monitoring system for cable tension forces using deep learning
    Jeong, S; Kim, H; Lee, J
  • Nontarget image-based technique for small cable vibration measurement
    Ji, YF; Chang, CC
  • Fully automated peak-picking method for an autonomous stay-cable monitoring system in cable-stayed bridges
    Jin, S-S; Jeong, S; Sim, S-H
  • Field measurements for identification of modal parameters for high-rise buildings under construction or in use
    Kim, D; Kim, M; Bae, SG
  • Automated peak picking using region-based convolutional neural network for operational modal analysis
    Kim, H; Sim, SH
  • Wireless health monitoring of stay cable using piezoelectric strain response and smart skin technique
    Kim, J-T; Nguyen, K-D; Huynh, T-C
  • ImageNet classification with deep convolutional neural networks
    Krizhevsky, A; Sutskever, I; Hinton, GE
  • Integrating multi-level deep learning and concept ontology for large-scale visual recognition
    Kuang, Z; Yu, J; Li, Z
  • Target-free vision-based technique for vibration measurements of structures subjected to out-of-plane movements
    Kuddus, MA; Li, J; Hao, H
  • Intelligent wireless sensors with application to the identification of structural modal parameters and steel cable forces: from the lab to the field
    Lei, Y; Shen, WA; Song, Y
  • Structural damage identification with power spectral density transmissibility: numerical and experimental studies
    Li, J; Hao, H; Lo, JV
  • Classifying high resolution remote sensing images by fine-tuned VGG deep networks
    Liu, X; Chi, M; Zhang, Y
  • A hybrid Rao-NM algorithm for image template matching
    Liu, X; Wang, Z; Wang, L
  • Learning relaxed deep supervision for better edge detection
    Liu, Y; Lew, M
  • Output-only modal parameter identification of structures by vision modal analysis
    Lu, Z-R; Lin, G; Wang, L
  • An architecture for real-time hardware co-simulation of edge detection in image processing using Prewitt edge operator
    Nguyen, PML; Cho, JH; Cho, SB
  • Real-time structural health monitoring of a supertall building under construction based on visual modal identification strategy
    Park, HS; Oh, BK
  • Structural damage identification based on autoencoder neural networks and deep learning
    Pathirage, CSN; Li, J; Li, L
  • Reference-based stochastic subspace identification for output-only modal analysis
    Peeters, B; De Roeck, G
  • The PolyMAX frequency-domain method: a new standard for modal parameter estimation?
    Peeters, B; Van der Auweraer, H; Guillaume, P
  • Comparative study of modal analysis techniques for bridge dynamic characteristics
    Peeters, B; Ventura, CE
  • Remote sensing of building structural displacements using a microwave interferometer with imaging capability
    Pieraccini, M; Luzi, G; Mecatti, D
  • Comparison of DIC and LDV for practical vibration and modal measurements
    Reu, P; Rohe, D; Jacobs, L
  • Computer vision based target-free 3D vibration displacement measurement of structures
    Shao, Y; Li, L; Li, J
  • DeepContour: a deep convolutional feature learned by positive-sharing loss for contour detection
    Shen, W; Wang, X; Wang, Y
  • Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
    Shi, W; Caballero, J; Huszár, F
  • A comparison of various edge detection techniques used in image processing
    Shrivakshan, GT; Chandrasekar, C
  • Vibration displacement measurement technology for cylindrical structures using camera images
    Son, K-S; Jeon, H-S; Park, J-H
  • Going deeper with convolutions
    Szegedy, C; Liu, W; Jia, Y
  • Remote bridge deflection measurement using an advanced video deflectometer and actively illuminated LED targets
    Tian, L; Pan, B
  • Deep crisp boundaries
    Wang, Y; Zhao, X; Huang, K
  • Wider or deeper: revisiting the ResNet model for visual recognition
    Wu, Z; Shen, C; van den Hengel, A
  • Holistically-nested edge detection
    Xie, S; Tu, Z
  • Time-varying system identification by enhanced empirical wavelet transform based on synchroextracting transform
    Xin, Y; Hao, H; Li, J
  • Operational modal parameter identification from power spectrum density transmissibility
    Yan, W-J; Ren, W-X
  • An enhanced power spectral density transmissibility (EPSDT) approach for operational modal analysis: theoretical and experimental investigation
    Yan, W-J; Ren, W-X
  • Automated eigensystem realization algorithm for operational modal identification of bridge structures
    Yang, X-M; Yi, T-H; Qu, C-X
  • Image-based structural dynamic displacement measurement using different multi-object tracking algorithms
    Ye, XW; Dong, CZ; Liu, T
  • A review of machine vision-based structural health monitoring: methodologies and applications
    Ye, XW; Dong, CZ; Liu, T
  • A vision-based system for dynamic displacement measurement of long-span bridges: algorithm and verification
    Ye, XW; Ni, YQ; Wai, TT
  • Single-camera high-speed stereo-digital image correlation for full-field vibration measurement
    Yu, L; Pan, B