Aerospace welds are non-destructively evaluated (NDE) during manufacturing to identify defective parts that may pose structural risks, often using digital radiography. The analysis of these digital radiographs is time consuming and costly. Attempts to automate the analysis using conventional computer vision methods or shallow machine learning have not, thus far, provided performance equivalent to human inspectors due to the high reliability requirements and low contrast to noise ratio of the defects. Modern approaches based on deep learning have made considerable progress towards reliable automated analysis. However, limited data sets render current machine learning solutions insufficient for industrial use. Moreover, industrial acceptance would require performance demonstration using standard metrics in non-destructive evaluation, such as probability of detection (POD), which are not commonly used in previous studies. In this study, data augmentation with virtual flaws was used to overcome data scarcity, and compared with conventional data augmentation. A semantic segmentation network was trained to find defects from computed radiography data of aerospace welds. Standard evaluation metrics in non-destructive testing were adopted for the comparison. Finally, the network was deployed as an inspector’s aid in a realistic environment to predict flaws from production radiographs. The network achieved high detection reliability and defect sizing performance, and an acceptable false call rate. Virtual flaw augmentation was found to significantly improve performance, especially for limited data set sizes, and for underrepresented flaw types even at large data sets. The deployed prototype was found to be easy to use indicating readiness for industry adoption.

The current paper presents a comprehensive overview of weld quality control and assurance of welded structures where the major failure prevention is due to fatigue loading. It gives the drawbacks and limitation of quality control systems, international weld quality standards, and guidelines used in today’s weld production. Furthermore, in recent development in quality control and assurance of welded structures, a new online method is presented. The main target is to enable a complete, online evaluation of large quantities of welds in an accurate and repeatable fashion. Information gathered will not only be used for determining the weld quality level with respect to the fatigue strength but also to be evaluated for use in improved process control, in welding power sources, and robot control systems. It is verified that the new online method, a new laser scanning technology, and algorithms can successfully be used as modern tools for automated unbiased geometrical weld quality assurance and implemented in weld production environment.

Digital weld quality assurance systems are increasingly used to capture local geometrical variations that can be detrimental for the fatigue strength of welded components. In this study, a method is proposed to determine the required scanning sampling resolution for proper fatigue assessment. Based on FE analysis of laser-scanned welded joints, fatigue failure probabilities are computed using a Weakest-link fatigue model with experimentally determined parameters. By down-sampling of the scanning data in the FE simulations, it is shown that the uncertainty and error in the fatigue failure probability prediction increases with decreased sampling resolution. The required sampling resolution is thereafter determined by setting an allowable error in the predicted failure probability. A sampling resolution of 200 to 250 μm has been shown to be adequate for the fatigue-loaded welded joints investigated in the current study. The resolution requirements can be directly incorporated in production for continuous quality assurance of welded structures. The proposed probabilistic model used to derive the resolution requirement accurately captures the experimental fatigue strength distribution, with a correlation coefficient of 0.9 between model and experimental failure probabilities. This work therefore brings novelty by deriving sampling resolution requirements based on the influence of stochastic topographical variations on the fatigue strength distribution.

Robustness of HFMI treatment in different weld qualities according to ISO 5817 was studied, and fatigue testing of the treated samples was carried out in order to investigate the effect of the weld quality prior treatment. The results show that HFMI-treated welds with weld quality level D shows fatigue life improvements that fall within the IIW recommendations for HFMI. No significant influence from the HFMI operator or HFMI equipment on the fatigue life was found. However, the scatter in fatigue testing results varied with HFMI operator and indicated that different HFMI operators could produce consistent treatment results. A considerable effect on fatigue life from HFMI tool radius was found, where the 2-mm tool radius showed considerably greater fatigue life compared with the 1.5-mm tool radius. According to IIW (Marquis and Barsoum 2016), for steel grade S_Y = 700 MPa, the fatigue strength recommendation is FAT 160 (m = 5) for transverse stiffener–welded joints with as-welded quality B according to ISO 5817 (ISO/TC 44/SC 10 2011), prior to treatment. It can be observed in the current study that fatigue-tested HFMI-treated welded joints, welded with weld quality D, are in good agreement with the IIW recommendations.