Weld Defect Detection Research Articles

In-process calibration of a non-destructive testing system used for in-process inspection of multi-pass welding

In multi-pass welding, there is increasing motivation to move towards in-process defect detection to enable real-time repair; thus avoiding deposition of more layers over a defective weld pass. All defect detection techniques require a consistent and repeatable approach to calibration to ensure that measured defect sizing is accurate. Conventional approaches to calibration employ fixed test blocks with known defect sizes, however, this methodology can lead to incorrect sizing when considering complex geometries, materials with challenging microstructure, and the significant thermal gradients present in materials during the inter-pass inspection period. To circumvent these challenges, the authors present a novel approach to calibration and introduce the concept of in-process calibration applied to ultrasonic Non-Destructive Testing (NDT). The new concept is centred around the manufacturing of a second duplication sample, containing intentionally-embedded tungsten inclusions, with identical process parameters as the main sample. Both samples are then inspected using a high-temperature robotic NDT process to allow direct comparative measurements to be established between the real part and the calibration sample. It is demonstrated that in-process weld defect detection using the in-process calibration technique can more reliably identify defects in samples which would otherwise pass the acceptance test using a traditional calibration.

Classification of Welding Defects Using Gray Level Histogram Techniques via Neural Network. (Dept. M. ( Production ) )

window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag("js", new Date()); gtag("config", "UA-72322659-1");

Application Research on Ultrasonic Phased Array Technology in Weld Seam Inspection

Welding seams are prone to safety accidents and failures during actual operation, which has an adverse effect on the economic benefits of the enterprise. When using traditional ultrasonic inspection methods to inspect the pipe butt welds, the staff needs to use the inspection probe to move as needed, which makes the inspection process difficult to operate and is greatly affected by human factors. The beam of conventional ultrasound cannot be deflected and focused. It is difficult to detect parts with complex geometric shapes and large anisotropic welds. Ultrasonic phased array is a new type of non-destructive testing method, which makes up for the limitations of conventional ultrasonic testing, and has great advantages compared with conventional ultrasound. Therefore, in order to reduce the misjudgment of defects caused by humans, this paper studies the application method of ultrasonic phased array technology in weld inspection, discusses the principles and characteristics of ultrasonic phased array inspection technology in nondestructive testing, and the defects were tested. The test results show that the phased array technology can effectively detect weld defects.

Arc sound model for pulsed GTAW and recognition of different penetration states

Weld defect detection based on arc sound signal in pulsed gas tungsten arc welding (GTAW) has been a hot research topic in industry and academia. However, arc vocal mechanism model of pulsed GTAW remains to be studied further. In this paper, a sensing system is developed to collect arc voltage, welding current, arc sound, and weld pool images synchronously during pulsed GTAW process. Theoretical researches and experiments verify that the arc sound signal of pulsed GTAW is proportional to the change rate of the instantaneous arc power input. Furthermore, an arc sound excitation model is proposed to explain the mechanism of arc sound signal. The model inputs are arc voltage and welding current; the model output is the arc sound signal. The experiments prove that the proposed excitation model is a non-linear model. Therefore, a dynamic long short-term memory (DLSTM) network model is designed to identify the non-linear model. Furthermore, the effects of different penetration states on arc sound signal are discussed in combination with the proposed arc sound excitation model. Finally, a novel method based on DLSTM model is built to recognize different penetration states: lack of fusion, normal penetration, and burn through. The proposed method was verified to be effective with high accuracy and robustness.

Application of USCCD on Girth Weld Defect Detection of Oil Pipelines

Globally, more and more attention has been paid to the integrity of Girth Welds (GW) of oil and gas pipelines due to their failures with high consequences. A primary concern is that defects originate during field construction but over time may be subject to external loads due to earth movement. GW defects in newly built pipelines are also assumed to exist but would be much smaller in size, and more difficult to detect, which motivated the investigation into minimum defect detection capabilities of the inspection technologies. This study presents the evaluation results of UltraScan™ Circumferential Crack-Like Detection (USCCD) technology for oil pipeline GW inspection, based upon the pull test and in field data from Inline Inspection (ILI) of pipeline by PetroChina Pipeline Company (PPC) using GE PII (General Electric Company, Pipeline Integrity Inspection) 32” UltraScan™ CCD Tool. The performance of USCCD is given according to the ILI data, pull test results and dig NDE (Non-Destructive Examination). It can be concluded that crack-like defects with clear edges can be detected during ultrasonic propagation; however, the irregular shape of weld makes the inspection more difficult. It is still a challenge to identify the type of defects, and depth sizing can only be classified not quantified, which would require more excavations. However, this technology is feasible for the alternative technology of GW defect inspection.

Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural Network

In the process of welding zinc-coated steel, zinc vapor causes serious porosity defects. The porosity defect is an important indicator of the quality of welds and degrades the durability and productivity of the weld. Therefore, this study proposes a deep neural network (DNN)-based non-destructive testing method that can detect and predict porosity defects in real-time, based on welding voltage signal, without requiring additional device in gas metal arc welding (GMAW) process. To this end, a galvannealed hot-rolled high-strength steel sheet applied to automotive parts was used to measure process signals in real-time. Then, feature variables were extracted through preprocessing, and correlation between the feature variables and weld porosity was analyzed. The proposed DNN based framework outperformed the artificial neural network (ANN) model by 15% or more. Finally, an experiment was conducted by using the developed porosity detection and prediction system to evaluate its field application.

Review on Computer Aided Weld Defect Detection from Radiography Images

The weld defects inspection from radiography films is critical for assuring the serviceability and safety of weld joints. The various limitations of human interpretation made the development of innovative computer-aided techniques for automatic detection from radiography images an interest point of recent studies. The studies of automatic defect inspection are synthetically concluded from three aspects: pre-processing, defect segmentation and defect classification. The achievement and limitations of traditional defect classification method based on the feature extraction, selection and classifier are summarized. Then the applications of novel models based on learning(especially deep learning) were introduced. Finally, the achievement of automation methods were discussed and the challenges of current technology are presented for future research for both weld quality management and computer science researchers.

광-적외선열화상에 의한 차량 도막 이면 용접 결함 검출에 대한 신호응답대비 메커니즘

광-적외선열화상에 의한 차량 도막 이면 용접 결함 검출에 대한 신호응답대비 메커니즘

Real-time seam defect identification for Al alloys in robotic arc welding using optical spectroscopy and integrating learning

Accurate on-line weld defect detection in robotic arc welding manufacturing is still challenging, due to the complexity and diversity of weld defects. In this study, a new real-time defect identification method is proposed for Al alloys in robotic arc welding, using arc optical spectroscopy and an integrated learning method. Spectrum feature was extracted, based on the absolute coefficients of the principal components. Feature importance was quantitatively evaluated using the mean decrease accuracy of Principal Component Analysis-Random Forest (PCA-RF). A new indicator, e.g., Importance Factor, was proposed, based on the variance of the out-of-bag test error of RF to select the optimal feature subset. The proposed PCA-RF proved to effectively identify five classes of weld defects with better performance than support vector machine and back propagation neural network. Finally, the selection pattern of spectrum feature subset was investigated, before revealing the correlation mechanism of the selected lines spectrum and weld process.

Deep Learning Technology for Weld Defects Classification Based on Transfer Learning and Activation Features

Weld defects detection using X‐ray images is an effective method of nondestructive testing. Conventionally, this work is based on qualified human experts, although it requires their personal intervention for the extraction and classification of heterogeneity. Many approaches have been done using machine learning (ML) and image processing tools to solve those tasks. Although the detection and classification have been enhanced with regard to the problems of low contrast and poor quality, their result is still unsatisfying. Unlike the previous research based on ML, this paper proposes a novel classification method based on deep learning network. In this work, an original approach based on the use of the pretrained network AlexNet architecture aims at the classification of the shortcomings of welds and the increase of the correct recognition in our dataset. Transfer learning is used as methodology with the pretrained AlexNet model. For deep learning applications, a large amount of X‐ray images is required, but there are few datasets of pipeline welding defects. For this, we have enhanced our dataset focusing on two types of defects and augmented using data augmentation (random image transformations over data such as translation and reflection). Finally, a fine‐tuning technique is applied to classify the welding images and is compared to the deep convolutional activation features (DCFA) and several pretrained DCNN models, namely, VGG‐16, VGG‐19, ResNet50, ResNet101, and GoogLeNet. The main objective of this work is to explore the capacity of AlexNet and different pretrained architecture with transfer learning for the classification of X‐ray images. The accuracy achieved with our model is thoroughly presented. The experimental results obtained on the weld dataset with our proposed model are validated using GDXray database. The results obtained also in the validation test set are compared to the others offered by DCNN models, which show a best performance in less time. This can be seen as evidence of the strength of our proposed classification model.

In-situ measurement of weld quality during MAG welding using laser ultrasonic

ABSTRACT Laser ultrasonic technique (LUT) is applicable for measurement under high temperature condition because of the non-contact and remoteness. In this study, LUT was applied to detection the welding defect such as solidification crack and/or lack of penetration at single bevel groove during Gas Metal Arc (GMA) welding process. Nanosecond pulse laser (1064 nm, 60 mJ/pulse 100 Hz) was used to generate ultrasonic, and was scanned using a galvanometer mirror. Nd:YAG laser interferometer (532 nm, 1 W) was used for detection the surface micro vibration caused by arrival of ultrasonic wave. After acquiring the B-scope, which is composed of multi transmit- and receive-points, the synthetic aperture focusing technique (SAFT) is applied. SAFT image obtained by in-process measurement was evaluated to confirm the presence or absence of welding defect indication. As a result, it was possible to indicate the solidification crack and the lack of penetration in the joint even during the welding process. Furthermore, it was able to indicate the penetration depth change (2 mm difference) due to the welding condition change during process. These results suggest that in-process measurement using LUT is very effective technique for detecting weld defects.

An Effective Method of Weld Defect Detection and Classification Based on Machine Vision

In order to effectively identify and classify weld defects of thin-walled metal canisters, a weld defect detection and classification algorithm based on machine vision is proposed in this paper. With the weld defects categorized, a modified background subtraction method based on Gaussian mixture models, is proposed to extract the feature areas of the weld defects. Then, we design an algorithm for weld detection and classification according to the extracted features. Next, by using the weld images sampled by the constructed weld defect detection system on a real-world production line, the parameters of the weld defect classifiers are determined empirically. Experimental results show that the proposed methods can identify and classify the weld defects with more than 95% accuracy rate. Moreover, the weld detection results obtained in the actual production line show that the detection and classification accuracy can reach more than 99%, which means that the system enhanced with the proposed method can meet the requirements for the best real-time and continuous weld defect detection systems available nowadays.

A Smart Monitoring System for Automatic Welding Defect Detection

This paper introduces an intelligent system able to perform quality control assessment in an industrial production line. Deep learning techniques are employed and proved successful in a real application for the inspection of welding defects on an assembly line of fuel injectors. Starting from state-of-the-art deep architectures and using the transfer learning technique, it is possible to train a network with about 7 million parameters using a reduced number of injector's images, obtaining an accuracy of 97.22%. The system is also configured in order to exploit new data, collected during operation, to extend the existing dataset and to improve further its performance. The developed system shows that deep neural networks can successfully perform quality inspection tasks that are usually demanded to humans.

Elucidation of magnetic flux leakage for welding defect detection at different magnetic field directions through alternating magnetic field measurement

Alternating current field measurement (ACFM) is a technology for detecting magnetic flux leakage (MFL) using a magnetic sensor and is often used to detect welding defects. An alternating magnetic field was generated under the excitation of an alternating electric field. The magnetic field direction of an alternating magnetic field changes with time and the size and direction of the leakage magnetic field on the weldment also change periodically. In order to verify this rule, the distribution of the leakage magnetic field in different magnetisation directions was analysed through simulation and experiment. The simulation results show that when sinusoidal excitation is applied to the coil, the direction of magnetisation changes with time and the magnetic field density (B) gradually changes periodically on the weldment. This was verified through related experiments. When the surface of the weldment had welding defects, the dynamic magneto-optical image was captured in different magnetisation directions. Welding defects have different magneto-optical images in different frames, which can present more information for the same defect. In addition, in the experiment, the correlation between the grey-level co-occurrence matrix (GLCM) of magneto-optical images in different magnetisation directions and that of the leakage magnetic field in the corresponding direction was analysed. Simulations and experiments were performed on different types of welding defect. It was found that the trend of characteristics for the leakage magnetic fields was similar to that of the characteristics for the grey-level co-occurrence matrix of the magneto-optical images. The results show that the characteristics of the leakage magnetic field can reflect the texture features of the welding defect.

Formation mechanism of SH guided wave in weld seam

Shear horizontal (SH)-guided wave detection of weld seams is a new type of weld detection technology. To better apply SH-guided waves to weld detection, it is necessary to study the formation mechanism of SH-guided waves and to identify weld structures suitable for SH-guided wave detection. Here, we used the theory of peridynamics as well as the reflection and refraction of SH-guided waves in different media. Theoretical analysis suggested that the formation of an SH-guided wave is related to the incident angle of the guided wave, and the formation of SH-guided waves is related to the weld height and the weld interface. The influence of different weld heights and weld interfaces on the formation of SH-guided waves was studied by numerical simulation. We concluded that the weld height is beneficial to the formation of the guided wave because the strength of guided wave in weld seam and steel plate can reflect the refraction and reflection characteristics of the SH wave. More energy is trapped in the weld with increasing weld height, and the radiation rate of SH-guided waves linearly decreases. Higher welds will disperse the SH-guided waves and confuse the signals. This makes the echo subtle and is not conducive to the detection of weld defects. Therefore, we concluded that weld heights over 5% of the weld width are more conducive to detection of weld defects. After analysis of the weld interface, we concluded that the radiation rate of SH-guided waves in a U-type interface and V-type interface are much higher than those a type II interface: These are not conducive to the formation of weld-guided waves and lead to low sensitivity for SH-guided wave detection.

Piping and Pressure Vessel Welding Automation through Adaptive Planning and Control

Welding automation is a pathway to reducing costs in the energy sector and dependence on certified welders, who are in short supply. Recent research into system-level automation of multibead/layer Tungsten Inert Gas welding for stainless-steel components is presented. Automation is pursued for weld planning, execution, and defect detection. Planning utilizes active seam/groove sensing and intuitive weld bead positioning. Bead and layer geometries are estimated using weld bead shape prediction that takes into account process parameters. After the first weld layer, subsequent trajectory plans are adapted to compensate for differences between the planned and actual weld surface. Sensor-based, closed-loop control of the process is being pursued to compensate for gravitational effects. Continuous monitoring of the real-time process to predict/detect the occurrence of welding defects is in development. Near-real-time defect detection provides the opportunity for immediate evaluation and correction, reducing costly repairs. Preliminary experimental results are presented.

Ultrasonic multi-view total focusing method for weld defect detection on small-diameter austenitic stainless steel tubes

Austenitic stainless steels are widely used in the key components of major equipment and the welds can be the weakest parts of equipment made with these materials. Ultrasonic waves propagate in austenitic stainless steel welds with multiple paths and modes. This study employed a multi-view total focusing method using an ultrasonic phased array for defect detection in the welds of small-diameter austenitic stainless steel pipes. The detection capability of four different direct wave modes and eight different half-skip wave modes for typical defects were compared and analysed through numerical simulation. A fusion imaging method was developed using the preferred direct and half-skip wave modes. The process was further verified with a weld defect detection experiment carried out on small-diameter austenitic stainless steel pipes. The results show that the multi-view total focusing method can efficiently detect the defects in the welds of small-diameter tubes. Compared with the single-mode imaging method, the fusion total focusing imaging approach can not only improve the signal-to-noise ratio but can also reduce the number of image artefacts.

Welding defect detection based on local image enhancement

Welding defect detection in a radiographic image is an important topic in the field of industrial non-destructive testing. To improve the accuracy of welding defect segmentation, a local image enhancement approach is proposed. In this algorithm, the requirement of contrast enhancement is considered when extracting the weld seam and segmenting the weld defect. The whole defect detection is conducted by three procedures: image enhancement, welding seam extraction, and defect segmentation. Firstly, a method for determining the Localised Pixel Inhomogeneity Factor (LPIF) is proposed. Then, based on the results of LPIF, the Otsu method is applied to segment the welding seam and defects are, identified by region growing algorithm. The authors compared LPIF with histogram equalisation, adaptive histogram equalisation, and contrast-limited adaptive histogram equalisation algorithms and assessed its performance by using indicators such as image contrast, image definition, and edge intensity. Moreover, the authors compared the segmentation results of the enhanced defect images with the original image to further study the method's effect on weld defect segmentation. More than 70 images containing various types of defects are tested. The experimental results demonstrate that the quality of enhanced defect images is improved significantly, and has a high relative segmentation accuracy of more than 92%.

Data-Driven Detection of Laser Welding Defects Based on Real-Time Spectrometer Signals

The spectrometer is applied in this paper to get the in-process information of welding defects during the high-power disk laser welding process. The high-dimensional signal captured by the spectrometer is fed into a data-driven framework based on stacked auto-encoder (SAE) to automatically extract salient features for performing real-time welding defects detection. The particle swarm optimization (PSO) algorithm is employed to optimize the proposed data-driven framework by acquiring the global optimal parameters to strengthen its capability in extracting the representative features from the original high-dimensional signal. The extracted features are classified by a softmax classifier to get the real-time identifications of the welding defects. The proposed framework is compared with the conventional shallow artificial intelligent methods, such as back-propagation (BP) neural network and support vector machine (SVM), and reveals better performance. The actual welding experiments under different welding parameters are implemented to validate the detection accuracy of our proposed data-driven framework. This paper provides an effective framework for the detection of the high-power disk laser welding status in real-time.

A spectroscopic method based on support vector machine and artificial neural network for fiber laser welding defects detection and classification

Diverse welding processes have been utilized in manufacturing industry for years. But up to date, welding quality still cannot be guaranteed, due to the lack of an efficient and on-line welding defects monitoring method, and this leads to increased manufacturing costs. In this paper, a method based on feature extraction and machine learning algorithm for on-line quality monitoring and defects classification was presented. Plasma radiation was captured by an optical fiber probe, and delivered by an optical fiber to the spectrometer. The captured spectral signal was processed by selecting sensitive emission lines and extracting features of spectral data's evolution, which realized spectral data compression with low computational cost. After selecting the proper training data set, the designed ANN and SVM allows automatic detection and classification of welding defects. The validity of proposed method was successfully approved by test data set in welding experiments. Welding experiments on galvanized steel sheets showed the corresponding relationship between the output of classifiers and welding defects. Finally, the two classifiers were compared. Experiments indicated the performance of ANN is slightly better than that of SVM, while both of them have its own advantages.