Detection model of invisible weld defects using magneto-optical imaging induced by rotating magnetic field

Magneto-optical (MO) imaging non-destructive testing (NDT) system excited by rotating magnetic field is proposed for feature extraction and detection classification of invisible arbitrary-angle weld defects. Based on Faraday rotation effect, the relationship between the imaging characteristics of weld defect MO image and the leakage magnetic field intensity is analyzed. The gray-level co-occurrence matrix (GLCM) method is used to extract texture features of the weld defect MO images, and the texture features of the images can reflect the leakage magnetic field characteristics of the defects. These texture features of the weld defect MO images are used as the input vector of the defect classification model based on support vector machine (SVM). The effectiveness and feasibility of the classification model are verified by the weld defect detection experiment. Experimental results show that the established recognition model can accurately classify invisible arbitrary-angle weld defects.