Surface defects detection in metal materials repaired by laser surfacing of seal welds

Abstract

Laser surfacing repair technology for sealing welds is widely used in metal repair. Due to welding technology and usage scenarios, process defects on the metal surface are inevitable. Therefore, ultrasonic surface wave technology is used to analyze the surface defects of metal materials. Principal Component Analysis (PCA) is used to extract the main defect signals on the metal surface, and synthetic aperture focusing technology is used to reduce imaging errors. Considering the lack of PCA in imaging defects, wavelet domain hidden Markov models (WHMM) are combined to optimize the signal, thereby improving the inspection effect of metal defects. In the test results of the relationship between the propagation distance of 316 L steel and the defect echo signal, the echo signal gradually fitted as the propagation distance increased. When the propagation distance was greater than 10 mm, the image acquisition defect signal had significant noise points. Various techniques were used to process the original echo signals of metal surface defects. The improved PCA-WHMM algorithm had significant advantages with the SNR value of the defect image increased by 13.65 % compared to PCA-WHMM. At the same time, the surface repair effects of laser surfacing 316 L metal before and after optimization were compared. The hardness, toughness, and corrosion resistance of the optimized metal were significantly improved. The proposed technological innovation combines traditional laser surfacing repair with deep learning fault diagnosis, which not only greatly improves the efficiency of fault diagnosis, but also proves that this research can effectively avoid common focus issues of laser surfacing repair technology, providing important technical reference for the application of ultrasonic technology in metal defect detection.