Robust principal component analysis and support vector machine for detection of microcracks with distributed optical fiber sensors

Abstract

Development of a method for distributed detection of microcracks on structural elements with very small crack opening displacements is described in this study. Robust principal component analysis (RPCA) and support vector machine (SVM) techniques were employed for denoising and classification of the signals. The objective was to detect microcracks in structural elements less than 30 µm in size. The viability of the method was accomplished by experiments involving a 15-meter steel beam with known microcracks. A distributed optical fiber sensor system based on the Brillouin scattering technology was employed for distributed measurement of strains along the length of the 15-m long beam. Distributed strain signals based on Brillouin based sensors possess inherent system noise and ambient perturbations which in turn reduce the signal-to-noise ratio of the measurements. Therefore, it is not possible to detect the smaller microcracks with small crack opening displacements. Smaller CODs are lost within the noisy distributed strain signal acquired by the Brillouin system. Undetected microcracks result in larger cracks, corrosion, and other anomalies with severe economical and safety ramifications.The method introduced for denoising and enhancement of the signal in the present study enables manifestation of the singularities on the distributed strain data and detection of microcracks. The significant component containing those singularities is effectively separated from the noise component by RPCA-based matrix decomposition. An SVM classifier with Gaussian kernel function was designed, through which the crack detections are realized by singular and nonsingular binary classification. The experimental results demonstrated that it was possible to detect microcracks with CODs as low as 23 µm without errors.