A Review of Non-Destructive Testing (NDT) Techniques for Defect Detection: Application to Fusion Welding and Future Wire Arc Additive Manufacturing Processes

Deep convolutional neural network for weld defect classification in radiographic images

The quality of welds is critical to the safety of structures in construction, so early detection of irregularities is crucial. Advances in machine vision inspection technologies, such as deep learning models, have improved the detection of weld defects. This paper presents a new CNN model based on ResNet50 to classify four types of weld defects in radiographic images: crack, pore, non-penetration, and no defect. Stratified cross-validation, data augmentation, and regularization were used to improve generalization and avoid over-fitting. The model was tested on three datasets, RIAWELC, GDXray, and a private dataset of low image quality, obtaining an accuracy of 98.75 %, 90.255 %, and 75.83 %, respectively. The model proposed in this paper achieves high accuracies on different datasets and constitutes a valuable tool to improve the efficiency and effectiveness of quality control processes in the welding industry. Moreover, experimental tests show that the proposed approach performs well on even low-resolution images.

Coded Excitation for Ultrasonic Testing: A Review

Originating in the early 20th century, ultrasonic testing has found increasingly extensive applications in medicine, industry, and materials science. Achieving both a high signal-to-noise ratio and high efficiency is crucial in ultrasonic testing. The former means an increase in imaging clarity as well as the detection depth, while the latter facilitates a faster refresh of the image. It is difficult to balance these two indicators with a conventional short pulse to excite the probe, so in general handling methods, these two factors have a trade-off. To solve the above problems, coded excitation (CE) can increase the pulse duration and offers great potential to improve the signal-to-noise ratio with equivalent or even higher efficiency. In this paper, we first review the fundamentals of CE, including signal modulation, signal transmission, signal reception, pulse compression, and optimization methods. Then, we introduce the application of CE in different areas of ultrasonic testing, with a focus on industrial bulk wave single-probe detection, industrial guided wave detection, industrial bulk wave phased array detection, and medical phased array imaging. Finally, we point out the advantages as well as a few future directions of CE.

Full-Matrix Imaging in Fourier Domain towards Ultrasonic Inspection with Wide-Angle Oblique Incidence for Welded Structures

The total focusing method (TFM) has been increasingly applied to weld inspection given its high image quality and defect sensitivity. Oblique incidence is widely used to steer the beam effectively, considering the defect orientation and structural complexity of welded structures. However, the conventional TFM based on the delay-and-sum (DAS) principle is time-consuming, especially for oblique incidence. In this paper, a fast full-matrix imaging algorithm in the Fourier domain is proposed to accelerate the TFM under the condition of oblique incidence. The algorithm adopts the Chebyshev polynomials of the second kind to directly expand the Fourier extrapolator with lateral sound velocity variation. The direct expansion maintains image accuracy and resolution in wide-angle situations, covering both small and large angles, making it highly suitable for weld inspection. Simulations prove that the third-order Chebyshev expansion is required to achieve image accuracy equivalent to the TFM with wide-angle incidence. Experiments verify the algorithm's performance for weld flaws using the proposed method with the transverse wave and the full-skip mode. The depth deviation is within 0.53 mm, and the sizing error is below 15%. The imaging efficiency is improved by a factor of up to 8 compared to conventional TFM. We conclude that the proposed method is applicable to high-speed weld inspection with various oblique incidence angles.

A Real-Time Defect Detection Strategy for Additive Manufacturing Processes Based on Deep Learning and Machine Vision Technologies

Nowadays, additive manufacturing (AM) is advanced to deliver high-value end-use products rather than individual components. This evolution necessitates integrating multiple manufacturing processes to implement multi-material processing, much more complex structures, and the realization of end-user functionality. One significant product category that benefits from such advanced AM technologies is 3D microelectronics. However, the complexity of the entire manufacturing procedure and the various microstructures of 3D microelectronic products significantly intensified the risk of product failure due to fabrication defects. To respond to this challenge, this work presents a defect detection technology based on deep learning and machine vision for real-time monitoring of the AM fabrication process. We have proposed an enhanced YOLOv8 algorithm to train a defect detection model capable of identifying and evaluating defect images. To assess the feasibility of our approach, we took the extrusion 3D printing process as an application object and tailored a dataset comprising a total of 3550 images across four typical defect categories. Test results demonstrated that the improved YOLOv8 model achieved an impressive mean average precision (mAP50) of 91.7% at a frame rate of 71.9 frames per second.

WD-YOLO: A More Accurate YOLO for Defect Detection in Weld X-ray Images

X-ray images are an important industrial non-destructive testing method. However, the contrast of some weld seam images is low, and the shapes and sizes of defects vary greatly, which makes it very difficult to detect defects in weld seams. In this paper, we propose a gray value curve enhancement (GCE) module and a model specifically designed for weld defect detection, namely WD-YOLO. The GCE module can improve image contrast to make detection easier. WD-YOLO adopts feature pyramid and path aggregation designs. In particular, we propose the NeXt backbone for extraction and fusion of image features. In the YOLO head, we added a dual attention mechanism to enable the model to better distinguish between foreground and background areas. Experimental results show that our model achieves a satisfactory balance between performance and accuracy. Our model achieved 92.6% mAP@0.5 with 98 frames per second.

Integrated Video and Acoustic Emission Data Fusion for Intelligent Decision Making in Material Surface Inspection System

In the field of intelligent surface inspection systems, particular attention is paid to decision making problems, based on data from different sensors. The combination of such data helps to make an intelligent decision. In this research, an approach to intelligent decision making based on a data integration strategy to raise awareness of a controlled object is used. In the following article, this approach is considered in the context of reasonable decisions when detecting defects on the surface of welds that arise after the metal pipe welding processes. The main data types were RGB, RGB-D images, and acoustic emission signals. The fusion of such multimodality data, which mimics the eyes and ears of an experienced person through computer vision and digital signal processing, provides more concrete and meaningful information for intelligent decision making. The main results of this study include an overview of the architecture of the system with a detailed description of its parts, methods for acquiring data from various sensors, pseudocodes for data processing algorithms, and an approach to data fusion meant to improve the efficiency of decision making in detecting defects on the surface of various materials.

Non-Destructive Detection of Real Defects in Polymer Composites by Ultrasonic Testing and Recurrence Analysis

This paper presents results of ultrasonic non-destructive testing of carbon fibre-reinforced plastics (CFRPs) and glass-fibre reinforced plastics (GFRPs). First, ultrasonic C-scan analysis was used to detect real defects inside the composite materials. Next, the composite materials were subjected to drilling in the area of defect formation, and measured forces were used to analyse the drilling process using recurrence methods. Results have confirmed that recurrence methods can be used to detect defects formed inside a composite material during machining.

Numerical Study and Optimal Design of the Butterfly Coil EMAT for Signal Amplitude Enhancement

The low energy conversion efficiency of electromagnetic acoustic transducers (EMATs) is a critical issue in nondestructive testing applications. To overcome this shortcoming, a butterfly coil EMAT was developed and optimized by numerical simulation based on a 2-D finite element model. First, the effect of the structural parameters of the butterfly coil EMAT was investigated by orthogonal test theory. Then, a modified butterfly coil EMAT was designed that consists of three-square permanent magnets with opposite polarity (TSPM-OP) to enhance the signal amplitude. Finally, the signal amplitude obtained from the three types of EMATs, that is, the traditional EMAT, the EMAT optimized by orthogonal test theory, and the modified EMAT with TSPM-OP, were analyzed and compared. The results show that the signal amplitude achieved by the modified butterfly coil EMAT with TSPM-OP can be increased by 4.97 times compared to the traditional butterfly coil EMAT.

Metal Surface Defect Detection Method Based on TE01 Mode Microwave

With the aim of addressing the difficulty of detecting metal surface cracks and corrosion defects in complex environments, we propose a detection method for metal surface cracks and corrosion defects based on TE01-mode microwave. The microwave detection equations of cracks and corrosion defects were established by the Maxwell equations when the TE01 mode was excited by microwaves, and the relationship model between the defect size and the microwave characteristic quantity was established. A finite integral simulation model was established to analyze the influence of defects on the microwave electric field, magnetic field, and tube wall current in the rectangular waveguide, as well as the return loss at the defect; an experimental platform for the detection of metal surface cracks and corrosion defects was built. The absolute value of the return loss of the microwave reflected wave increased, and with the increase of the defect width, the microwave detection frequency at the defect decreased. The TE01-mode microwave has good detection ability for metal surface cracks and corrosion defects and can effectively detect cracks with a width of 0.3 mm.