Nondestructive Evaluation of Crack Depth in Concrete Using PCA-compressed Wave Transmission Function and Neural Networks

• Published in: Experimental mechanics Vol. 48; no. 2; pp. 225 - 231
• Main Authors: Shin, S. W., Yun, C. B., Futura, H., Popovics, J. S.
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01-04-2008; Springer
• Subjects: Applied sciences; Biomedical Engineering and Bioengineering; Buildings. Public works; Characterization and Evaluation of Materials; Control; Dynamical Systems; Engineering; Exact sciences and technology; Fracture mechanics (crack, fatigue, damage...); Fundamental areas of phenomenology (including applications); Lasers; Measurement and testing methods; Measurements. Technique of testing; Optical Devices; Optics; Photonics; Physics; Solid Mechanics; Structural and continuum mechanics; Vibration; Nondestructive evaluation of concrete; Surface wave transmission measurements; Crack depth; Neural networks; Self-calibrating technique; Principal component analysis; Measurement; Crack depth, Surface wave transmission measurements; Surface crack; Variability; Notch; Wave function; Rupture; Surface wave; Elastic wave; Neural network; Surface metrology; Cut off frequency; Wave transmission; Selfcalibration; Concrete; S wave; Non destructive test
• ISSN: 0014-4851; 1741-2765
• DOI: 10.1007/s11340-007-9083-3

Cracks in concrete are common defects that may enable rapid deterioration and failure of structures. Determination of a crack’s depth using surface wave transmission measurement and the cut-off frequency in the transmission function (TRF) is difficult, in part due to variability of the measurement data. In this study, use of complete TRF data as features for crack depth assessment is proposed. A principal component analysis (PCA) is employed to generate a basis for the measured TRFs for various simulated crack (notch) cases in concrete. The measured TRFs are represented by their projections onto the most significant PCs. Then neural networks (NN), using the PCA-compressed TRFs, are applied to estimate the crack depth. An experimental study is carried out for five different artificial crack (notch) cases to investigate the effectiveness of the proposed method. Results reveal that the proposed method can effectively estimate the artificial crack depth in concrete structures, even with incomplete NN training.