衍射时差法 (TOFD) 具有检测信息丰富、抗噪声强、效率高、定位定量

Time-of-Flight Diffraction (TOFD) has the advantages of rich detection information, strong anti-noise, high efficiency, and accurate positioning and quantification. It is widely used in weld inspection, while TOFD map discrimination mainly relies on people, with low efficiency, high subjectivity, and reliability Low-level issues. In order to improve the accuracy and efficiency of defect type recognition, a cascaded fusion convolutional neural network (CNN-TCN) is constructed by combining TOFD map and waveform characteristics to automatically recognize the defect type in the weld defect scan image. The results show that the classification accuracy based on CNN-TCN is significantly higher than the pure lenet5 and TCN methods, and the recognition rate of defect types can reach more than 88%. It shows that the image characteristics of TOFD weld defects and the waveform characteristics of its ultrasonic sequence are considered comprehensively. Improving the classification accuracy of TOFD weld defects has a great effect, and has high recognition rate, robustness and anti-interference ability.

Diffraction time difference method (TOFD) has the advantages of rich detection information, strong noise resistance, high efficiency and accurate positioning, and is widely used in weld detection, while TOFD map evaluation mainly depends on people, there are low efficiency, subjectivity, low reliability and other problems. In order to improve the accuracy and efficiency of defect type recognition, combined with TOFD map and waveform characteristics, a cascading fusion converge neural network (CNN-TCN) is constructed to automatically identify defect types in weld defect scanning images. The results show that the classification accuracy of CNN-TCN is significantly higher than that of the simple lenet5 and TCN methods, and the recognition rate of defect types can reach more than 88%, which shows that the image characteristics of TOFD weld defects and the waveform characteristics of their ultrasonic sequence are considered comprehensively, which has a great effect on improving the classification accuracy of TOFD weld defects, and has high recognition rate, robustness and anti-jamming ability.

TOFD has many advantages, such as abundant detection information, strong noise resistance, high efficiency and accurate positioning, and is widely used in weld detection. TOFD spectrum discrimination mainly depends on human beings, which has low efficiency, high subjectivity and low reliability. In order to improve the accuracy and efficiency of defect type recognition, a cascade fusion convolutional neural network (CNN TCN) is constructed based on TOFD and waveform characteristics to automatically identify the defect types in the weld defect scanning image. The results show that the classification accuracy of CNN TCN is significantly higher than that of lenet5 and TCN method, and the recognition rate of defect types can reach over 88%. It shows that considering the image characteristics of TOFD weld defects and the waveform characteristics of ultrasonic sequence, it has a great effect on improving the classification accuracy of TOFD weld defects, and has high recognition rate, robustness and anti-interference ability.<br>