• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.397-402
• /
• 2005

In this paper, to improve the efficiency of welding and user convenience in the shipbuilding industry, a PC-based off-line programming (OLP) technique and the development of a robot transfer unit are presented. The developed OLP system is capable of not only robot motion simulations but also automatic generations of a series of robot programs. The strength of the developed OLP system lies in its flexibility in handling the changes of the welding robot's target objects. Moreover, for a precise transfer of the robot to a desired location, an auxiliary mobile platform named a robot-origin-transfer-unit (ROTU) was developed. To enhance the cornering capability of the platform in a narrow area, the developed ROTU is equipped with 2 steering wheels and 1 driving wheel. Both the OLP and the ROTU were field-tested and their performances were proven successful.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.6 no.1
• /
• pp.78-82
• /
• 2010

The feeder pipe of Main Primary Heat Transfer System in Wolsong Nuclear Power Plant was inspected by the Ultrasonic Phase Array technique in 2010. It is the first time to apply this method to the construction at Nuclear Power Plant in Korea. The time required for UT technique is less than RT method. The UT method doesn't need to evacuate personnel who works nearby inspecting area and doesn't need to wait developing of film. For these reasons, the UT method is the fastest method among the volumetric inspections. As a result of the examination, it became clear that main defect of the feeder pipe is the Lack of fusion in the welded area. Moreover, the rate of defect was reduced gradually as improvement of welder's skill. If welding machine has problem, the defect has tended to same pattern(occurred same position in the welding area) but these defects were founded without specific rules. For these reasons, the creation of defect is dependent on the skill of worker not on the automatic welding machine. This evaluation of defect signal and collecting data would be useful to further examination in ISI.

• Transactions of Materials Processing
• /
• v.15 no.7 s.88
• /
• pp.496-503
• /
• 2006

The inner and outer car panels for bonnet, door, and trunk lid are assembled by hemming rather than welding. To achieve successful fabrication of these panels, the complicated timing chart of hemming units for pre-and main hemming stages should be made to optimal one. In this study, a design system for automatic timing chart generation is developed. Using AutoCAD VBA and EXCEL data chart, hemming die design parameters and guidelines were put into the program to give hemming unit drawings and consequent timing charts. Then the prepared timing charts were checked and modified. The effectiveness of the system is verified by applying it successfully to hemming unit design for bonnet panel joining.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.16 no.5
• /
• pp.8-14
• /
• 2008

For nondestructive inspection of electron beam (EB) welding part in automotive power transmission assembly, a pulse-echo ultrasonic testing apparatus in water immersion has been applied using the ultrasonic waves with a frequency of 10MHz. However various problems have appeared during the ultrasonic inspection, which led to some significant mistakes in automatic quality evaluation of the welding parts. Experimental study showed that the state of water couplant medium containing some amount of contaminants, rusts and anti-corrosion agents had considerable influences on the reduction of ultrasonic amplitudes during wave propagation. The amplitude reduction depending on the coupling medium state could bring about some mis-diagnoses for defects in the welding parts. The results proposed that for a reliable inspection of defects in welds the state of water medium should be kept in about 15 volume fractions (vol.%) of anti-corrosion agents and in minimized contaminants.

• Special Issue of the Society of Naval Architects of Korea
• /
• 2006.09a
• /
• pp.112-121
• /
• 2006

The vertical displacement of a ship on the basis of the sea level is an important parameter for its stability and control. To indicate the displacement on operating conditions, "draft marks" are carved on the hull of the ship in various ways. One of the methods is welding. The position, shape and size of the marks are specified on the shipbuilding rules by classification societies to be checked by shipbuilders. In most cases, high-skilled workers do the welding along the drawing for the marks and welding bead becomes the marks. But the inaccuracies due to human errors and high labor cost increase the needs for automating the work process of the draft marks. In the preceding work, an indoor robot was developed for automatic marking system on flat surfaces and the work proved that the robot welding was more effective and accurate than manual welding. However, many parts of the hull structure constructed at the outdoor are cowed shapes, which is beyond the capability of the robot developed for the indoor works on the flat surface. The marking on the curved steel surface requiring the 25m elevations is one of the main challenges to the conventional robots. In the present paper, the robot capable of climbing vertical curved steel surfaces and performing the welding at the marked position by effectively solving the problems mentioned earlier is presented.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.6 no.2
• /
• pp.20-27
• /
• 2010

In order to prevent the corrosion of component contacted primary water designed alloy 600 material in the nuclear power plant. But the primary water stress corrosion cracking(PWSCC) of alloy 600 and weld area occurs continuously due to the residual stress. The leakage accident resulted from PWSCC in the drain nozzle of the steam generator of domestic power plants. Heater sleeves of the pressurizer are welded with alloy 600 weld material and therefore exposed to the primary water environment. PWSCC occurred in heater sleeve material and weld area of many foreign power plants. The current issue of domestic nuclear power plants are consequently concentrated to PWSCC of similar material. In order to improve the detection and the sizing of the PWSCC in the welding sleeve of the pressurizer, the automatic UT system and multi-directions probe sets have been developed. The experimental studies have been performed using the mock-up block containing artificial reflectors(ID connected EDM notch) and semi-artificial cracks made from thermal fatigue. The automatic UT System is applied in the detection and the length sizing of the ID/OD on the tube and the J-groove weld area of the artificial reflectors and results of the detection and the sizing are compared respectively. Also, the developed automatic UT system is successfully accomplished to inspect the heater sleeve and the J-groove weld area on the pressurizer for the detection of PWSCC.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.1 no.2
• /
• pp.78-88
• /
• 2009

In shipbuilding industry, the manufacturing technology has advanced at an unprecedented pace for the last decade. As a result, many automatic systems for cutting, welding, etc. have been developed and employed in the manufacturing process and accordingly the productivity has been increased drastically. Despite such improvement in the manufacturing technology, however, development of an automatic system for fabricating a curved hull plate remains at the beginning stage since hardware and software for the automation of the curved hull fabrication process should be developed differently depending on the dimensions of plates, forming methods and manufacturing processes of each shipyard. To deal with this problem, it is necessary to create a "plug-in" framework, which can adopt various kinds of hardware and software to construct a full automatic fabrication system. In this paper, a framework for automatic fabrication of curved hull plates is proposed, which consists of four components and related software. In particular the software module for computing fabrication information is developed by using the ooCBD development methodology, which can interface with other hardware and software with minimum effort. Examples of the proposed framework applied to medium and large shipyards are presented.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.2
• /
• pp.87-92
• /
• 2006

This paper supplements shortcoming of radioactivity check by detecting defect of SWP weld zone using ultrasonic wave. Manufacture 2 stage robot detection systems that can follow weld bead of SWP by method to detect weld defects of SWP that shape of weld bead is complex for this as quantitative. Also, through signal processing ultrasonic wave defect signal system of GUI environment that can grasp easily existence availability of defect because do videotex compose. Ultrasonic wave signal of weld defects develops artificial intelligence style sightseeing system to enhance pattern recognition of weld defects and the classification rate using neural net. Classification of weld defects that do fan Planar defect and that do volume defect of by classify.

• Journal of the Korea Society for Simulation
• /
• v.15 no.1
• /
• pp.51-58
• /
• 2006

Virtual Manufacturing is a powerful methodology for developing a new product, new equipment and new production system. It enables the checking errors in design before production. This paper is a case study of virtual manufacturing in an excavator factory. The final welding operations of the boom and the rotating table of upper body are selected for application. 3D models of parts and fixtures are developed with $CATIA^{(R)}$ and 3D simulation models are developed with $IGRIP^{(R)}$. These models are used for verifying the design of fixture and for the motion design of robot. As a result, the manual welding systems are replaced by automatic systems and many design errors are corrected in the design phase, which reduces the developing cost and time.

• 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.