In this work, classification of cracks in a non-ferromagnetic material (aluminum 1050) is presented using two supervised machine learning techniques called support vector machines (SVM) and decision tree. The classification performances between the two classifiers were evaluated using confusion matrices and miss-classification errors. In order to improve the classification performance, a multi-level SVM model is proposed wherein each level implements SVM using different features and kernels. The experimental tests were performed in two aluminum plates containing 18 defects with different depths and lengths. The 18 defects were inspected in the surface and sub-surface locations, resulting in a study of 36 different crack cases. The experimental data used to extract features for supervised machine learning were obtained using an eddy current testing (ECT) probe that includes a planar coil and a tunnel magnetoresistance (TMR) sensor. The probe was excited by a multi-frequency signal with four testing frequencies to evaluate the dimensions and the locations of the defects. Due to the experimental noise existing in the measurement signals, it is important to pre-process the signals before feature extraction. Signal processing techniques (such as moving average filter, spline interpolation and symmetry corrections) were used before extracting the features for classification.

Wavefield measurements by a scanning laser Doppler vibrometer are generally carried out in a cartesian coordinate. As a piezoelectric transducer generates Lamb waves following radial paths, the use of a polar coordinate can be a suitable alternative to the use of a cartesian coordinate. Therefore, in the proposed method, using a single transducer placed on the center of the specimen, the measured wavefields are transformed into polar coordinates, making several identical radial line inspections from the center in a direction of incident waves. Taking advantage of the properties of the polar coordinates, a signal processing technique is proposed through a frequency-wavenumber filtering process in these coordinates. In this technique, by using proper filters, unwanted wave modes of the incident wave along with all reflected waves are filtered out. In addition, the conventional features of RMS and Euclidean distance are adapted for the polar coordinate system to image the bonded plate. The proposed signal processing and damage imaging are first introduced through a numerical simulation. Then, the performance of the proposed technique is presented by experimental measurements of two specimens including adhesively bonded carbon fiber-reinforced plastic composite plates and bonded aluminum plates.

This paper compares low-frequency Lamb waves in a pitch-catch configuration and high-frequency bulk waves in a pulse-echo mode for ultrasonic C-scan imaging of composite lap joints. The pulse-echo measurement is conducted by using a delay line transducer. On the other hand, the ultrasonic guided waves are measured in a pitch-catch configuration by using a PZT disk moved by a positioning system over the scan area. In both methods, the signals are acquired in a C-scan manner over the adhesive joint area. Applying signal processing techniques, including frequency-wavenumber filtering, and bandpass filtering, along with different feature extraction, images of the scan area are obtained. For this study, two different types of composite lap joints are used. The first joint consists of composite plates reinforced with woven composite fabric, with defects in the form of missing adhesive. In the second joint, quasi-isotropic composite plates are employed, and disbonds are used to simulate defects. The Fisher discriminant criterion is used to assess the capability of each method in accurately distinguishing defects from the pristine condition. The paper concludes with a discussion of the results and effects of using both techniques.

In this paper, guided Lamb wave tomography and eddy current testing (ECT) techniques were combined to locate and evaluate fiber breaks in carbon-fiber-reinforced plastic (CFRP) structures. Guided wave testing (GWT) and computed tomography (CT) imaging were employed to quickly locate fiber breaks in the CFRP plate. From B-scans performed along two different fiber orientations (0 and 90 degrees), parallel-beam projections of different features were extracted from the guided wave signals, using signal-processing techniques (such as wavelet and Hilbert transforms) and statistical functions (such as skewness and kurtosis). The parallel-beam projections of each individual feature were used as input in computed tomography imaging reconstruction to approximately estimate the location of fiber breaks. From the obtained reconstructed images, image-fusion techniques were applied to get complementary information from multiple source images into one single image. After locating the fiber breaks, C-scans were performed in the vicinity of the damage, using an ECT probe with double excitation configuration to evaluate the condition of the fiber break.