Radiographic Weld Research Articles

Identification of weld sub-surface defects by radiographic images using texture features

Non-Destructive Testing (NDT) is important to detect sub-surface defects in the weldments to ensure the quality of weld joints. The weld radiographs are digitized using a high-resolution digital camera. Data augmentation techniques are applied to expand the radiographic image dataset. Multi-class defect classification is done using the Gray-level co-occurrence matrix as a feature extractor and these features are given as input to various classifiers for classifying slag inclusion, incomplete penetration, and acceptable weld bead classes. The proposed methodology achieved the highest accuracies of 84%,83%,80%,70%, and 64% respectively for GLCM plus Random Forest, GLCM plus XGBoost, GLCM plus lightGBM, GLCM plus KNN, and GLCM plus SVM. The technology of applying ML techniques on radiographic images in detection of defects in welding as well as other manufacturing processes can be a sustainable practice.

Defect detection enhancement using Gaussian Sparse Models

Detecting defects is critical in industrial fabrication, such as pipe welding, where radiography testing (RT) is the gold standard as a non-destructive method for monitoring weld quality and weld corrosion. The extraction of seamless information from radiographic images is critical for this approach. Image processing techniques can improve the quality of radiographic images by enhancing image contrast, especially in flawed regions. In this study, a method based on Gaussian mixture models was implemented and applied to radiographs of welded objects to improve visualization and detectability. In the Sparse Coding and Gaussian Scale Mixture method (SSC-GSM), the local image patches are described as a mixture of Gaussian distributions. Given the different levels of noise in the individual images, the background was determined and subtracted from each original image. The results show that the proposed techniques can maintain and improve the edge information in radiographs and defective regions. The density of pixels along the analyzed profile lines has yielded enhancement by a factor of approximately two for the reconstructed images as compared to the original images. We tested the SSC-GSM method on GD-Xray database with 68 radiographs of the weld. In total, the SSC-GSM technique can improve the contrast of radiography image by back ground removal method and show the defects better that exist in weld radiographs, compared to traditional method for the detection of weld defects.

Defect signal intelligent recognition of weld radiographs based on YOLO V5-IMPROVEMENT

Internal pipeline weld defects cause pipeline cracking accidents, whereas X-ray detection can detect these defects. The deep learning-based intelligent defect identification model of weld radiographs extracted weld defects automatically through a convolutional neural network, thereby eliminating the subjective interference of human factors and improving the quality and speed of film evaluation. By proposing the YOLO V5-IMPROVEMENT model and adding the CA attention mechanism, SIOU loss function, and FReLU activation function, this paper improved the ability to detect small targets, capture low-sensitivity spatial information, and perform global optimization. A total of 7500 radiographs containing weld defects of a Chinese oil and gas long-distance pipeline were selected for training, verifying, and testing the model developed in the paper. Precision and recall of the YOLO V5-improvement presented in this paper reached 92.2 % and 92.3 %, which were 10.7 % and 12.5 % higher than YOLO V4, and 9 % and 11.2 % higher than the unimproved YOLO V5 model, respectively. It is confirmed that YOLO V5-IMPROVEMENT has high accuracy and high robustness and that applying this model to the intelligent defect identification of weld ray images can significantly improve detection efficiency and reduce the misjudgment rate.

A self-directed dashboard for the evaluation and classification of weld defects

At present, several methods are being evolved in enhancing probability of detection (POD) in the domain of Non-destructive Testing (NDT). However there is demand for reducing human exhaustion and enhance POD in NDT due to lack of accuracy and time to complete the detection and interpretation of defects..To improve this process, an attempt towards incorporating several computational techniques is being analyzed. Yet, a robust model incorporating suitable image processing techniques and an efficient interpretation mechanism with an appropriate visualization technique is proposed. The system attempts to process the radiographs to segregate and extract the different Region of Interest (ROI) s (defects) from the given image using an automated task. For image classification, Convolutional Neural Network (CNN) is used. Thus, a complete AI based computational solution is devised for processing, interpreting the radiographic weld defects.

Approach to weld segmentation and defect classification in radiographic images of pipe welds

Detecting indications (points suspicious for defects) in weld radiographs is an important research topic in the field of industrial non-destructive testing. Many computer-aided detection techniques have been designed for such applications as detecting indications occurrence, segmentation of the indication area, classification of the indications. However, these techniques are mainly focused on only one of the listed problems. Different defects may exhibit different visual properties in shapes, sizes, textures, contrasts, and positions, that often leading to ad-hoc solutions. The paper investigates to the fine tuning of the machine learning approach to high resolution radiograph processing produced by real-time radiography using digital detector arrays (DDA) method. The main contributions of this work are the preprocessing feature for human readability of the radiographic images and the proposed neural network-based solutions for all stages, from weld detection on the radiographic images and its segmentation to indication segmentation and classification. The designed approach was implemented as a web service with web site front-end. The demo version of the software is available with this instruction https://github.com/NastyaMittseva/DefectRecognitionSystem.

Accurate segmentation of weld defects with horizontal shapes

Many researchers used computer-aided detection techniques for weld flaws segmentation problems. However, existing approaches fail to segment different weld defects types. We elaborate on our recently published work [1] to provide a comprehensive framework capable of detecting weld defects. This paper proposes a novel image processing pipeline that explores two new filters to segment the horizontal flaws and separates the background and vertical defects. Our technique performs two separate convolutional processes between the preprocessed image and both filters. We test our method on a publicly available GDXray database, which consists of 68 weld X-ray images for nondestructive testing [2]. Experiments showed that the proposed technique achieved a high segmentation accuracy, based on multiple evaluation metrics such as Dice and Jaccard metrics. The efficiency of our method is high. The proposed pipeline demonstrated its efficiency and applicability (Dice and Jaccard metrics are >99%), in practical weld defect segmentation processes, despite its simple structure. Thus, it is a promising technique for the detection of weld defects. In total, our technique can segment more different flaws types that exist in weld radiographs, compared to traditional approaches for the detection of weld defects.

Text recognition in radiographic weld images

Automatic recognition of text characters on radiographic images based on computer vision would be a very useful step forward as it could improve and simplify the file handling of digitised radiographs. Text recognition in radiographic weld images is challenging since there is no uniform font or character size and each character may tilt in different directions and by different amounts. Deep learning approaches for text recognition have recently achieved breakthrough performance using convolutional neural networks (CNNs). CNNs can recognise normalised characters in different fonts. However, the tilt of a character still has a strong influence on the accuracy of recognition. In this paper, a new improved algorithm is proposed based on the Radon transform, which is very effective at character rectification. The improved algorithm increases the accuracy of character recognition from 86.25% to 98.48% in the current experiments. The CNN is used to recognise the rectified characters, which achieves good accuracy and improves character recognition in radiographic weld images. A CNN greatly improves the efficiency of digital scanning and filing of radiographic film. The method proposed in this paper is also compared with other methods that are commonly used in other fields and the results show that the proposed method is better than state-of-the-art methods.

Computer Aided Radiograph Interpretation Tool for Defect Characterization from Weld Plates

Industrial Radiography is the most widely used NDT technique for weld defect characterization. As it is an indirect technique, an expert radiologist is required at the interpretation end to identify and characterize the defect in radiographs. However radiographs suffer from poor contrast thereby making it difficult to isolate the defect region from the background. Hence it is necessary to develop computer aided analysis tool for automated interpretation of weld radiographs. It involves an efficient contrast enhancement and segmentation technique for isolating the weld defect to its true size. In this work, wavelet based contrast enhancement technique has been developed to highlight the defect region from background. Biorthogonal 6.8 wavelet and Daubechies wavelet of order 4 are used for enhancing root/slag and porosity respectively. Thresholding and region growing are used for segmenting the region of interest.

Accurate defect detection via sparsity reconstruction for weld radiographs

Detecting defects in weld radiographs is an important research topic in the field of industrial non-destructive testing. Many computer-aided detection techniques have been designed for detecting defects. However, these techniques are mainly used to detect specific defective types. They cannot be applied to detect diverse types of defects, which is a difficult task because the number and types of defects in weld radiographs are generally unknown in advance, and different defects may exhibit different visual properties in shapes, sizes, textures, contrasts and positions. Inspired by the experienced workers' visual inspection mechanism, this paper develops a novel framework to detect diverse types of defects from X-ray images. In the framework, a large number of normal X-ray images are firstly collected to serve as “workers' experience” and guide the defect detection. Then, a dictionary is learned from the collected normal set. It can selectively reconstruct the background and the weld region of a test image while suppressing defective regions via sparsity reconstruction. By computing the difference image between the test image and its reconstructed image, flaws are well highlighted as the reconstruction residuals and separated from the difference image. Extensive experiments have shown that the proposed technique detects diverse defects more accurately compared with the state-of-the-art methods.

A method for increasing the objectivity of the interpretation of weld radiographs

Current radiography-based acceptance criteria do not always guarantee consistency in opinion among experts who are involved in interpretation of radiographs. To improve this consistency, which to a large extent determines the objectivity of the technique, the authors propose classification of radiographic images by shape and appearance in order to simplify weld-defect identification. The acceptance criteria of the RD-25.160.10 KTN-016-15 regulatory document for weld joints in Category 2 oil trunk lines are referred to as an example. The criteria that were developed on the basis of the image classification were used in a statistical experiment that involved six experts. The experiment showed that the number of cases of a substantial degree of consistency of the expert opinions increased by 2.2 times compared to the criteria that are currently in use.

The utilization of image subtraction and wavelet decomposition-reconstruction for improving FCM based segmentation of radiographic weld defect

The utilization of image subtraction and wavelet decomposition-reconstruction for improving FCM based segmentation of radiographic weld defect

DWT Based Automated Weld Pool Detection and Defect Characterisation from Weld Radiographs

Industrial Radiography is the most widely accepted NDT technique for weld quality in industries. As it is an indirect method, defect type and nature must be obtained by analyzing the radiographs. Manual interpretation of radiographs is subjective in nature. So the paradigm shifted to automated weld defect detection system. Though considerable research is done in automated weld defect detection, an accurate domain specific technique has not yet been evolved due to noise, artifacts in radiographs, low contrast between the defect region and the background and difficulty in isolating the defect. The proposed work aims at developing an automated weld defect detection system that enhances the contrast between the object and the background and isolates the weld defect. In this work, real time weld radiographs are acquired and contrast enhancement is performed with DWT. Slag and Porosity are isolated and dimensionally characterized.

Detection, 3-D positioning, and sizing of small pore defects using digital radiography and tracking

This article presents an algorithm that handles the detection, positioning, and sizing of submillimeter-sized pores in welds using radiographic inspection and tracking. The possibility to detect, position, and size pores which have a low contrast-to-noise ratio increases the value of the nondestructive evaluation of welds by facilitating fatigue life predictions with lower uncertainty. In this article, a multiple hypothesis tracker with an extended Kalman filter is used to track an unknown number of pore indications in a sequence of radiographs as an object is rotated. Each pore is not required to be detected in all radiographs. In addition, in the tracking step, three-dimensional (3-D) positions of pore defects are calculated. To optimize, set up, and pre-evaluate the algorithm, the article explores a design of experimental approach in combination with synthetic radiographs of titanium laser welds containing pore defects. The pre-evaluation on synthetic radiographs at industrially reasonable contrast-to-noise ratios indicate less than 1% false detection rates at high detection rates and less than 0.1 mm of positioning errors for more than 90% of the pores. A comparison between experimental results of the presented algorithm and a computerized tomography reference measurement shows qualitatively good agreement in the 3-D positions of approximately 0.1-mm diameter pores in 5-mm-thick Ti-6242.

Review on Lossless Image Compression Techniques for Welding Radiographic Images

Recent development in image processing allows us to apply it in different domains. Radiography image of weld joint is one area where image processing techniques can be applied. It can be used to identify the quality of the weld joint. For this the image has to be stored and processed later in the labs. In order to optimize the use of disk space compression is required. The aim of this study is to find a suitable and efficient lossless compression technique for radiographic weld images. Image compression is a technique by which the amount of data required to represent information is reduced. Hence image compression is effectively carried out by removing the redundant data. This study compares different ways of compressing the radiography images using combinations of different lossless compression techniques like RLE, Huffman.

Analysis of Image Segmentation for Radiographic Images

Digital image processing is used to identify regions in an image by using various segmentation methods. This paper gives a brief account on five of the different segmentation techniques namely region growing, watershed, thresholding, split and merge, k-means clustering methods highlighting the advantages as well as disadvantages of each of these methods. A modification of traditional region growing segmentation method is presented which automatically selects the seed points and grows the regions until all the regions in the image are segmented. The results of segmentation methods presented in the paper are not dependent on the kind of image to be segmented and these methods are used in segmenting industrial radiographic weld images in which several defects like porosity, lack of fusion, slag line, incomplete penetrations, and wormholes occur. The methods are evaluated on various types of images and efficiency of these methods in the detection of several weld defects is presented along with the experimental results. The evaluation of performance of these different segmentation methods on sample images is done on the basis of subjective criteria and conclusions are achieved. These methods are used to detect the flaws in an object by identifying the flawed region in the image. Due to this ability of region detection, it finds various applications in medical imaging, optical character recognition, computer vision, remote sensing, mobile robots and industrial radiography. Keywords: Image segmentation, thresholding, region growing, watershed, split and merge, k-means clustering

Digital Radiographic Image Enhancement for Weld Defect Detection using Smoothing and Morphological Transformations

Accurate inspection ofweldedmaterials is important in relation to achieve acceptable standards. Radiography, a non-destructive test method, is commonly used to evaluate the internal condition ofa material with respect to defect detection. Thepresence ofnoise in low resolution ofradiographic images significantly complicates analysis; thereforeattaining higher quality radiographic images makes defect detection more readily achievable. This paper presents a study pertaining to the quality enhancement of radiographic images with respect to different types of defects. A series of digital radiographic weld flaw images were smoothed using multiple smoothing techniques to remove inherent noise followed by top and bottom hat morphological transformations. Image quality was evaluated quantitatively with respect to SNR, PSNR andMAE. The results indicate that smoothing enhances the quality ofradiographic images, thereby promoting defect detection with the respect to original radiographic images.

X-ray modeling of realistic synthetic radiographs of thin titanium welds

This paper describes the addition and benefits of an improved detector model and a radiographic noise model to a previously developed mathematical model of a specific radiographic system. The model intentions are to simulate realistic synthetic radiographs of thin laser welded titanium welds and to act as an X-ray projection kernel in an image analysis algorithm. Both these objectives put high demands on low calculation time and to accomplish this a number of simplifications have been done. An evaluation of the tradeoff when using the simplifications is essential and simulations of specific geometries and the radiographic inspection procedure are used for this purpose. As verification the simulated radiographs are compared to real digital radiographs relevant for the proposed applications.

Digital Radiographic Image Enhancement for Weld Defect Detection using Smoothing and Morphological Transformations

Accurate inspection of welded materials is important in relation to achieve acceptable standards. Radiography, a non-destructive test method, is commonly used to evaluate the internal condition of a material with respect to defect detection. The presence of noise in low resolution of radiographic images significantly complicates analysis; therefore attaining higher quality radiographic images makes defect detection more readily achievable. This paper presents a study pertaining to the quality enhancement of radiographic images with respect to different types of defects. A series of digital radiographic weld flaw images were smoothed using multiple smoothing techniques to remove inherent noise followed by top and bottom hat morphological transformations. Image quality was evaluated quantitatively with respect to SNR, PSNR and MAE. The results indicate that smoothing enhances the quality of radiographic images, thereby promoting defect detection with the respect to original radiographic images.

Automatic Label Removal from Digitized Weld Radiographs

Kertas kerja ini membentangkan keadah mengeluarkan label secara automatik daripada radiograf kimpalan sebagai sebahagian daripada proses pengesanan kecacatan automatik. Suatu algoritma telah dibangunkan untuk mengesan dan mengeluarkan label yang tercetak pada radiograf kimpalan sebelum algoritma penyarian kimpalan dikenakan. Ujian kenormalan digunakan untuk menentukan sama ada profil keamatan selari dengan kimpalan mengandungi piksel label. Pengambangan diikuti dengan operasi mengisi kawasan dilakukan untuk mengeluarkan label. Algoritma tersebut diuji ke atas 50 radiograf kimpalan yang mempunyai label dan label pada 90% daripada imej tersebut dikeluarkan dengan jayanya. Kata kunci: Radiograpfi kimpalan, pengeluaran label, ujian kenormalan This paper presents a methodology to remove labels automatically from digitized weld radiographs as part of the automatic weld defect detection process. An algorithm was developed to detect and remove labels printed onto weld radiographs before weld extraction algorithm or defect detection algorithm is applied. Normality test was used to determine if the intensity profile parallel to the weld contains label pixels. Thresholding followed by region filling operations were carried out to remove the labels. The algorithm was tested on 50 weld radiographs with labels and the labels on 90% of these images were successfully removed. Key words: Weld radiography, label removal, normality test

A novel method for detection and quantification of incomplete penetration type flaws in weldments

This paper presents an image processing approach to process incomplete penetration type flaws in radiographic images of the weld specimens considering morphological aspects of the image. In the present approach, radiographic weld image is processed to get the image with good contrast and reduced noise using image enhancement techniques like histogram equalization and noise filtering. This is followed by an effe ctive edge detector such as Canny operator to find the edges of flaws, which are further used to segment the image to fix the bou ndaries. Image segmentation is performed using morphological approach implemented through dilation of similar boundaries and erosion of dissimilar and irrelevant boundaries decided on the basis of pixel characteristics. The incomplete penetra tion type flaws are clearly identifiable in the finally process ed image, which is obtained by superimposing the segmented image over the original enhanced image. The experimental results proved that proposed approach can be used as a reliable method for automatic detection of incomplete penetration types of flaws i n radiographic weld images.