Weld Defect Detection Research Articles

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.

A welding defect detection method based on multiscale feature enhancement and aggregation

ABSTRACT Welding defects can pose significant safety risks in the industrial production. Accurate detection of these defects is crucial for ensuring the industrial production safety. Traditional computer vision methods rely on operator experience and knowledge and are time-consuming. In addition, manual feature extraction and classifier definition become more difficult for complex images or unknown defects. In contrast, deep learning can automatically extract features from raw data and build classifiers with higher accuracy. Additionally, deep learning models have stronger generalization ability and can identify a wider range of defects, without being limited by feature engineering. Consequently, we proposed a welding defect detection model based on multiscale feature enhancement and aggregation based on the advanced deep learning model YOLOv7. The model is composed of a wavelet multiscale attention (WMA), a parallel sampling module (PSS), and a path expansion aggregation network (PEANet). We compared the model with a variety of excellent object detection algorithms. Experiments show that the proposed model can effectively identify welding defects. Compared with the original model, the mAP has increased by approximately 1.2%, the average recall has increased by approximately 5.3%, the parameter volume has increased slightly, and the Flops has decreased by approximately 62.6%..

A Novel Penetration State Recognition Method Based on LSTM With Auditory Attention During Pulsed GTAW

Weld defect detection and control is of great significance for gas tungsten arc welding (GTAW) process of aluminum alloy, and the recognition of penetration states based on acoustic signal has been a hot topic. However, previous studies have ignored that acoustic features have distinct effects on the penetration state. In this paper, inspired by the attention mechanism in the vision, a novel auditory attention model combining the attention mechanism with long short-term memory (LSTM) network for penetration state recognition has been proposed. First, the 15-dimensional informative features including 9-dimensional time-domain and 6-dimensional wavelet features related to the penetration state are extracted. Second, the auditory attention mechanism is explored and the attention-based LSTM including attention mechanism before LSTM(AT-LSTM) and attention after LSTM(LSTM-AT) are established, which are experimentally verified to show greater performance than other traditional methods with an average accuracy of 93.56% and 95.32%, respectively. Furthermore, the attention vectors are visualized to figure out the mechanism of auditory attention when different penetration occurs.

Image Analysis of the Automatic Welding Defects Detection Based on Deep Learning

Image Analysis of the Automatic Welding Defects Detection Based on Deep Learning

Laser welding defects detection in lithium-ion battery poles

Strong demand for electric vehicles and energy storage applications has led to a rapid expansion of the battery sector. Laser welding is widely used in lithium-ion batteries and manufacturing companies due to its high energy density and capability to join different materials. Welding quality plays a vital role in the durability and effectiveness of welding structures. Therefore, it is essential to monitor welding defects to ensure welds quality. Manual inspection, analysis and evaluation of welding defect images is difficult due to the non-uniformity in their shape, position, and size. Hence the use of deep learning techniques to identify welding defects is more accurate and reliable due to the adequate training data samples, which helps to identify welding defects with greater accuracy. In this study, we present a novel collection of 3,736 laser welding images which are labeled with eight classes. This dataset contains both normal and defective classes collected from a Dade Laser Chinese production line. Moreover, we introduce a modified loss function that integrates cross entropy and complement objective training. The EfficientNetB6 model is trained with the newly introduced loss function that performed efficiently and achieved a promising accuracy during the classification phase. The experimental results demonstrate the significance of the proposed loss function and the sufficiency of EfficientNetB6 model on the laser welding dataset. Compared to other models, EfficientNetB6 performs better.

Context and scale-aware YOLO for welding defect detection

Radiography testing for welding defect detection is an essential inspection procedure to ensure welding quality. However, detecting these defects is a challenging task because they have various size and aspect ratio characteristics and low perceptiveness due to the low luminance and contrast characteristics of the radiography image (RI). To address these difficulties, this paper proposes a twin model-based automatic welding defect detection method to reveal welding defects of various sizes and aspect ratios more accurately. In addition, we propose a new image adjustment technique that is optimized to improve the accuracy of welding defect detection by adaptively adjusting the luminance and contrast of a given RI. The proposed method consists of three steps: preprocessing for defect detection (PDD), context-aware image adjustment (CIA), and scale-aware defect detection (SDD). In the PDD step, we extract the region of interest from a RI based on text detection by removing regions unnecessary for welding defect detection. In the CIA step, we adaptively optimize a given image to improve the detection accuracy by utilizing a differentiable parametric module that performs image enhancement filtering. In the SDD step, we define a twin model that outputs the embeddings of different scales from the adjusted RI to detect the defects with various scales accurately. At the inference stage of the detection model, we ensemble the results using a weighted fusion of the detection results from the twin model to take advantage of the ensemble strategy. The experimental results indicate that the proposed method achieves outstanding detection accuracy compared to the benchmark methods.

Real-Time Defect Detection Scheme Based on Deep Learning for Laser Welding System

Laser welding, as an important material processing technology, has been widely used in various fields of industry. In most industrial welding production and processing, high precision is required for welding parameters and fixed work pieces. However, in the process of laser welding, serious heat transfer effect will bring unpredictable welding deviations, and even a small deviation will lead to serious welding defects, which will affect the quality of the welded products. Traditional non-destructive testing methods have been widely used, but they have been proved to have some limitations. Existing laser welding defect detection schemes are mainly focused on the detection of post-weld defects, which requires a large amount of data, and the real-time detection cannot be guaranteed. In this paper, we propose a data acquisition system for collecting changes in physical characteristics during laser welding with the aids of multiple sensors. Based on the data originating from sensors’ system, an efficient laser welding defect detection model has been designed and investigated based on the MSCNN (multi-scale convolutional neural network), BiLSTM (bidirectional long short-term memory), and AM (attention mechanism). The final proposed MSCNN-BiLSTM-AM fusion detection model can achieve 99.38% detection accuracy, which make the laser welding system more efficient and more suitable.

Detection of Welding Defects by Non-Destructive Testing Methods

One of the most used joining methods in the manufacturing industry is welded joints. Welded joints are non-removable types of joints and good mechanical properties are expected from the weld seam after joining. For this reason, it is extremely important that there are no errors, defects or gaps in the weld area. This study is about the detection of defects existing in the welding regions of various machine elements with welded joints by non-destructive testing methods. The advantages and disadvantages of the non-destructive testing methods used in the study are presented.

A Novel Weld-Seam Defect Detection Algorithm Based on the S-YOLO Model

Detecting small targets and handling target occlusion and overlap are critical challenges in weld defect detection. In this paper, we propose the S-YOLO model, a novel weld defect detection method based on the YOLOv8-nano model and several mathematical techniques, specifically tailored to address these issues. Our approach includes several key contributions. Firstly, we introduce omni-dimensional dynamic convolution, which is sensitive to small targets, for improved feature extraction. Secondly, the NAM attention mechanism enhances feature representation in the region of interest. NAM computes the channel-wise and spatial-wise attention weights by matrix multiplications and element-wise operations, and then applies them to the feature maps. Additionally, we replace the SPPF module with a context augmentation module to improve feature map resolution and quality. To minimize information loss, we utilize Carafe upsampling instead of the conventional upsampling operations. Furthermore, we use a loss function that combines IoU, binary cross-entropy, and focal loss to improve bounding box regression and object classification. We use stochastic gradient descent (SGD) with momentum and weight decay to update the parameters of our model. Through rigorous experimental validation, our S-YOLO model demonstrates outstanding accuracy and efficiency in weld defect detection. It effectively tackles the challenges of small target detection, target occlusion, and target overlap. Notably, the proposed model achieves an impressive 8.9% improvement in mean Average Precision (mAP) compared to the native model.

Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network.

The detection of weld defects by using X-rays is an important task in the industry. It requires trained specialists with the expertise to conduct a timely inspection, which is costly and cumbersome. Moreover, the process can be erroneous due to fatigue and lack of concentration. In this context, this study proposes an automated approach to identify multi-class welding defects by processing the X-ray images. It is realized by an intelligent hybridization of the data augmentation techniques and convolutional neural network (CNN). The proposed data augmentation mainly performs random rotation, shearing, zooming, brightness adjustment, and horizontal flips on the intended images. This augmentation is beneficial for the realization of a generalized trained CNN model, which can process the multi-class dataset for the identification of welding defects. The effectiveness of the proposed method is confirmed by testing its performance in processing an industrial dataset. The intended dataset contains 4479 X-ray images and belongs to six groups: cavity, cracks, inclusion slag, lack of fusion, shape defects, and normal defects. The devised technique achieved an average accuracy of 92%. This indicates that the approach is promising and can be used in contemporary solutions for the automated detection and categorization of welding defects.

Semi-supervised transfer learning-based automatic weld defect detection and visual inspection

Welding is the most used fusing technology in the fabrication process of engineering structures including buildings, industrial facilities, bridges, and vital pipelines. Regular inspection of these welds is important for their overall safety and reliable usage. The need for fully automated, highly efficient structural health monitoring has encouraged researchers to invest their focus on new technologies involving artificial intelligence and computer vision. In this paper, a novel Semi-supervised Transfer learning based Multi-domain learning (ST-MDL) network is proposed for automatic weld image segmentation. Six traditional segmentation models based on U-net architecture have been utilized for comparative analysis with the proposed ST-MDL approach. The best performing model is employed for semantic segmentation of weld images to identify and measure the weld porosity inside a weld image. A novel end-to-end fully automated weld visual inspection framework (W-VIF) has also been proposed, where the measurements of segmented weld images are compared with the American welding society handbook of visual inspection standards to fully automate the process of visual inspection. The results demonstrate that the trained models are capable of identifying and quantifying weld defects, and hence a practical fully automated weld visual inspection procedure is created.

Numerical analysis and experimental research on detection of welding defects in pipelines based on magnetic flux leakage

Regular inspection of long-distance oil and gas pipelines plays an important role in ensuring the safe transportation of oil and gas, and inspection on welding defects is an important part of the inspection process. Magnetic flux leakage (MFL) is an electromagnetic non-destructive testing technique which has been commonly utilized to detect welding defects in pipelines. In the present study, Maxwell electromagnetic simulation software was used to carry out numerical study on the welding defects in pipelines, including incomplete penetration and undercut. The Ф406 pipeline with a wall thickness of 7 mm was selected as the study case to establish the numerical model. Setting the life-off value at 1 mm, the distribution of magnetic leakage field was investigated for pipeline without defect, pipeline with incomplete penetration defect and pipeline with undercut defect respectively, the characteristic values describing the depth and width of defects were found. Furthermore, quantified equations which can be used to describe the defect depth were proposed. Finally, experimental research was carried out to validate the effectiveness of the numerical model, and the experimental results showed good consistence with the numerical calculation results. The research results indicate that, it is technically feasible and reliable to diagnose the incomplete penetration and undercut welding defects in pipelines using MFL.

Welding defects classification by weakly supervised semantic segmentation

Radiographic non-destructive evaluation (NDE) is an essential technique for understanding defects in welds. These radiographs require certified workers to interpret them to identify the presence of defects. Recent deep learning techniques, primarily semantic segmentation, could help welding defect detection and classification. Using image segmentation technology to obtain performance evaluations of the presence, location, and size of defects can improve the stability of defect evaluations while saving a great deal of time. However, supervised instance segmentation requires many manually implemented pixel-level annotations, dramatically increasing the difficulty and cost of achieving non-destructive evaluations. In our work, the weakly supervised semantic segmentation based on the Cut-Cascade RCNN model is used to classify defects. The cascade RCNN obtains the region of interest (ROI) and classification information. In the ROI, adaptive threshold segmentation of the defects is implemented, and the image is filtered to obtain the mask information. The accuracy of using the Cut-Cascade RCNN model in our x-ray dataset size can reach 90.15%.

Defect detection method for high-resolution weld based on wandering Gaussian and multi-feature enhancement fusion

As the weakest point of the pipeline, the weld seam is prone to various internal defects and has great safety risks, so it is necessary to conduct a weld seam inspection. In addition, accurately detecting small-sized defects from high-resolution and low-contrast X-ray images is still a challenging task. Therefore, this paper proposes a defect detection method for high-resolution weld images, including three steps: welded extraction, weld restructuring, and defect detection. Because the resolution of the original image is high and the defect features are mainly concentrated in the weld area, it is not easy to directly defect detection. Firstly, a new irregular long weld extraction algorithm based on wandering Gaussian was designed. Secondly, because the existing welding seams aspect ratio is large and the information loss of conventional compression methods is serious, a new feature reorganization method was provided to maximize the effective information of the weld. Finally, a new method of welding defects detection method based on cross-layer feature fusion has been redesigned to take into efficiency and accuracy. The experiments show that the proposed method achieves the best detection performance on the public GDXray dataset compared with other advanced defect detection methods, from which it can locate the weld defects automatically and fast with high accuracy. It provides an effective solution for high-resolution weld defect detection.

Weld defect detection with convolutional neural network: an application of deep learning

Weld defect detection with convolutional neural network: an application of deep learning

Weld defect identification and characterization in radiographic images using deep learning: Review

Defects in the welds degrade the quality of the weld. Weld defect identification is a challenging task in the industry because of the wide range of weld imperfections. Weld defect detection using radiographic images is an effective technique for achieving good weld quality in shipbuilding and aerospace applications. Foreign inclusions, cracks and pores are examples of welding joint imperfections. Several appropriate computer-based image processing techniques have made the detection of weld defects possible. It is challenging because weld imperfection can show various sizes, shapes, contrasts and locations in radiography images. The accuracy of this inspection process is more dependent on various external factors and is also time-consuming. Automatic weld defect detection is needed by analyzing the images obtained directly from digital radiographic systems. This paper uses a unique image-based approach to a small batch of x-ray imaging datasets to investigate a potential solution for weld defect identification. This article compares a deep learning network’s performance for various parameter and hyper-parameter combinations. Also it compares the traditional approaches of defect detection using manual inspection method, feature-based defect identification, and finally deep - learning based approach on several types of weld defects in various industrial applications. This comparative analysis concludes that deep learning-based approaches have achieved more accuracy as compared to conventional techniques. This research paper also highlights a few challenges and future directions in welding area.

Influences of Magnetization Direction on the Flux Leakage Field of Weld Defects

The magnetic flux leakage (MFL) detection technique is applied to the detection of weld defects, such as cracks and pores. As the weld has a distinct structure, there are differences in the magnetization path and leakage field intensity under different magnetization directions. According to surveys, a suitable magnetization direction can significantly enhance detection rates of small-sized defects by stimulating a stronger field signal of the defect leakage. In this study, ANSYS finite element simulation software is used to calculate the weld defect leakage field based on the quantitative analysis. Specifically, the leakage field component strengths of circular hole defects and longitudinal rectangular groove defects are compared when the magnetization direction is perpendicular or parallel to the weld. Furthermore, the characteristic rules of the defect leakage field and its components under any magnetization direction are discussed, and a weld MFL detection platform is set up for validation. According to the experimental results, the amplitude of the magnetic leakage signal during vertical magnetization of circular hole defects is only 18.6% of that during parallel magnetization. Similarly, the amplitude of the magnetic leakage signal during parallel magnetization of longitudinal crack-type defects is only 9.2%~29.3% of that during vertical magnetization.

Magneto-optical imaging nondestructive testing of welding defects based on image fusion

Improving the visual effect of welding defect detection is a key research area of magneto-optical imaging nondestructive testing technology. Finite element analysis and magneto-optical image simulation are used to analyze the characteristics of magneto-optical imaging detection under rotating excitation. Through the stripe analysis of simulated magneto-optical images, it is found that the multi-frame magneto-optical images at defects have low discrete degree of gray value. Therefore, an image fusion method based on pixel standard deviation is proposed for the welding defect detection of magneto-optical imaging. Fast guide filtering is applied to the magneto-optical images of welding defects under rotating excitation. Pixel standard deviation is used to fuse multi-frame magneto-optical images, and image enhancement and rendering are used to improve the visual effect of welding defect detection. The experimental results show that the fast guided filter can improve the speed of image preprocessing and ensure good image smoothing effect. Compared with other image fusion algorithms, the proposed method can significantly improve the image quality of magneto-optical imaging detection, and does not require screening of magneto-optical images. This method has the advantages of tolerating frame drops in acquisition and excellent generalization performance, enabling fast and efficient nondestructive testing of welding defects.

Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning

Welding is a vital joining process; however, occurrences of weld defects often degrade the quality of the welded part. The risk of occurrence of a variety of defects has led to the development of advanced weld defects detection systems such as automated weld defects detection and classification. The present work is a novel approach that proposes and investigates a unique image-centered method based on a deep learning model trained by a small X-ray image dataset. A data augmentation method able to process images on the go was used to offset the limitation of the small X-ray dataset. Fine-tuned transfer learning techniques were used to train two convolutional neural network based architectures with VGG16 and ResNet50 as the base models for the augmented sets. Out of the networks we fine-tuned, VGG16 based model performed well with a relatively higher average accuracy of 90%. Even though the small dataset was spread across 15 different classes in an unbalanced way, the learning curves showed acceptable model generalization characteristics.

Weld Defect Detection of a CMT Arc-Welded Aluminum Alloy Sheet Based on Arc Sound Signal Processing

The cold metal transfer (CMT) process is widely used in thin plate welding because of its characteristics of low heat input and stable arc. In actual production, a larger weld gap, misalignment, or other problems due to assembly error lead to serious welding defects, such as burn-through and a lack of fusion. The arc sound contains a wealth of information related to the quality of the weld. This work analyzes the mechanism of CMT arc sound generation, as well as the correlation between the time–frequency spectrum of the arc sound signal and welding quality. This paper studies the extraction of the multi-channel time–frequency spectrum of an arc sound and inputs it to a custom convolutional neural network for the CMT welding defect identification of thin aluminum alloy plates. The experimental result shows that the average accuracy of the proposed model is 91.49% in the defect identification of a CMT arc-welded aluminum alloy sheet, which is higher than that of the single-channel time–frequency convolutional neural network and other traditional classification models.