• Journal of Power System Engineering
• /
• v.13 no.5
• /
• pp.95-102
• /
• 2009

A steam generator (boiler) in thermal power plants, consisting of more than 30,000 parts and components, can lead to the plant shutdown with damage to even the small part of the components; esp., like weld failures on boiler tubes. Consequently it is greatly demanded to improve the quality of the weld on the boiler tube for the stable operation of the power plants. Because of the feature of the welding, which is done past by melting the work pieces and adding a filler material that cools to become a strong coalescence, there is a great possibility that weld failures take place. As a result, it is regulated to make a non-destructive testing, like radiography test, to detect defects and flaws in the weld. The current film radiography test provides a lower image quality exceeding 2.0% of a basic quality level for a penetrameter, it is very likely to fail to detect micro defect. As a result, the prevention for the boiler tube failure has not been made effectively. In this study, computed radiography technology has been applied as a digital radiography test to the boiler tube weld, and Se-75 radiation source was used to improve the image quality, instead of Ir-192 source. As a result of this study, it is proven to save the time and cost for test and to enhance the quality level of penetrameter penetrating image, which enables to upgrade the quality of radiography test to the boiler tube weld.

• Journal of Welding and Joining
• /
• v.14 no.2
• /
• pp.96-105
• /
• 1996

Robot systems are widely utilized in the shipbuilding industry to enhance the productivity by automating the welding process. In order to increase productivity, it is necessary to reduce the time used for robot teaching. In this work, the automatic teaching system is developed for the subassembly process in the shipbuilding industry. A alser/vision sensor is designed to detect the weld seam and the image of the fillet joint is processed using the arm method. Positions of weld seams defined in the CAD database are transformed into the robot coordinate, and the dynamic programming technique is applied to find the sub-optimum weld path. Experiments are carried out to verify the system performance. The results show that the proposed automatic teaching system performs successfully and can be applied to the robot system in the subassembly process.

• Journal of Welding and Joining
• /
• v.17 no.2
• /
• pp.53-60
• /
• 1999

Conventionally, CCD camera and vision sensor using the projected pattern of light is generally used to inspect the weld bead defects. But with this method, a lot of time is needed for image preprocessing, stripe extraction and thinning, etc. In this study, laser vision sensor using the scanning beam of light is used to shorten the time required for image preprocessing. The software for deciding whether the weld bead is in proper shape or not in real time is developed. The criteria are based upon the classification of imperfections in metallic fusion welds(ISO 6520) and limits for imperfections(ISO 5817).

• Journal of Welding and Joining
• /
• v.19 no.6
• /
• pp.600-607
• /
• 2001

A CCD camera with a laser stripe was applied to realize the automatic weld seam tracking in GMAW. It takes relatively long time to process image on-line control using the basic Hough transformation, but it has a tendency of robustness over the noises such as spatter and arc light. For this reason. it was complemented with adaptive Hough transformation to have an on-line processing ability for scanning specific weld points. The adaptive Hough transformation was used to extract laser stripes and to obtain specific weld points. The 3-dimensional information obtained from the vision system made it possible to generate the weld torch path and to obtain the information such as width and depth of weld line. We controled the wire feeding rate using informations of weld line.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.1294-1298
• /
• 2007

Welding process monitoring is advantageous for maintaining weld quality and numerous sensing techniques have been developed for laser welding. Coaxial image monitoring enables direct monitoring of the weld pool shape and keyhole behavior, but requires the complex optical system and the image processing technique. In this study, we coaxially acquired the weld pool images during laser lap welding by using the camera and special illumination. The welding characteristics - pool width and length, keyhole shape, etc - were extracted by using image processing and the relationship between these characteristics and the penetration depth were investigated.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.1
• /
• pp.124-132
• /
• 1997

This paper describes an experimental and numerical study on growing ductile crack-tip behaviors. The hybrid experimental and numerical method by means of a computer image processign technique, was applied to the analysis of both base metal and weld metal CT specimens. In the weld metal specimen, the initial crack-tip was placed in front of fusion line, and the crack orientation was perpendicular to it. Finite element analysis of crack growth behaviors in both base and weld matal specimens made of A533B Class 1 steel were also performed to examine the effects of weldment on near crack-tip fields. a series of experimental studies on crack-tip behaviors have clearly shown the qualitative effects of material properties, especially a hardening exponent. The experimental and numerical results have also shown that weldment does not affect displacement and strain fields near a crack-tip while a stress field is influenced by the difference between yield stresses of both base and weld metals.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.179-184
• /
• 2024

In the car industry, welding is a fundamental linking technique used for joining components, such as steel, molds, and automobile parts. However, accurate inspection is required to test the reliability of the welding components. In this study, we investigate the detection of weld beads using 2D image processing in an automatic recognition system. The sample image is obtained using a 2D vision camera embedded in a lighting system, from where a portion of the bead is successfully extracted after image processing. In this process, the soot removal algorithm plays an important role in accurate weld bead detection, and adopts adaptive local gamma correction and gray color coordinates. Using this automatic recognition system, geometric parameters of the weld bead, such as its length, width, angle, and defect size can also be defined. Finally, on comparing the obtained data with the industrial standards, we can determine whether the weld bead is at an acceptable level or not.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1086-1103
• /
• 2020

The automatic identification and classification of image-based weld defects is a difficult task due to the complex texture of the X-ray images of the weld defect. Several depth learning methods for automatically identifying welds were proposed and tested. In this work, four different depth convolutional neural networks were evaluated and compared on the 1631 image set. The concavity, undercut, bar defects, circular defects, unfused defects and incomplete penetration in the weld image 6 different types of defects are classified. Another contribution of this paper is to train a CNN model "RayNet" for the dataset from scratch. In the experiment part, the parameters of convolution operation are compared and analyzed, in which the experimental part performs a comparative analysis of various parameters in the convolution operation, compares the size of the input image, gives the classification results for each defect, and finally shows the partial feature map during feature extraction with the classification accuracy reaching 96.5%, which is 6.6% higher than the classification accuracy of other existing fine-tuned models, and even improves the classification accuracy compared with the traditional image processing methods, and also proves that the model trained from scratch also has a good performance on small-scale data sets. Our proposed method can assist the evaluators in classifying pipeline welding defects.

• Journal of Welding and Joining
• /
• v.32 no.6
• /
• pp.1-7
• /
• 2014

For the resistance spot welds of CR1180 and GA1180 TRIP steels, the weld quality evaluation method using the digitalized X-ray transmission imaging apparatus was investigated in comparison with the crosssectional examination method. In the case of the resistance spot welding of CR1180, three circular regions, such as WZ(white zone), GZ(grey zone) and DZ(dark zone), appeared on X-ray image and they corresponded to the diameters of indentation mark, nugget and corona bond, respectively. The variation of X-ray transmission thickness due to the thickness variation of the weld seemed to be mainly responsible for the formation of those contrasts. The X-ray image contrast formed from the variation of transmission thickness at the outer border line of DZ could also enable the inspections of the notch shape, nonuniformity of the welding pressure and spatter from its sharpness, concentricity and the normal straight line, respectively. The X-ray image of the resistance spot weld of galvannealed GA1180 TRIP steel was very similar to that of CR1180 TRIP steel except the crown shaped outer border line of DZ which was considered to be due to the melting behavior of zinc having the boiling temperature even lower than the melting temperature of steel.

• Journal of Welding and Joining
• /
• v.14 no.4
• /
• pp.79-88
• /
• 1996

For improvement in productivity and weld quality, weld seam tracking and welding parameter control are very essential in the welding of a structure which can not be cxactly fit-up due to mismatch, discontinous gap, deflection, etc.. In this study, an automatic weld seam tracking system is developed for I-butt joint structure, and the system consists of XYZ working table, vision sensor and user interface program. In the developed vision sensor system, an image projection algorithm for weld-line detection and an adaptive current control algorithm for gap variation were implemented. The user interface program developed in this study by basing on the objct oriented concept could provide very convenient way to utilize the tracking system with the pull-down menu driven structure. The developed system showed a good seam tracking and weld quality control capability corresponding to deflected weld lines and gap variations.