• Journal of Welding and Joining
• /
• 제29권3호
• /
• pp.64-69
• /
• 2011

Since welding process for most pipelines with large diameter has been carried out by the manual process, automation of the welding process is necessary for the sake of consistent weld quality and improvement in productivity. Therefore the development of the optimized algorithm to decide the welding condition is an effective technique to prove the feasibility of interface standards and intelligent control technology to increase productivity and reduce the cost of system integration. In this study, the pipe welding experiment has been carried out using plused GMA welding process to select optimal welding condition. And necessary information in root-pass welding has been obtained by applying in the pipeline using the selected welding conditions through the welding experiment.

• 한국정보통신학회논문지
• /
• 제9권6호
• /
• pp.1379-1386
• /
• 2005

현재 산업현장에서 활용하는 용접용 로봇은 대부분 오프라인(off-line)으로 작업을 수행하고 있어 생산성과 용접 품질 향상에 그 기능을 충분하게 발휘하지 못하는 실정이다. 현재에는 용접 품질 향상을 위하여 용접 매카니즘이 많이 연구되어 많은 수학적인 해석과 물리적인 해석방법을 도입하여 비선형적인 용접 메카니즘을 연구하고 있다. 이러한 여러 가지 비선형적인 문제와 해석상의 어려움에도 불구하고 용접의 결함을 보완하기 위해 보다 정확한 용접데이터를 생성하기 위하여 고감도의 센서를 도입하여 신호처리 하고 있으며, 이를 이용하여 용접시스템에 포함시키는 피드백제어시스템(feed-back control system)을 구성하여 용접선 추적 및 용접 비드(bead) 형상제어에 응용하고 있다. 또한, 최근에는 인공지능제어기술이 발달되어 인간의 학습능력과 의사결정능력을 대신하는 신경회로망(neural network)과 퍼지이론(fuzzy logic)을 도입하여 용접기술을 개발하고 발전시키고 있다. 본 연구에서는 신경회로망이론을 이용하여 실시간으로 용접시스템을 모니터링하고 퍼지제어기에 의하여 용접결함을 보정하는 지능시스템을 개발방법을 제시하고자 한다.

• 한국정보통신학회논문지
• /
• 제4권5호
• /
• pp.937-942
• /
• 2000

This paper describes for applications of neural networks in the field of arc welding. Conventional, automated process generally involves sophisticated sensing and control techniques applied to various processing parameters. Welding parameters affecting quality include the arc voltage, the welding current and the torch travel speed. The relationship between the welding parameters and weld quality is not a direct one, and in addition, the effect of the weld parameter variables are not independent of the each other - changing the welding current will affect the arc voltage, and so on. Finally, a suitable proposal to improve the construction of the model has also been presented in the paper.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2001년도 춘계종합학술대회
• /
• pp.369-373
• /
• 2001

In this paper, we proposes the steps adopted to construct the neural network model for GMAW welds. Conventional, automated process generally involves sophisticated sensing and control techniques applied to various processing parameters. Welding parameters are influenced by numerous factors, such as welding current, arc voltage, torch travel speed, electrode condition and shielding gas type and flow rate etc. In traditional work, the structural mathematical models have been used to represent this relationship. Contrary to the traditional model method, neural network models are based on non-parametric modeling techniques. For the welding process modeling, the non-linearity at well as the coupled input characteristics makes it apparent that the neural network is probably the most suitable candidate for this task. Finally, a suitable proposal to improve the construction of the model has also been presented in the paper.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 학술대회 논문집 전문대학교육위원
• /
• pp.166-171
• /
• 2002

We are in transitional period of welding technique, which has changed from the stage of quantity and quality to the stage of future technique, imported and introduced from many advanced countries. Therefore, many researches and studies for development on high speeding and making welding machines with high effectiveness has been doing vigorously. In this dissertation, I have studied on a pulsed MAG welding machine, with which welding of thin plates may perform high speeding and effecting. First, I produced a phase shifted full bridge DC-DC convert, which is the type of reduced conduction loss and the power supply for welding machine. And then, I found out an output waveform control algorithm about one pulsed one droplet and short waveform control for thin plates with high speed by deriving the circuit model utilizing the circuit averaged method for full bridge converter.

• 대한조선학회 특별논문집
• /
• 대한조선학회 2007년도 특별논문집
• /
• pp.43-47
• /
• 2007

In this paper, we will introduce how we utilize 3D design model information at factory automation field with welding robot OLP system which is in using at out shipyard. At this area, so far, most of design information is used in NC data generation for steel cutting, but we can utilize 3D model information at more wide and complex area likes robot welding. Moreover, OpenGL which is a graphic library can be possible to verify robot NC data is correct or not through 3D simulation even if some one is not a expert at robot handling.

• 대한조선학회논문집
• /
• 제34권1호
• /
• pp.111-121
• /
• 1997

본 연구에서는 선박설계/생산공정에 필요한 용접정보를 생성 지원하는 전산 시스템을 모델링하였다. 이를 위해 기존의 선박 용접정보의 특성과 흐름을 고찰, 분석하고, 전산 처리가 가능한 선박 용접정보 모델을 정의하였다. 모델링 기법으로는 효율적이고 유연한 시스템을 구축하기 위해 객체 지향 기법과 데이터베이스 기술을 접목시키고, Event-driven방식의 그래픽 사용자 인터페이스 기술을 동원하였다. 그리고, 테스트 프로그램을 개발하여 정의된 모델의 적합성과 그 구현 수단의 유효성을 확인, 검증하였다.

• Journal of Welding and Joining
• /
• 제20권5호
• /
• pp.113-119
• /
• 2002

To prevent problems caused by welding deformation, preparation in the design stage is necessary. Countermeasures in the design stage is also the most cost-effective method. In this study, to give designers information on the welding deformation, a system to visualize the welding deformation is developed. The model to visualize the deformation is the stiffened plate common in steel structures. To increase computational efficiency, theoretical solutions to calculate the deformation of plate and stiffener are used instead of numerical analysis. Also, to secure accuracy, experiments to estimate bending moment causing welding deformations are performed. A computer program written with Visual C++ is developed for interactive data input, calculation of welding deformation and display of deformed shape. Designers can change the design in the early stage after checking the deformed shape by this system.

• 한국공작기계학회논문집
• /
• 제13권4호
• /
• pp.113-120
• /
• 2004

The object of this study is to investigate the effect of compounded welding through the AE(Acoustic Emission) characteristics for weld HAZ(Heat Affected Zone) under the static tensile test. This study was carried out an SWS 490A, high tension steel for electric shield metal arc welding(SMAW), $CO_2$ gas arc welding and TIG welding. Data displays are based on the measured parameters of the AE signals, along with environmental variables such as time and load. The accumulated AE event curve of HAZ definitely have the point of inflection subject to tensile test. The results of the tensile test of HAZ come out electric shield arc welding ＞$CO_2$ gas arc welding＞TIG welding in case of single welding, but generally the tensile test of HAZ come out electric shield arc welding＞ TIG welding ＞ $CO_2$ gas arc welding. These history plots give us useful and powerful information to analyze the results of material evaluation testing.

• 한국정밀공학회지
• /
• 제22권5호
• /
• pp.113-120
• /
• 2005

Because of the turbulent markets and the increasing demand on product quality, the application of new technology to practice is increasingly important. In case of automotive industries, they take interest in laser welding to solve these problems because laser welding has many advantages such as good accessibility, welding quality, fast welding speed and so on. To apply this technology to welding of car body, the data of laser welding are collected through lots of the experiment according to the material, geometry and layer number of welding points. Based on the experiment results and the information of product, i.e. the car side panel, the clustering of stitches for laser welding was carried out and the optimal equipments are selected through the comparison between the requirements of welding and the potential of equipments. Using these results, laser welding cell for the car side panel are configured with the concept of the digital manufacturing, which ensures maximum planning security with visualization and simulation. Finally, the optimal laser welding cell is chosen by the evaluation of alternative cells with assessment criteria.