TY - GEN
T1 - Detection of delamination in concrete bridge decks using MFCC of acoustic impact signals
AU - Zhang, G.
AU - Harichandran, R. S.
AU - Ramuhalli, P.
PY - 2010
Y1 - 2010
N2 - Delamination of the concrete cover is a commonly observed damage in concrete bridge decks. The delamination is typically initiated by corrosion of the upper reinforcing bars and promoted by freeze-thaw cycling and traffic loading. The detection of delamination is important for bridge maintenance and acoustic non-destructive evaluation (NDE) is widely used due to its low cost, speed, and easy implementation. In traditional acoustic approaches, the inspector sounds the surface of the deck by impacting it with a hammer or bar, or by dragging a chain, and assesses delamination by the "hollowness" of the sound. The detection of the delamination is subjective and requires extensive training. To improve performance, this paper proposes an objective method for delamination detection. In this method, mel-frequency cepstral coefficients (MFCC) of the signal are extracted. Some MFCC are then selected as features for detection purposes using a mutual information criterion. Finally, the selected features are used to train a classifier which is subsequently used for detection. In this work, a simple quadratic Bayesian classifier is used. Different numbers of features are used to compare the performance of the detection method. The results show that the performance first increases with the number of features, but then decreases after an optimal value. The optimal number of features based on the recorded signals is four, and the mean error rate is only 3.3% when four features are used. Therefore, the proposed algorithm has sufficient accuracy to be used in field detection.
AB - Delamination of the concrete cover is a commonly observed damage in concrete bridge decks. The delamination is typically initiated by corrosion of the upper reinforcing bars and promoted by freeze-thaw cycling and traffic loading. The detection of delamination is important for bridge maintenance and acoustic non-destructive evaluation (NDE) is widely used due to its low cost, speed, and easy implementation. In traditional acoustic approaches, the inspector sounds the surface of the deck by impacting it with a hammer or bar, or by dragging a chain, and assesses delamination by the "hollowness" of the sound. The detection of the delamination is subjective and requires extensive training. To improve performance, this paper proposes an objective method for delamination detection. In this method, mel-frequency cepstral coefficients (MFCC) of the signal are extracted. Some MFCC are then selected as features for detection purposes using a mutual information criterion. Finally, the selected features are used to train a classifier which is subsequently used for detection. In this work, a simple quadratic Bayesian classifier is used. Different numbers of features are used to compare the performance of the detection method. The results show that the performance first increases with the number of features, but then decreases after an optimal value. The optimal number of features based on the recorded signals is four, and the mean error rate is only 3.3% when four features are used. Therefore, the proposed algorithm has sufficient accuracy to be used in field detection.
KW - Acoustic signal processing
KW - Bayesian classifier
KW - Delamination detection
KW - Mel-frequency cepstral coefficients
KW - Mutual information
UR - http://www.scopus.com/inward/record.url?scp=77950167063&partnerID=8YFLogxK
U2 - 10.1063/1.3362454
DO - 10.1063/1.3362454
M3 - Conference contribution
AN - SCOPUS:77950167063
SN - 9780735407480
T3 - AIP Conference Proceedings
SP - 639
EP - 646
BT - Review of Progress in Quantitative Nondestructive Evaluation
T2 - 36th Annual Review of Progress in Quantitative Nondestructive Evaluation, QNDE
Y2 - 26 July 2009 through 31 July 2009
ER -