• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.05a
• /
• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.499-503
• /
• 2004

This application-oriented paper describes an automated welding carriage system to weld a thin corrugated workpiece with welding seam tracking function. Hyundai Heavy Industries Corporation has developed an automatic welding carriage system, which utilizes pulsed plasma arc welding process for corrugated sheets. It can obtain high speed welding more than 2 times faster than traditional TIG based welding system. The aim of this development is to increase the productivity by using automatic plasma welding carriage systems, to track weld seam line using vision sensor automatically, and finally to provide a convenience to operator in order to carry out welding. In this paper a robust image processing and a distance based tracking algorithms are introduced for corrugated workpiece welding. The automatic welding carriage system is controlled by the programmable logic controller(PLC), and the automatic welding seam tracking system is controlled by the industrial personal computer(IPC) equipped with embedded OS. The system was tested at actual workpiece to show the feasibility and performance of proposed algorithm and to confirm the reliability of developed controller.

• Journal of Welding and Joining
• /
• v.27 no.3
• /
• pp.67-72
• /
• 2009

The flux cored arc welding (FCAW) process is one of the most frequently employed and important welding process due to high productivity and excellent workability. The process is performed either as an automated process or as a semi-automatic process. In FCAW process, welding voltage has been considered as a qualitative indication of arc length. But it is necessary to let welding operators know, maintain and manage the arc length directly by estimating and displaying it. In this study, to develop arc length estimation technique, we measured a welding circuit resistance($R_sc$) and then we calculated welding circuit voltage drop($V_sc$). Also, we measured arc peak voltage($V_ap$). By subtracting $V_sc$ from $V_arc$, we can easily calculate net arc voltage drop($V_arc$). Consequently, we suggested arc length estimating equation and basic algorithm by regressive analyzing the relationship between net arc voltage drop($V_arc$) and real arc length(Larc) measured by high speed camera. Therefore, arc length can be predicted by just monitoring welding current and voltage.

• Journal of Welding and Joining
• /
• v.25 no.2
• /
• pp.49-54
• /
• 2007

Since the wall thickness can be up to 6" or greater, welds must be made in many layers, each layer containing several passes. However, the welding time for the conventional welding processes such as SAW(Submerged Arc Welding) and FCAW(Flux Cored Arc Welding) can be required many hours. The aim of this paper is to develop a high speed welding system with multi-torch and laser vision sensor for increasing the production speed on the line and to remove the need for the operator so that the system can run automatically for the complete multi-torch multi-layer weld. It was shown that the developed laser vision sensor and analysis of arc blow for multi-torch were effective for multi-pass seam tracking and stable arc. A new automated multi-torch welding systems for thick wall applications has been proved in several production lines.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.5
• /
• pp.42-52
• /
• 1997

Computer aided process planning and Offline programming are decisive factors in successful implementation of automated robotic production. However, conventional offline programming procedure has proven ineffective due to time-consuming teaching process for robot programming and due to inefficient system modeling. The paper presents an efficient procedure to semi-automatically generate robot job programs for ship block welding applications. In the research, the teaching positions are automatically determined by predefined rules which are functions of the type and the dimensions of the given welding section of ship block. And a sequence of robot movements and welding conditions such as welding type, welding current, welding speed, and welding torch orientation, are determined by use of Standard Program which is experimentally proved to work well for the welding wection group. Finally, a robot program for the welding section is generated automatically. Based on the algorithm, a offline automatic teaching software is developed. The paper presents also the algorithm and structure of the software.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.10a
• /
• pp.642-646
• /
• 2000

The use of neural-fuzzy system to model mesh seam welding is described in this paper. 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 torch travel speed and the pressure and so on. The relationship between the welding parameters and weld quality is not a direct one, md' in addition, the effect of the weld parameter variables are not independent of the each other. The effectiveness of the proposed neuro-fuzzy algorithms is demonstrated by computer simulations.

• Proceedings of the KWS Conference
• /
• 2003.11a
• /
• pp.45-48
• /
• 2003

Over the past few decades, there has been increasing research and commercial activity in invasive and non-invasive biomedical technology. One important challenge to developing these devices involves the increasing density of electrical interconnects. Resistance spot welding is limited in the density of interconnect based on either the size of welding head or the positional precision with which a weld can be made. Development of an automated laser microwelding system would permit the continued advancement of these important biomedical technologies. The objective of this work is to demonstrate the application of pseudo-pulse Nd:YAG laser technology as an alternative to resistance spot welding in performing electrical interconnection within biomedical products. To date, some experiments have been conducted by using a pseudo-pulse 1064 nm Nd:YAG laser, a successful weld of a 25 ${\mu}{\textrm}{m}$ diameter Pt/Ir wire to a 316 stainless steel shim can be made. Another application involves welding clips, which may be used for external interconnection, to electrodeposited nickel domes that make particular interconnections to specific insulated wires within a cable. These results show a great deal of promise for developing such a process.

• Proceedings of the KWS Conference
• /
• 2005.06a
• /
• pp.324-325
• /
• 2005

The primary aim of this paper is to develop an automated welding system capable of adapting to variation in the weld seam center in order to allow higher welding speeds and improved welding quality by using a laser vision sensor. The system is designed to compensate for production problems such as pipe ovality, variation in bevel geometry and track misalignment.

• Proceedings of the KWS Conference
• /
• 2005.06a
• /
• pp.63-65
• /
• 2005

Because of simple principal and low cost, resistance spot welding has been used a lot for joining the sheet metal in automotive manufacturing process. Welding current, welding time, and force are the most important variables in resistance spot wording. Air guns have hem still used widely. The requirement of synchronizing between robot and weld-gun has become bigger as the field has been automated. The number of servo-gun in the field is trending upward because there're advantages as like to synchronize with robot and to control the stroke path and force by programming on servo-gun system. But no cleared force control method is suggested on servo-gun system until now. In this study, we proved the feedback current of the servo-motor can be used to an excellent force measuring sensor and the force is controlled by the feedback current. And we also detected force lowering during welding cycle on the servo-gun system and solved by compensated force control.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.520-523
• /
• 2008

As a result of the recent development of the electro-information industry, the hardware of an automated ultrasonic testing system is getting lighter and diversified image processing techniques are applied to its software so that the possible precise totaling and detecting of the flaws are studied. This study proposes an automated ultrasonic testing system of the pipe in order to organize the optimized system, and also describes the data flow and general composition of the software for the design of the system.