Temporal Resolution of Acoustic Process Emissions for Monitoring Joint Gap Formation in Laser Beam Butt Welding

With the increasing power and speed of laser welding, in-process monitoring has become even more crucial to ensure process stability and weld quality. Due to its low cost and installation flexibility, acoustic process monitoring is a promising method and has demonstrated its effectiveness. Although its feasibility has been the focus of existing studies, the temporal resolution of acoustic emissions (AE) has not yet been addressed despite its utmost importance for realizing real-time systems. Aiming to provide a benchmark for further development, this study investigates the relationship between duration and informativeness of AE signals during high-power (3.5 kW) and high-speed (12 m/min) laser beam butt welding. Specifically, the informativeness of AE signals is evaluated based on the accuracy of detecting and quantifying joint gaps for various time windows of signals, yielding numerical comparison. The obtained results show that signals can be shortened up to a certain point without sacrificing their informativeness, encouraging the optimization of the signal duration. Our results also suggest that large gaps (>0.3mm) induce unique signal characteristics in AE, which are clearly identifiable from 1 ms signal segments, equivalent to 0.2mm weld seam.

Press Release - Fraunhofer IZFP

Presseinformation - Fraunhofer IZFP

SHMNDT 2023

会议网站描述

SHMNDT 2023

会议网站描述

H2SkaProMo - Fraunhofer IZFP

H2SkaProMo - Fraunhofer IZFP

Deep Learning Neural Network Performance on NDT Digital X-ray Radiography Images: Analyzing the Impact of Image Quality Parameters—An Experimental Study

In response to the growing inspection demand exerted by process automation in component manufacturing, non-destructive testing (NDT) continues to explore automated approaches that utilize deep-learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep-learning models. This study investigated the influence of two image-quality parameters, namely signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), on the performance of a U-net deep-learning semantic segmentation model. Input images were acquired with varying combinations of exposure factors, such as kilovoltage, milli-ampere, and exposure time, which altered the resultant radiographic image quality. The data were sorted into five different datasets according to their measured SNR and CNR values. The deep-learning model was trained five distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection-over-union (IoU) metric of 0.9594 on test data of the same category but dropped to 0.5875 when tested on lower CNR test data. The result of this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters in order to enhance the performance of deep-learning segmentation models for NDT digital X-ray radiography applications.

Using the Corner Reflection for Depth Evaluation of Surface Breaking Cracks in Concrete by Ultrasound - Journal of Nondestructive Evaluation

The corner echo is a well-known effect in ultrasonic testing, which allows detection of surface breaking cracks with predominantly perpendicular orientation to the surface as, for example, corrosion cracks in metal pipes or shafts. This echo is formed by two planes, the surface of the crack and the surface which the crack breaks. It can also be classified as a half-skip method, since a reflection of the pulse occurs on the backwall before the reflection at the defect takes place. In combination with the diffraction from the crack tip, the corner echo also allows crack sizing. As shown in this paper, the corner reflection can be used in civil engineering for nondestructive inspection of concrete. Commercially available low frequency ultrasonic arrays with dry point contact sources generate SH transversal waves with sufficient divergence of the sound field in order to detect corner reflections. Ultrasonic line-scans and area-scans were acquired with a linear array on flat concrete specimens, and the data were reconstructed by the Synthetic aperture focusing technique. If the angles and the area of reconstruction are chosen accordingly, the corner echo reflection can be distinguished from other ultrasonic information. The corner echo can thus be used as a method for deciding whether a crack is a partial-depth crack or a full-depth crack and thus for obtaining a statement about crack depth. This paper presents corresponding experimental results obtained on concrete specimens with artificial test defects and cracks induced under controlled conditions.

Press Release - Fraunhofer IZFP