• Journal of Korean Society of Steel Construction
• /
• v.11 no.1 s.38
• /
• pp.1-11
• /
• 1999

The aim of this study is to construct a machine vision monitoring system for an automatic visual inspection of weld joint in steel structure. An image processing algorithm for a visual weld defects detection on weld bead is developed using the intensity image. An optic system for getting four intensity images was set as a fixed camera position and four different illumination directions. The input images were thresholded and segmented after a suitable preprocessing and the features of each region were defined and calculated. The features were used in the detection and the classification of the visual weld defects. It is confirmed that the developed algorithm can detect weld defects that could not be detected by previously developed techniques. The recognized results were evaluated and compared to expert inspectors' results.

• Journal of Welding and Joining
• /
• v.18 no.4
• /
• pp.20-27
• /
• 2000

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.193-201
• /
• 2021

The welding has a high proportion of the production and drying of ships or offshore plants. Non-destructive testing is carried out to verify the quality of welds in Korea, radiography test (RT) is mainly used. Currently, most shipyards adopt analog-type techniques to print the films through the shoot of welding parts. Therefore, the time required from radiography test to pass or fail judgment is long and complex, and is being manually carried out by qualified inspectors. To improve this problem, this paper covers a platform for scanning and digitalizing RT films occurring in shipyards with high resolution, accumulating them in management servers, and applying artificial intelligence (AI) technology to detect welding defects. To do this, we describe the process of designing and developing RT film scanning equipment, welding inspection information integrated management platform, fault reading algorithms, visualization software, and testing and verification of each developed element in conjunction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.28-36
• /
• 2020

In shipbuilding industry, there is conducting most of works by welding at the shipyard, and the volume of welding is increasing with international trends of green ships. Welding joint is guaranteed quality through non-destructive testing (NDT). The manual welding inspection report is produced by identifying the drawings designed, which results in losses the many workforce and occurs human errors. To solve these problems, this paper covers a system that reports on inspection information is automatically generation by input data based on shipbuilding-specific CAD. The developed system analyzes the shape data from drawings of modeling. Also, the system determines welding joints through expansion of the part boundary and generates tag numbers. In addition, it provides the function to automatically extract the information needed for inspection such as weld length, thickness and etc. We conducted test to verify the usefulness of the developed system and confirmed that the welding inspection information extracted through system matches the information shown in drawings of modeling.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.5
• /
• pp.985-993
• /
• 2001

Neural networks are shown to be effective in being able to distinguish incomplete penetration-like weld defects by directly analyzing the plasma which is generated on each impingement of the laser on the materials. The performance is similar to that of existing methods based on extracted feature parameters. In each case around 93% of the defects in a database derived from 100 artificially produced defects of known types can be placed into one of two classes: incomplete penetration and bubbling. The present method based on classification using plasma is faster, and the speed is sufficient to allow on-line classification during data collection.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.15 no.4
• /
• pp.511-519
• /
• 1996

The purposes of this study are 1) to develop optimum FRW technique of SNCM220, SCM435, SACM645 and SCM415 bar-to-bar similar friction welding, 2) to develop in-process real-time weld quality nondestructive evaluation technique by acoustic emission method, and 3) to certify of weld quality by inspection of tensile fracture surface on friction welded joints.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.453-458
• /
• 2016

One of the most common applications of machine vision is quality inspections in automated production. In this study, a welding inspection system that is controlled by a PC and a PLC equipped with a multi-camera setup was developed. The system was designed to measure the primary dimensions, such as the length and width of the welding areas. The TCP/IP protocols and multi-threading techniques were used for parallel control of the optical components and physical distribution. A coaxial light was used to maintain uniform lighting conditions and enhance the image quality of the weld areas. The core image processing system was established through a combination of various algorithms from the OpenCV library. The proposed vision inspection system was fully validated for an actual weld production line and was shown to satisfy the functional and performance requirements.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.10 no.2
• /
• pp.241-246
• /
• 1986

A new method of on-line monitoring of spot weld quality is proposed by analysing weld votage signal. Weld voltage signal has been modeled by autoregressive model which is suitable for on-line modeling scheme, and order of the model is determined by F-test. From the chosen model, strength. Upon experimental results, it has been shown that fundamental frequency dispersion of weld voltage can be used as a good parameter like maximum thermal expansion in on-line monitoring of spot weld quality. Microcomputer implementation of the proposed monitoring method is also developed and presented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.7
• /
• pp.1326-1331
• /
• 2006

Weld root gap is a important fact of a falling-off weld quality in various kind of weld defect. The welding quality can be controlled by monitoring important parameters, such as, the Arc voltage, welding current and welding speed during the welding process. Welding systems use either a vision sensor or an Arc sensor, both of which are unable to control these parameters directly. Therefore, it is difficult to obtain necessary bead geometry without automatically controlling the welding parameters through the sensors. In this paper we propose a novel approach using neural networks for detecting and monitoring of weld root gap and bead shape. Through experiments we demonstrate that the proposed system can be used for real welding processes. The results demonstrate that the system can efficiently estimate the weld bead shape and detect the welding defects.

• Proceedings of the KIEE Conference
• /
• 2002.07b
• /
• pp.844-847
• /
• 2002

본 논문에서는 단상 thyristor 정류기 구조의 대전력 150KVA급의 mash seam 용접기에 용접 센터링등 여러 가지 용접 효율 향상을 위한 부가 장치를 포함한 용접장치 개발을 통한 용접품질 분석결과를 보이고 있다. 일반적으로 제철소에 사용되는 수10KVA급의 용접기들은 그동안 전량 수입에 의존하던 것을 공동연구를 통해서 국산화에 성공하였다. 본 시스템은 기존의 타사제품의 기능을 포함하여 용접 센터링 장치, 용접 전후단 의 크램핑기능, 선후행 코일의 선단부를 절단하는 shear ing 기능, 용접 휠높이 자동조절기능을 포함하였으며, 자체 설계된 대전력용 변압기, 대전력 절환용 thyristor 제어들을 포함한 용접기로써 기존의 타사제품에 비하여 기능적, 성능적으로 향상된 형태로써 용접 성능 검사에서도 양호한 결과 얻었다. 본 논문에서는 mash seam 용접기의 기본적인 기능설명과 개된 용접기를 기능별로 설명하고, 실용접 결과를 소개하여 향후 계획을 제시한다