• Journal of Welding and Joining
• /
• v.17 no.5
• /
• pp.40-46
• /
• 1999

The sensors employed in the robotic are welding system must detect the changes in weld characteristics and produce the output that is in some way related to the change being detected. Such adaptive systems, which synchronise the robot arm and eyes using a primitive brain will form the basis for the development of robotic GMA(Gas Metal Arc) welding which increasingly higher levels of artificial intelligence. The objective of this paper is to realize the mapping characteristics of bead height through learning. After learning, the neural estimation can estimate the bead height desired from the learning mapping characteristic. The design parameters of the neural network estimator(the number of hidden layers and the number of nodes in a layer) are chosen from an estimation error analysis. A series of bead of bead-on-plate GMA welding experiments was carried out in order to verify the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can predict the bead height with reasonable accuracy and guarantee the uniform weld quality.

• Proceedings of the KWS Conference
• /
• 2009.11a
• /
• pp.239-242
• /
• 2009

Friction stir spot welding (FSSW), developed based on principle of friction stir welding, has been paid attention as a new solid-state spot welding process. Since FSSW can produce high-quality weld in Al alloys more easily than resistance spot welding, this process has been already used for construction of Al components in the automotive industries. Despite the large industrial interests in FSSW, fundamental knowledge on welding phenomena of this process has not been fully understood. In this study, FSSW phenomena, such as the consolidation mechanism, the microstructural evolution and the material flow, were examined in Al alloy 6061. This study clarified that the elliptical zone found in the vicinity of the pin hole on the cross section was characterized by the initially lapped surface of two sheets. Moreover, the following material flow was proposed; capture of the upper material with the threads on the pin surface, spiral flow along the tool rotation, and then release at the tip of the pin.

• Journal of Welding and Joining
• /
• v.15 no.6
• /
• pp.41-48
• /
• 1997

For analyzing the characteristics of arc welding processes, an algorithm is necessary to determine the metal transfer mode, arc stability and weld quality. In this study, the weight of spatter during welding was selected for determining the arc stability, which is very relevant to the occurrence of spatter. Weld spatter occurs mainly at the moment when the short circuit is formed and also when it is broken causing the arc to restrike. Based on this fact, the arc stability can be determined by finding the suitable parameters of welding current and arc voltage which influence the weight of spatter. Through various welding experiments, the peak current, the arcing time, the short circuit time, the current and its slope at the start of short circuit were found mainly to influence the weight of spatter. For the convenient usage, an index was proposed by combining all these parameters. It was found that the index is very effective for determining the arc stability.

• Proceedings of the KWS Conference
• /
• 2007.11a
• /
• pp.36-38
• /
• 2007

The instability of the arc in the $CO_2$ arc welding affects the quality of the weld in the automotive industry. This paper evaluates the effects of the arc stability in $CO_2$ arc welding with respect to vertical welding positions. In this experiment, galva-annealed steel sheets(CA) were used as specimens, and these materials were welded by adopting new Cold Metal Transfer (CMT) process. For each sample, fillet joint welding trials were carried out using the same conditions. Each part of welding joints was welded with vertical-up, vertical-down position at $45^{\circ},\;90^{\circ}\;and\;135^{\circ}$ degrees. A high speed camera and a welding signal monitoring system were used for monitoring fluid-flow phenomena in weld pools and frequency measurements, respectively. Through this study, the welding position were found to be key factors mainly to influence the arc stability in $CO_2$ welding moreover and that the arc stability in the vertical-up welding position was observed to be more stable than the vertical-down welding position below $90^{\circ}$.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2005.05a
• /
• pp.66-70
• /
• 2005

The full automation of welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this paper, an attempt has been made to develop an neural network model to predict the weld top-bead height as a function of key process parameters in the welding. and to compare the developed model and a simple neural network model using two different training algorithms in order to select an optimal neural network model.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.18 no.6
• /
• pp.652-657
• /
• 2009

MPW(Magnetic Pulse Welding) is a technologies for welding of metals by means of repulsive force on account of the interaction between electro-magnetic field of coil and current induced in outer pipe. These MPW is one of the most useful welding process of welding ability of the dissimilar metal in which cylindrical materials, such as pipe, tube. As the quality of a weld joint is strongly influenced by process parameters during the welding process and the success of the welding to evaluated according to the leakage pressure. Generally, the process parameters is magnetic pressure, the gap between outer pipe and inner pipe, and the ratio of thickness to diameter of pipe(D/T) in MPW. Therefore, the goal of this study was to explain the effect of parameters on the weld joint leakage pressure. For these purposes, FFD(Fractional Factorial Design) were used for the experiment. The measured data were analyzed by regression analysis and verification experiments with random condition were conducted to confirm the suggested experimental model.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.12
• /
• pp.73-81
• /
• 2001

The MIAB welding uses a rotating arc as its heat source and is known as an efficient method fur pipe butt welding. The arc is rotated around the weld line by the electro-magnetic force resulting from the interaction of arc current and magnetic field. The electro-magnetic force is affected by magnetic flux density, arc current, and arc length. Especially, the magnetic flux density is an important factor on arc rotation and weld quality. This paper presents a 2D finite element model for the analysis of magnetic flux density in the actual welding conditions. The magnetic flux density is mainly dependent on gap between two pipes, the position of coil from gap center, exciting current, and relative permeability. Thus, the relations between magnetic flux density and main factors were investigated through experiment and analysis. Experiments were performed for the steel pipes(48.1mm O.D and 2.0mm thickness). The analysis results of magnetic flux density reveal that it increases with increasing exciting current, increasing relative permeability, decreasing distance from gap center to coil, and decreasing gap size. It is considered that the results of this study can be used as important data on the design of coil system and MIAB welding system.

• Journal of Welding and Joining
• /
• v.11 no.4
• /
• pp.44-56
• /
• 1993

The arc welding processes are substantially nonlinear, in addition to being highly coupled multivariable systems, Frequently, not all the variables affecting the welding quality are known, nor may they be easily quantified. From this point of view, decoupling between the welding parameters from the welding quality is very difficult, which makes it also difficult to control the welding parameters for obtaining the desired welding quality. In this study, a neural network based on the backpropagation algorithm was implemented and adopted for the selection of gas metal arc welding parameters of the fillet joint, that is, welding current, arc voltage and welding speed. The performance of the neural network for modeling the relationship between the welding quality and welding parameters was presented and evaluated by using the actual welding data. To obtain the optimal neural network structure, various types of the neural network structures were tested with the experimental data. It was revealed that the neural network can be effectively adopted to select the appropriate gas metal arc welding parameter of fillet joints for a given weld quality.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1845-1848
• /
• 2005

The automatic $CO_2$ welding is a manufacturing process to produce high quality joints for metal and it could provide a capability of full automation to enhance productivity. Despite the widespread use in the various manufacturing industries, the full automation of the robotic $CO_2$ welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this research, an attempt has been made to develop an intelligent algorithm to predict the weld geometry (top-bead width, top-bead height, back-bead width and back-bead height) as a function of key process parameters in the robotic $CO_2$welding. A sensitivity analysis has been conducted and compared the relative impact of three process parameters on bead geometry in order to verify the measurement errors on the values of the uncertainty in estimated parameters.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.2
• /
• pp.145-152
• /
• 2009

Currently almost all in-service-inspection techniques, applied in domestic nuclear power plants, are partial to field inspection technique. These kinds of techniques are related to managing nuclear power plants by the operation of foreign-produced inspection devices. There have been so many needsfor development of native in-service-inspection device because there is no native diagnosis device for nuclear power plant inspection yet in Korea. In this research, we developed several core techniques to make an automated ultrasonic pipe inspection system for nuclear power plants. A high performance multi-channel ultrasonic pulser/receiver module, an A/D converter module and a digital main CPU module were developed and the performance of the developed modules was verified. The S/N ratio, noise level and signal acquisition performance of the developed modules showed proper level as we designed in the beginning.