To solve the problem of low detection accuracy for complex weld defects,the paper proposes a weld defects detection method based on improved YOLOv5s.To enhance the ability to focus on key information in feature maps,t...To solve the problem of low detection accuracy for complex weld defects,the paper proposes a weld defects detection method based on improved YOLOv5s.To enhance the ability to focus on key information in feature maps,the scSE attention mechanism is intro-duced into the backbone network of YOLOv5s.A Fusion-Block module and additional layers are added to the neck network of YOLOv5s to improve the effect of feature fusion,which is to meet the needs of complex object detection.To reduce the computation-al complexity of the model,the C3Ghost module is used to replace the CSP2_1 module in the neck network of YOLOv5s.The scSE-ASFF module is constructed and inserted between the neck network and the prediction end,which is to realize the fusion of features between the different layers.To address the issue of imbalanced sample quality in the dataset and improve the regression speed and accuracy of the loss function,the CIoU loss function in the YOLOv5s model is replaced with the Focal-EIoU loss function.Finally,ex-periments are conducted based on the collected weld defect dataset to verify the feasibility of the improved YOLOv5s for weld defects detection.The experimental results show that the precision and mAP of the improved YOLOv5s in detecting complex weld defects are as high as 83.4%and 76.1%,respectively,which are 2.5%and 7.6%higher than the traditional YOLOv5s model.The proposed weld defects detection method based on the improved YOLOv5s in this paper can effectively solve the problem of low weld defects detection accuracy.展开更多
Imbalanced data distribution stands as the primary cause of performance deterioration in the majority of supervised classification algorithms.The current publicly available weld defect datasets are very limited,and th...Imbalanced data distribution stands as the primary cause of performance deterioration in the majority of supervised classification algorithms.The current publicly available weld defect datasets are very limited,and the samples of various defects are seriously imbalanced.The paper proposes an improved deep convolution generative adversarial network(DCGAN)to balance the weld defect dataset.To solve the problem of poor diversity in the samples generated by the traditional DCGAN,a C-Res unit is constructed,which integrates the convolutional block attention module(CBAM)into the residual block.The transposed convolution in the DCGAN's generator is replaced with the constructed C-Res unit to enhance the attention to image details and improve the stability and learning efficiency of the model.The Pixelshuffle module is added into the generator as the upsampling module to solve the problem that the C-Res unit can't up-sample like the transposed convolution.CBAM is added into the DCGAN's discriminator to further enhance the discriminator's ability to judge the quality of the generated sample.To validate the effectiveness of the improved DCGAN,comparison experiments are carried out.The weld defect dataset is balanced by DCGAN and improved DCGAN,respectively,and then YOLOv8s-cls is used to classify the weld defect sample based on the original dataset,the dataset balanced by the DCGAN,and the dataset balanced by the improved DCGAN,respectively.Among the nine F1 scores of the nine types of samples,seven of them are higher than those of YOLOv8s-cls trained with the original dataset,and six of them are higher than those of YOLOv8s-cls trained with the dataset balanced by the traditional DCGAN.The experiments reveal that the weld defect dataset balanced with improved DCGAN can enhance the performance of the supervised classification model,and is helpful to realize automation of weld defect detection.展开更多
A first and effective method is proposed to detect weld deject adaptively in various Dypes of real-time X-ray images obtained in different conditions. After weld extraction and noise reduction, a proper template of me...A first and effective method is proposed to detect weld deject adaptively in various Dypes of real-time X-ray images obtained in different conditions. After weld extraction and noise reduction, a proper template of median filter is used to estimate the weld background. After the weld background is subtracted from the original image, an adaptite threshold segmentation algorithm is proposed to obtain the binary image, and then the morphological close and open operation, labeling algorithm and fids＇e alarm eliminating algorithm are applied to pracess the binary image to obtain the defect, ct detection result. At last, a fast realization procedure jbr proposed method is developed. The proposed method is tested in real-time X-ray image,s obtairted in different X-ray imaging sutems. Experiment results show that the proposed method is effective to detect low contrast weld dejects with few .false alarms and is adaptive to various types of real-time X-ray imaging systems.展开更多
The visual automatic detection method based on artificial intelligence has attracted more and more attention. In order to improve the performance of weld nondestructive defect detection,we propose DRepDet(Dilated RepP...The visual automatic detection method based on artificial intelligence has attracted more and more attention. In order to improve the performance of weld nondestructive defect detection,we propose DRepDet(Dilated RepPoints Detector). First, we analyze the weld defect dataset in detail and summarize the distribution characteristics of weld defect data, that is, the defect scale is very different and the aspect ratio distribution range is large. Second, according to the distribution characteristics of defect data, we design DResBlock module, and introduce dilated convolution with different dilated rates in the process of feature extraction to expand the receptive field and improve the detection performance of large-scale defects. Based on DResBlock and anchor-free detection framework RepPoints, we design DRepDet. Extensive experiments show that our proposed detector can detect 7 types of defects. When using combined dilated rate convolution network in detection, the AP50 and Recall50 of big defects are improved by 3.1% and 3.3% respectively, while the performance of small defects is not affected, almost the same or slightly improved. The final performance of the whole network is improved a large margin,with 6% AP50 and 4.2% Recall50 compared with Cascade RCNN and 1.4% AP50 and 2.9% Recall50 compared with RepPoints.展开更多
In the present study, we simulated the reel-lay installation process of deepwater steel catenary risers（SCRs） using the finite element method and proposed multiaxial fatigue analysis for reeled SCRs. The reel-lay me...In the present study, we simulated the reel-lay installation process of deepwater steel catenary risers（SCRs） using the finite element method and proposed multiaxial fatigue analysis for reeled SCRs. The reel-lay method is one of the most efficient and economical pipeline installation methods. However, material properties of reeled risers may change, especially in the weld zone, which can affect the fatigue performance. Applying finite element analysis（FEA）, we simulated an installation load history through the reel, aligner, and straightener and analyzed the property variations. The impact of weld defects during the installation process, lack of penetration and lack of fusion, was also discussed. Based on the FEA results, we used the Brown-Miller criterion combined with the critical plane approach to predict the fatigue life of reeled and non-reeled models. The results indicated that a weld defect has a significant influence on the material properties of a riser, and the reel-lay method can significantly reduce the fatigue life of SCRs. The analysis conclusion can help designers understand the mechanical performance of welds during reel-lay installation.展开更多
Support vector machines（SVM） received wide attention for its excellent ability to learn, it has been applied in many fields. A review of the application of SVM in weld defect detection and recognition of X-ray image...Support vector machines（SVM） received wide attention for its excellent ability to learn, it has been applied in many fields. A review of the application of SVM in weld defect detection and recognition of X-ray image is been presented. We will show some commonly used methods of weld defect detection and recognition using SVM, and the advantages and disadvantages of each method will be discussed. SVM appears to be promising in weld defect detection and recognition, but future research is needed before it fully mature in this filed.展开更多
Luminosity and contrast variation problems are among the most challenging tasks in the image processing field,significantly improving image quality.Enhancement is implemented by adjusting the dark or bright intensity ...Luminosity and contrast variation problems are among the most challenging tasks in the image processing field,significantly improving image quality.Enhancement is implemented by adjusting the dark or bright intensity to improve the quality of the images and increase the segmentation performance.Recently,numerous methods had been proposed to normalise the luminosity and contrast variation.A new approach based on a direct technique using statistical data known as Hybrid Statistical Enhancement(HSE)is presented in this study.TheHSE method uses themean and standard deviation of a local and global neighbourhood and classified the pixel into three groups;the foreground,border,and problematic region(contrast&luminosity).The datasets,namely weld defect images,were utilised to demonstrate the effectiveness of the HSE method.The results from the visual and objective aspects showed that the HSE method could normalise the luminosity and enhance the contrast variation problem effectively.The proposed method was compared to the two(2)populor enhancement methods which is Homomorphic Filter(HF)and Difference of Gaussian(DoG).To prove the HSE effectiveness,a few image quality assessments were presented,and the results were discussed.The HSE method achieved a better result compared to the other methods,which are Signal Noise Ratio(8.920),Standard Deviation(18.588)and Absolute Mean Brightness Error(9.356).In conclusion,implementing the HSE method has produced an effective and efficient result for background correction and quality images improvement.展开更多
Structural integrity isstated as the science and technology of margin between safety and disaster. Systematic prediction of structural integrity of critical structures such ascombustion chambers,pressure vessels,nucle...Structural integrity isstated as the science and technology of margin between safety and disaster. Systematic prediction of structural integrity of critical structures such ascombustion chambers,pressure vessels,nuclear reactor components,boilers etc.,ensures the human safety,environmental protection,and the economical considerations.The present work aims at prediction of fatigue behaviour of symmetric structures like pressure vessels in the presence of common welding defects such as lack of fusion( LOF),lack of penetration( LOP) and porosity.A ring type specimen which replicates the stress pattern in thepressure vessel is considered for the study of severity of weld imperfections. Initial dimensions of weld defects are arrived by performing NDT inspection.Crack growth analysis is carried out to determine the remaining life of the welded joint with defects.展开更多
This paper proposes a machine-learning-based methodology to automatically classify different types of steel weld defects,including lack of the fusion,porosity,slag inclusion,and the qualified(no defects)cases.This met...This paper proposes a machine-learning-based methodology to automatically classify different types of steel weld defects,including lack of the fusion,porosity,slag inclusion,and the qualified(no defects)cases.This methodology solves the shortcomings of existing detection methods,such as expensive equipment,complicated operation and inability to detect internal defects.The study first collected percussed data from welded steel members with or without weld defects.Then,three methods,the Mel frequency cepstral coefficients,short-time Fourier transform(STFT),and continuous wavelet transform were implemented and compared to explore the most appropriate features for classification of weld statuses.Classic and convolutional neural network-enhanced algorithms were used to classify,the extracted features.Furthermore,experiments were designed and performed to validate the proposed method.Results showed that STFT achieved higher accuracies(up to 96.63%on average)in the weld status classification.The convolutional neural network-enhanced support vector machine(SVM)outperformed six other algorithms with an average accuracy of 95.8%.In addition,random forest and SVM were efficient approaches with a balanced trade-off between the accuracies and the computational efforts.展开更多
There are many flaws in welding images such as noise, low contrast, and blurred edges, which affect feature extraction from welding defect regions and impede classification and recognition of welding defects. To deal ...There are many flaws in welding images such as noise, low contrast, and blurred edges, which affect feature extraction from welding defect regions and impede classification and recognition of welding defects. To deal with the complexity of welding defect images, this paper proposes an effective method for extracting the features of welding defect regions. Firstly, image preprocessing, image segmentation and image background removal are carried out to a welding image in order to extract welding defect region; and then an 8-connected-component labeling method is used to mark defect regions. Finally, it extracts geometric characteristic parameters including perimeter, area, circularity and others. The experimental result shows that the method proposed in the paper can accurately extract the features of welding defect regions. It has good adaptability and practicability.展开更多
With von Mises yield criterion,the loading range of Net Section Collapse(NSC) Criteria is extended from combined tension and bending loadings to combined bending,torsion and internal pressure loadings.A new theoretica...With von Mises yield criterion,the loading range of Net Section Collapse(NSC) Criteria is extended from combined tension and bending loadings to combined bending,torsion and internal pressure loadings.A new theoretical analyzing method of plastic limit load for pressure pipe with incomplete welding defects based on the extended NSC Criteria is presented and the correlative formulas are deduced,the influences of pipe curvature,circumferential length and depth of incomplete welding defects on the plastic limit load of pressure pipe are considered as well in this method.Meanwhile,according to the orthogonal experimental design method,the plastic limit loads are calculated by the finite element method and compared with the theoretical values.The results show that the expressions of plastic limit load of pressure pipe with incomplete welding defects under bending,torsion and internal pressure based on extended NSC criteria are reliable.The study provides an important theoretical basis for the establishment of safety assessment measure towards pressure pipe with incomplete welding defects.展开更多
In order to reduce noise effectively in the welding defect image and preserve the minutiae information, a noise reduction method of welding defect image based on nonsubsampled contourlet transform(NSCT) and anisotropi...In order to reduce noise effectively in the welding defect image and preserve the minutiae information, a noise reduction method of welding defect image based on nonsubsampled contourlet transform(NSCT) and anisotropic diffusion is proposed. Firstly, an X-ray welding defect image is decomposed by NSCT. Then total variation(TV) model and Catte_PM model are used for the obtained low-pass component and band-pass components, respectively. Finally, the denoised image is synthesized by inverse NSCT. Experimental results show that, compared with the hybrid method of wavelet threshold shrinkage with TV diffusion, the method combining NSCT with P_Laplace diffusion, and the method combining contourlet with TV model and adaptive contrast diffusion, the proposed method has a great improvement in the aspects of subjective visual effect, peak signal-to-noise ratio(PSNR) and mean-square error(MSE). Noise is suppressed more effectively and the minutiae information is preserved better in the image.展开更多
The groove defect formed in the friction stir welding dramatically deteriorates weld appearances and mechanical properties of the joints owing to its larger size and penetration. Therefore, the friction stir repair we...The groove defect formed in the friction stir welding dramatically deteriorates weld appearances and mechanical properties of the joints owing to its larger size and penetration. Therefore, the friction stir repair welding was utilized to remove such a groove defect, and the focus was placed on the mechanical properties and microstructural characteristics of the repair joints so as to obtain an optimum repair welding process. The experimental results indicate that the groove defect can be removed by friction stir repair welding, and the offset repair welding process is superior to the symmetrical repair welding process. In the symmetrical repair welding process, a large number of fine cavity defects and an obvious aggregation of hard-brittle phase Al2Cu occur, accordingly the mechanical properties of the repair joint are weakened, and the fracture feature of repair joint is partially brittle and partially plastic. A good-quality repair joint can be obtained by the offset repair welding process, and the repair joint is fractured near the interface between the weld nugget zone and thermal-mechanically affected zone.展开更多
The mechanical properties of welded joints in resistance spot welding of DP780 steel were tested,and three different types of welding cracks in welded joints were investigated by optical microscopy,scanning electron m...The mechanical properties of welded joints in resistance spot welding of DP780 steel were tested,and three different types of welding cracks in welded joints were investigated by optical microscopy,scanning electron microscopy and electron back-scattered diffraction.Finally,the failure mode of the welded joints in shear tensile test was discussed.It is found the shear tensile strength of welded joints can be greatly improved by adding preheating current or tempering current.The surface crack in welded joint is intergranular fracture,while the inner crack in welded joint is transgranular fracture,and the surface crack on the edge of the electrode imprint can be improved by adding preheating current or tempering current.The traditional failure mode criterion advised by American Welding Society is no longer suitable for DP780 spot welds and the critical nugget size suggested by Pouranvari is overestimated.展开更多
Currently, the welding defects recognition of X-ray nondestructive inspection is principally carried out by manual work, which highly depends on the experience of the inspectors and costs plenty of workload. In this p...Currently, the welding defects recognition of X-ray nondestructive inspection is principally carried out by manual work, which highly depends on the experience of the inspectors and costs plenty of workload. In this paper, an intelligent image processing and recognition method for the tube welding radiographic testing in large-scale pressure vessels is proposed. Firstly, the raw image is preprocessed by median filtering, pseudo point removing and non-lincar image enhancement. Secondly, the welded joints parts are separated from the whole image by edge detection and threshold segmentation algorithms. Then, the separated images are handled by FFT transformation. Finally, whether defects exist and the specific type of defects are judged by Support Vector Machine. Software developed basing on this method works stably on site, and experiments demonstrate that the recognition results are compliance with the JB/T 4730. 2 or ASME standards.展开更多
Feature extraction and selection from signals is a key issue for metal magnetic memory testing technique. In order to realize the classification of metal magnetic memory signals of welding defects, four fractal analys...Feature extraction and selection from signals is a key issue for metal magnetic memory testing technique. In order to realize the classification of metal magnetic memory signals of welding defects, four fractal analysis methods, such as box- counting, detrended fluctuation, minimal cover and rescaled-range analysis, were used to extract the feature signal after the original metal magnet memory signal was de-noising and differential processing, then the Karhunen-Lo^e transformation was adopted as classification tool to identify the defect signals. The result shows that this study can provide an efficient classification method for metal magnetic memory signal of welding defects.展开更多
With the increase of surface assembly density and the rapid development of surface mount technology (SMT), electronic products tend to be miniaturized and integrated. The welding quality and welding technology of surf...With the increase of surface assembly density and the rapid development of surface mount technology (SMT), electronic products tend to be miniaturized and integrated. The welding quality and welding technology of surface mount components have attracted more and more attention. Reflow processing technology is a comprehensive scientific research. There are many reasons for the welding quality defects of each electronic component. Any material performance change or unreasonable processing parameters may lead to hidden welding quality defects. Therefore, in the specific production process, it is necessary to make in-depth analysis of practical problems and constantly improve the reflow soldering process, so as to improve the reflow soldering quality, ensure the up-to-standard rate of new products and improve the stability of electronic products and commodity quality.展开更多
Abstract Horizontal welding is important for heavy or huge welding structures. Keyhole mode variable polarity plasma arc welding of aluminum alloy plates with medium thickness was carried out in horizontal position. T...Abstract Horizontal welding is important for heavy or huge welding structures. Keyhole mode variable polarity plasma arc welding of aluminum alloy plates with medium thickness was carried out in horizontal position. The characteristic of welding defects was introduced. Preliminary experiments indicated that the undercut defect could not be eliminated easily. The relationship between welding parameters and the undercut defect showed that this deject could be lessened by using higher heat input. The fluid flow of weld pool was observed by a high speed camera. The fluid flow in weld pool was not symmetric and much of molten metal gathered in the lower part. The fluid flow velocity in the lower part was bigger than that in the upper part. To this end, the formative mechanism of the undercut defect was proposed. The flowability of the molten metal was an influential factor for the undercut defect. A preheating method was designed to verify the formative mechanism.展开更多
9. 6 mm thick 1060-H24 aluminum alloy plates were friction stir welded and the influencing factors on groove and tunnel defects were examined. Results show that the welding speed range for achieving a groove-free join...9. 6 mm thick 1060-H24 aluminum alloy plates were friction stir welded and the influencing factors on groove and tunnel defects were examined. Results show that the welding speed range for achieving a groove-free joint is enlarged with increasing the rotating speed. The tunnel size decreases with decreasing the welding speed under the same rotating speed. Excessive or insufficient shoulder plunge depth will cause defective joints. At a relatively low rotating speed and high welding speed, the tool having a larger shoulder diameter has a larger range of processing parameters to obtain a groove-free joint. Moreover, the tensile fracture behaviors of the defective and defect-free samples are different.展开更多
基金supported by Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX24_4084).
文摘To solve the problem of low detection accuracy for complex weld defects,the paper proposes a weld defects detection method based on improved YOLOv5s.To enhance the ability to focus on key information in feature maps,the scSE attention mechanism is intro-duced into the backbone network of YOLOv5s.A Fusion-Block module and additional layers are added to the neck network of YOLOv5s to improve the effect of feature fusion,which is to meet the needs of complex object detection.To reduce the computation-al complexity of the model,the C3Ghost module is used to replace the CSP2_1 module in the neck network of YOLOv5s.The scSE-ASFF module is constructed and inserted between the neck network and the prediction end,which is to realize the fusion of features between the different layers.To address the issue of imbalanced sample quality in the dataset and improve the regression speed and accuracy of the loss function,the CIoU loss function in the YOLOv5s model is replaced with the Focal-EIoU loss function.Finally,ex-periments are conducted based on the collected weld defect dataset to verify the feasibility of the improved YOLOv5s for weld defects detection.The experimental results show that the precision and mAP of the improved YOLOv5s in detecting complex weld defects are as high as 83.4%and 76.1%,respectively,which are 2.5%and 7.6%higher than the traditional YOLOv5s model.The proposed weld defects detection method based on the improved YOLOv5s in this paper can effectively solve the problem of low weld defects detection accuracy.
基金supported by Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX24_4084)external funding。
文摘Imbalanced data distribution stands as the primary cause of performance deterioration in the majority of supervised classification algorithms.The current publicly available weld defect datasets are very limited,and the samples of various defects are seriously imbalanced.The paper proposes an improved deep convolution generative adversarial network(DCGAN)to balance the weld defect dataset.To solve the problem of poor diversity in the samples generated by the traditional DCGAN,a C-Res unit is constructed,which integrates the convolutional block attention module(CBAM)into the residual block.The transposed convolution in the DCGAN's generator is replaced with the constructed C-Res unit to enhance the attention to image details and improve the stability and learning efficiency of the model.The Pixelshuffle module is added into the generator as the upsampling module to solve the problem that the C-Res unit can't up-sample like the transposed convolution.CBAM is added into the DCGAN's discriminator to further enhance the discriminator's ability to judge the quality of the generated sample.To validate the effectiveness of the improved DCGAN,comparison experiments are carried out.The weld defect dataset is balanced by DCGAN and improved DCGAN,respectively,and then YOLOv8s-cls is used to classify the weld defect sample based on the original dataset,the dataset balanced by the DCGAN,and the dataset balanced by the improved DCGAN,respectively.Among the nine F1 scores of the nine types of samples,seven of them are higher than those of YOLOv8s-cls trained with the original dataset,and six of them are higher than those of YOLOv8s-cls trained with the dataset balanced by the traditional DCGAN.The experiments reveal that the weld defect dataset balanced with improved DCGAN can enhance the performance of the supervised classification model,and is helpful to realize automation of weld defect detection.
文摘A first and effective method is proposed to detect weld deject adaptively in various Dypes of real-time X-ray images obtained in different conditions. After weld extraction and noise reduction, a proper template of median filter is used to estimate the weld background. After the weld background is subtracted from the original image, an adaptite threshold segmentation algorithm is proposed to obtain the binary image, and then the morphological close and open operation, labeling algorithm and fids＇e alarm eliminating algorithm are applied to pracess the binary image to obtain the defect, ct detection result. At last, a fast realization procedure jbr proposed method is developed. The proposed method is tested in real-time X-ray image,s obtairted in different X-ray imaging sutems. Experiment results show that the proposed method is effective to detect low contrast weld dejects with few .false alarms and is adaptive to various types of real-time X-ray imaging systems.
文摘The visual automatic detection method based on artificial intelligence has attracted more and more attention. In order to improve the performance of weld nondestructive defect detection,we propose DRepDet(Dilated RepPoints Detector). First, we analyze the weld defect dataset in detail and summarize the distribution characteristics of weld defect data, that is, the defect scale is very different and the aspect ratio distribution range is large. Second, according to the distribution characteristics of defect data, we design DResBlock module, and introduce dilated convolution with different dilated rates in the process of feature extraction to expand the receptive field and improve the detection performance of large-scale defects. Based on DResBlock and anchor-free detection framework RepPoints, we design DRepDet. Extensive experiments show that our proposed detector can detect 7 types of defects. When using combined dilated rate convolution network in detection, the AP50 and Recall50 of big defects are improved by 3.1% and 3.3% respectively, while the performance of small defects is not affected, almost the same or slightly improved. The final performance of the whole network is improved a large margin,with 6% AP50 and 4.2% Recall50 compared with Cascade RCNN and 1.4% AP50 and 2.9% Recall50 compared with RepPoints.
基金supported by the National Key Natural Science Foundation of China(Grant No.50739004)the National Natural Science Foundation of China(Grant Nos.51009093 and 51379005)
文摘In the present study, we simulated the reel-lay installation process of deepwater steel catenary risers（SCRs） using the finite element method and proposed multiaxial fatigue analysis for reeled SCRs. The reel-lay method is one of the most efficient and economical pipeline installation methods. However, material properties of reeled risers may change, especially in the weld zone, which can affect the fatigue performance. Applying finite element analysis（FEA）, we simulated an installation load history through the reel, aligner, and straightener and analyzed the property variations. The impact of weld defects during the installation process, lack of penetration and lack of fusion, was also discussed. Based on the FEA results, we used the Brown-Miller criterion combined with the critical plane approach to predict the fatigue life of reeled and non-reeled models. The results indicated that a weld defect has a significant influence on the material properties of a riser, and the reel-lay method can significantly reduce the fatigue life of SCRs. The analysis conclusion can help designers understand the mechanical performance of welds during reel-lay installation.
文摘Support vector machines（SVM） received wide attention for its excellent ability to learn, it has been applied in many fields. A review of the application of SVM in weld defect detection and recognition of X-ray image is been presented. We will show some commonly used methods of weld defect detection and recognition using SVM, and the advantages and disadvantages of each method will be discussed. SVM appears to be promising in weld defect detection and recognition, but future research is needed before it fully mature in this filed.
文摘Luminosity and contrast variation problems are among the most challenging tasks in the image processing field,significantly improving image quality.Enhancement is implemented by adjusting the dark or bright intensity to improve the quality of the images and increase the segmentation performance.Recently,numerous methods had been proposed to normalise the luminosity and contrast variation.A new approach based on a direct technique using statistical data known as Hybrid Statistical Enhancement(HSE)is presented in this study.TheHSE method uses themean and standard deviation of a local and global neighbourhood and classified the pixel into three groups;the foreground,border,and problematic region(contrast&luminosity).The datasets,namely weld defect images,were utilised to demonstrate the effectiveness of the HSE method.The results from the visual and objective aspects showed that the HSE method could normalise the luminosity and enhance the contrast variation problem effectively.The proposed method was compared to the two(2)populor enhancement methods which is Homomorphic Filter(HF)and Difference of Gaussian(DoG).To prove the HSE effectiveness,a few image quality assessments were presented,and the results were discussed.The HSE method achieved a better result compared to the other methods,which are Signal Noise Ratio(8.920),Standard Deviation(18.588)and Absolute Mean Brightness Error(9.356).In conclusion,implementing the HSE method has produced an effective and efficient result for background correction and quality images improvement.
文摘Structural integrity isstated as the science and technology of margin between safety and disaster. Systematic prediction of structural integrity of critical structures such ascombustion chambers,pressure vessels,nuclear reactor components,boilers etc.,ensures the human safety,environmental protection,and the economical considerations.The present work aims at prediction of fatigue behaviour of symmetric structures like pressure vessels in the presence of common welding defects such as lack of fusion( LOF),lack of penetration( LOP) and porosity.A ring type specimen which replicates the stress pattern in thepressure vessel is considered for the study of severity of weld imperfections. Initial dimensions of weld defects are arrived by performing NDT inspection.Crack growth analysis is carried out to determine the remaining life of the welded joint with defects.
基金support of Shanghai Pinlan Data Technology Co.,Ltd.,and Open Fund of Shanghai Key Laboratory of Engineering Structure Safety,SRIBS(No.2021-KF-06).
文摘This paper proposes a machine-learning-based methodology to automatically classify different types of steel weld defects,including lack of the fusion,porosity,slag inclusion,and the qualified(no defects)cases.This methodology solves the shortcomings of existing detection methods,such as expensive equipment,complicated operation and inability to detect internal defects.The study first collected percussed data from welded steel members with or without weld defects.Then,three methods,the Mel frequency cepstral coefficients,short-time Fourier transform(STFT),and continuous wavelet transform were implemented and compared to explore the most appropriate features for classification of weld statuses.Classic and convolutional neural network-enhanced algorithms were used to classify,the extracted features.Furthermore,experiments were designed and performed to validate the proposed method.Results showed that STFT achieved higher accuracies(up to 96.63%on average)in the weld status classification.The convolutional neural network-enhanced support vector machine(SVM)outperformed six other algorithms with an average accuracy of 95.8%.In addition,random forest and SVM were efficient approaches with a balanced trade-off between the accuracies and the computational efforts.
基金supported by Special Program for Trend Setting Research of Jiangsu Province(Grant No.BY2015065-07)Research Foundation of Jiangsu Key Laboratory of Recycling and Reusing Technology for Mechanical and Electronic Products(Grant No.RRME-KF1605)
文摘There are many flaws in welding images such as noise, low contrast, and blurred edges, which affect feature extraction from welding defect regions and impede classification and recognition of welding defects. To deal with the complexity of welding defect images, this paper proposes an effective method for extracting the features of welding defect regions. Firstly, image preprocessing, image segmentation and image background removal are carried out to a welding image in order to extract welding defect region; and then an 8-connected-component labeling method is used to mark defect regions. Finally, it extracts geometric characteristic parameters including perimeter, area, circularity and others. The experimental result shows that the method proposed in the paper can accurately extract the features of welding defect regions. It has good adaptability and practicability.
基金Project (No. X106871) supported by the Natural Science Foundation of Zhejiang Province,China
文摘With von Mises yield criterion,the loading range of Net Section Collapse(NSC) Criteria is extended from combined tension and bending loadings to combined bending,torsion and internal pressure loadings.A new theoretical analyzing method of plastic limit load for pressure pipe with incomplete welding defects based on the extended NSC Criteria is presented and the correlative formulas are deduced,the influences of pipe curvature,circumferential length and depth of incomplete welding defects on the plastic limit load of pressure pipe are considered as well in this method.Meanwhile,according to the orthogonal experimental design method,the plastic limit loads are calculated by the finite element method and compared with the theoretical values.The results show that the expressions of plastic limit load of pressure pipe with incomplete welding defects under bending,torsion and internal pressure based on extended NSC criteria are reliable.The study provides an important theoretical basis for the establishment of safety assessment measure towards pressure pipe with incomplete welding defects.
基金Supported by the National Natural Science Foundation of China(No.60872065)Open Foundation of State Key Laboratory of Advanced Welding and Connection,Harbin Institute of Technology(AWPT-M04)Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘In order to reduce noise effectively in the welding defect image and preserve the minutiae information, a noise reduction method of welding defect image based on nonsubsampled contourlet transform(NSCT) and anisotropic diffusion is proposed. Firstly, an X-ray welding defect image is decomposed by NSCT. Then total variation(TV) model and Catte_PM model are used for the obtained low-pass component and band-pass components, respectively. Finally, the denoised image is synthesized by inverse NSCT. Experimental results show that, compared with the hybrid method of wavelet threshold shrinkage with TV diffusion, the method combining NSCT with P_Laplace diffusion, and the method combining contourlet with TV model and adaptive contrast diffusion, the proposed method has a great improvement in the aspects of subjective visual effect, peak signal-to-noise ratio(PSNR) and mean-square error(MSE). Noise is suppressed more effectively and the minutiae information is preserved better in the image.
基金Project supported by the Program of Excellent Team in Harbin Institute of Technology, ChinaProject(2006BAF04B09) supported by the National Key Technology Research and Development Program of China
文摘The groove defect formed in the friction stir welding dramatically deteriorates weld appearances and mechanical properties of the joints owing to its larger size and penetration. Therefore, the friction stir repair welding was utilized to remove such a groove defect, and the focus was placed on the mechanical properties and microstructural characteristics of the repair joints so as to obtain an optimum repair welding process. The experimental results indicate that the groove defect can be removed by friction stir repair welding, and the offset repair welding process is superior to the symmetrical repair welding process. In the symmetrical repair welding process, a large number of fine cavity defects and an obvious aggregation of hard-brittle phase Al2Cu occur, accordingly the mechanical properties of the repair joint are weakened, and the fracture feature of repair joint is partially brittle and partially plastic. A good-quality repair joint can be obtained by the offset repair welding process, and the repair joint is fractured near the interface between the weld nugget zone and thermal-mechanically affected zone.
文摘The mechanical properties of welded joints in resistance spot welding of DP780 steel were tested,and three different types of welding cracks in welded joints were investigated by optical microscopy,scanning electron microscopy and electron back-scattered diffraction.Finally,the failure mode of the welded joints in shear tensile test was discussed.It is found the shear tensile strength of welded joints can be greatly improved by adding preheating current or tempering current.The surface crack in welded joint is intergranular fracture,while the inner crack in welded joint is transgranular fracture,and the surface crack on the edge of the electrode imprint can be improved by adding preheating current or tempering current.The traditional failure mode criterion advised by American Welding Society is no longer suitable for DP780 spot welds and the critical nugget size suggested by Pouranvari is overestimated.
文摘Currently, the welding defects recognition of X-ray nondestructive inspection is principally carried out by manual work, which highly depends on the experience of the inspectors and costs plenty of workload. In this paper, an intelligent image processing and recognition method for the tube welding radiographic testing in large-scale pressure vessels is proposed. Firstly, the raw image is preprocessed by median filtering, pseudo point removing and non-lincar image enhancement. Secondly, the welded joints parts are separated from the whole image by edge detection and threshold segmentation algorithms. Then, the separated images are handled by FFT transformation. Finally, whether defects exist and the specific type of defects are judged by Support Vector Machine. Software developed basing on this method works stably on site, and experiments demonstrate that the recognition results are compliance with the JB/T 4730. 2 or ASME standards.
基金This work was supported by Tianjin Natural Science Foundation （No. 11JCYBJC06000） and Specialized Research Fund for the Doctoral Program of Higher Education of China （No. 20100032120019）.
文摘Feature extraction and selection from signals is a key issue for metal magnetic memory testing technique. In order to realize the classification of metal magnetic memory signals of welding defects, four fractal analysis methods, such as box- counting, detrended fluctuation, minimal cover and rescaled-range analysis, were used to extract the feature signal after the original metal magnet memory signal was de-noising and differential processing, then the Karhunen-Lo^e transformation was adopted as classification tool to identify the defect signals. The result shows that this study can provide an efficient classification method for metal magnetic memory signal of welding defects.
文摘With the increase of surface assembly density and the rapid development of surface mount technology (SMT), electronic products tend to be miniaturized and integrated. The welding quality and welding technology of surface mount components have attracted more and more attention. Reflow processing technology is a comprehensive scientific research. There are many reasons for the welding quality defects of each electronic component. Any material performance change or unreasonable processing parameters may lead to hidden welding quality defects. Therefore, in the specific production process, it is necessary to make in-depth analysis of practical problems and constantly improve the reflow soldering process, so as to improve the reflow soldering quality, ensure the up-to-standard rate of new products and improve the stability of electronic products and commodity quality.
基金This research is supported by the National Natural Science Foundation of China （Grant No. 51475105）.
文摘Abstract Horizontal welding is important for heavy or huge welding structures. Keyhole mode variable polarity plasma arc welding of aluminum alloy plates with medium thickness was carried out in horizontal position. The characteristic of welding defects was introduced. Preliminary experiments indicated that the undercut defect could not be eliminated easily. The relationship between welding parameters and the undercut defect showed that this deject could be lessened by using higher heat input. The fluid flow of weld pool was observed by a high speed camera. The fluid flow in weld pool was not symmetric and much of molten metal gathered in the lower part. The fluid flow velocity in the lower part was bigger than that in the upper part. To this end, the formative mechanism of the undercut defect was proposed. The flowability of the molten metal was an influential factor for the undercut defect. A preheating method was designed to verify the formative mechanism.
基金The work is supported by the National Natural Science Foundation of China （51005180） and the Research Fund of the State Key Laboratory of Solidification Processing （69-QP-2011 ）.
文摘9. 6 mm thick 1060-H24 aluminum alloy plates were friction stir welded and the influencing factors on groove and tunnel defects were examined. Results show that the welding speed range for achieving a groove-free joint is enlarged with increasing the rotating speed. The tunnel size decreases with decreasing the welding speed under the same rotating speed. Excessive or insufficient shoulder plunge depth will cause defective joints. At a relatively low rotating speed and high welding speed, the tool having a larger shoulder diameter has a larger range of processing parameters to obtain a groove-free joint. Moreover, the tensile fracture behaviors of the defective and defect-free samples are different.
