Research on laser ultrasonic surface defect identification based on a support vector machine

Abstract

To solve the problem of difficult quantitative identification of surface defect depth during laser ultrasonic inspection, a support vector machine-based method for quantitative identification of surface rectangular defect depth is proposed. Based on the thermal-elastic mechanism, the finite element model for laser ultrasound inspection of aluminum materials containing surface defects was developed by using the finite element software COMSOL. The interaction process between laser ultrasound and rectangular defects was simulated, and the reflected wave signals corresponding to defects of different depths under pulsed laser irradiation were obtained. Laser ultrasonic detection experiments were conducted for surface defects of different depths, and multiple sets of ultrasonic signal waveform were collected, and several feature vectors such as time-domain peak, center frequency peak, waveform factor and peak factor were extracted by using MATLAB, the quantitative defect depth identification model based on support vector machine was established. The experimental results show that the laser ultrasonic surface defect identification model based on support vector machine can achieve high accuracy prediction of defect depth, the regression coefficient of determination is kept above 0.95, and the average relative error between the true value and the predicted value is kept below 10%, and the prediction accuracy is better than that of the reflection echo method and BP neural network model.

Delamination Depth Evaluation in Near-Surface of GFRP Laminates Based on RQA-MKLSVM Model

“…For 400 groups of data collected in each red square area in Fig. 13, calculate six different RQA parameters according to equation ( 12)- (20), and the results are shown in Fig. 17…”

“…Jiang et al used wavelet packet time-frequency coefficient and SVM to evaluate artificial rolling contact fatigue defects in different depths and achieved a 98.73% prediction accuracy rate [19]. Chen et al used SVM quantitative identification of surface defect depth of aluminum materials to achieve high accuracy prediction of defect depth, and the average relative error is kept below 10% [20]. Guan et al used genetic algorithm optimization SVM(GA-SVM) to realize quantitative testing of near-surface defects.…”

Research on surface defect identification of steel balls based on improved K-CV parameter optimization support vector machine

“…20,21 Therefore, SVM aims to optimize the margin, which is defined as the closest proximity between the hyperplane and the nearest sample sets belonging to different categories. 22,23 The learning strategy of SVM is to maximize the interval, which can be formalized as a problem of solving convex quadratic programing, which is also equivalent to the problem of minimizing the regularized hinge loss function. The learning algorithm of SVM is the optimization algorithm for solving convex quadratic programing.…”

Laser Ultrasonic Automatic Detection Method for Surface Microcracks on Metallic Cylinders

“…Magnetic particle testing (MT) [5], penetrant testing (PT) [6], eddy-current testing (ECT) [7] and ultrasonic testing (UT) [8] are the commonly used non-destructive methods used to test for surface defects. MT is mainly applied to the surface detection of ferromagnetic materials, but it cannot be applied to the detection of copper, aluminum and other non-ferromagnetic materials [9].…”