Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Nondestructive Damage Detection of Concrete With Alkali-Silica Reactions Using Coda Wave and Anomaly Detection

Journal Article · · IEEE Sensors Journal
 [1]; ORCiD logo [2]; ORCiD logo [1]; ORCiD logo [3]
  1. Georgia Institute of Technology, Atlanta, GA (United States)
  2. Univ. of Nebraska-Lincoln, Omaha, NE (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  3. Univ. of Nebraska-Lincoln, Omaha, NE (United States)
+ Show Author Affiliations

An anomaly detection model for early damage detection for concrete structures undergoing alkali-silica reaction (ASR) is presented. It is difficult to detect ASR initiation and early damage without a reference expansion measurement. Coda waves, or the multiply scattered portion of ultrasonic waves, have been found to be indicative of small changes in complex material such as concrete. The relationship between concrete damage and relative velocity change and decorrelation of coda waves has been studied, but a generalized model which detects when damage occurs in a concrete structure is still lacking. The presented method uses features extracted from coda waves to detect early damage in concrete structures. The model uses unsupervised learning and only requires data from undamaged structures for training. During the training process, the reconstruction error of the training data is minimized. When the data collected from damaged concrete structures is used as an input of the model, it returns high reconstruction errors that indicate the occurrence of damage in the structures. The performance of the model is validated using experimental studies and has been shown to generalize across two different ASR specimens.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE Office of Nuclear Energy (NE), Nuclear Energy University Program (NEUP)
Grant/Contract Number:
AC05-00OR22725; NE0008544
OSTI ID:
1864407
Journal Information:
IEEE Sensors Journal, Journal Name: IEEE Sensors Journal Journal Issue: 6 Vol. 22; ISSN 1530-437X
Publisher:
IEEECopyright Statement
Country of Publication:
United States
Language:
English

References (25)

Anomaly detection by robust statistics journal November 2017
Anomaly detection of defects on concrete structures with the convolutional autoencoder journal August 2020
Speech emotion recognition using deep 1D & 2D CNN LSTM networks journal January 2019
A review of ultrasonic Coda Wave Interferometry in concrete journal November 2013
The effective use of the one-class SVM classifier for handwritten signature verification based on writer-independent parameters journal January 2015
Study of stress-induced velocity variation in concrete under direct tensile force and monitoring of the damage level by using thermally-compensated Coda Wave Interferometry journal December 2012
Tracking fluids in multiple scattering and highly porous materials: Toward applications in non-destructive testing and seismic monitoring journal March 2020
Origin of coda waves: Source, attenuation, and scattering effects journal August 1975
Expansion of Concrete through Reaction between Cement and Aggregate journal January 1942
Locating a small change in a multiple scattering environment journal May 2010
Sensitivity kernels for coda-wave interferometry and scattering tomography: theory and numerical evaluation in two-dimensional anisotropically scattering media journal December 2015
Coda-Wave Interferometry in Finite Solids: Recovery of P -to- S Conversion Rates in an Elastodynamic Billiard journal June 2003
Gold Price Forecast Based on LSTM-CNN Model
  • He, Zhanhong; Zhou, Junhao; Dai, Hong-Ning
  • 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) https://doi.org/10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00188
conference August 2019
Wind Turbine Fault Detection Using a Denoising Autoencoder With Temporal Information journal February 2018
Semisupervised learning using denoising autoencoders for brain lesion detection and segmentation journal October 2017
Monitoring stress related velocity variation in concrete with a 2×10−5 relative resolution using diffuse ultrasound journal April 2009
Stability of monitoring weak changes in multiply scattering media with ambient noise correlation: Laboratory experiments journal June 2009
Imaging multiple local changes in heterogeneous media with diffuse waves journal February 2015
Diffuse ultrasound monitoring of stress and damage development on a 15-ton concrete beam journal April 2016
Coda-wave monitoring of continuously evolving material properties and the precursory detection of yielding journal February 2019
Coda Wave Interferometry for Estimating Nonlinear Behavior in Seismic Velocity journal March 2002
Anomaly detection: A survey journal July 2009
Ultrasonic-Acoustic Emission Hybrid System for Monitoring Concrete Structures Affected by Alkali-silica Reaction conference November 2019
Effect of Acoustoelasticity on Ultrasonic Pulses and Damage of Concrete Under Tensile Stresses journal May 2018
Processing Ultrasonic Data by Coda Wave Interferometry to Monitor Load Tests of Concrete Beams journal June 2018

Similar Records

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
acoustics
alkali-silica reaction
anomaly detection
concrete
decorrelation
feature extraction
image reconstruction
monitoring
sensors
ultrasonic coda wave