• 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
• /
• 1997.10a
• /
• pp.454-457
• /
• 1997

The purpose of this study is to develop an optimal model, using existing models, that is able to estimate the amount of spatter utilizing artificial neural network in the short circuit transfer mode of gas metal arc (GMA) welding. The amount of spatter generated during welding can become a barometer which represents the process stability of metal transfer in GMA welding, and it depends on some factors which constitute a periodic waveforms of welding current and arc voltage in short circuit GMA welding. So, the 12 factors, which could express the characteristics for the waveforms, and the amount of spatter are used as input and output variables of the neural network, respectively. Two neural network models to estimate the amount of spatter are proposed: A neural network model, where arc extinction is not considered, and a combined neural network model where it is considered. In order to reduce the calculation time it take to produce an output, the input vector and hidden layers for each model are optimized using the correlation coefficients between each factor and the amount of spattcr. The est~mation performance of each optimized model to the amount of spatter IS assessed and compared to the est~mation performance of the model proposed by Kang. Also, through the evaluation for the estimation performance of each optimized model, it is shown that the combined neural network model can almost perfectly predict the amount of spatter.

• Journal of Welding and Joining
• /
• v.34 no.4
• /
• pp.40-47
• /
• 2016

The Zn coating on automotive galvanized steel sheets can improve corrosion resistance. However, the boiling temperature of Zn is lower than the melting temperature of steel and it causes well-known spatter and porosity problem. One of most prominent solutions is a pretreatment of Zn coating by an additional welding arc prior to the main welding process. In this research, GTA and GMA are selected as heat sources for pretreatment and main welding processes, respectively. The authors suggested three possible mechanisms to reduce weld defects by the GTA pretreatment: (1) Formation of gap between the sheets; (2) Evaporation of Zn layer; (3) Oxidation of Zn layer. Among them, Zn Oxidation is the most important mechanism to reduce weld defects in the GTA-GMA hybrid process.

• Journal of Welding and Joining
• /
• v.33 no.1
• /
• pp.54-60
• /
• 2015

Laser-arc hybrid welding has been considered as an effective pipe girth welding process since early 2000's. Tolerance for fit-up offsets such as gap and edge misalignment is one of most important requirements in pipe girth laser-arc hybrid welding, and several approaches using parameter optimization, a laser beam scanning and an arc oscillation have been tried. However the required offset tolerance has not been fully accomplished up to now and laser-arc hybrid welding has not been widely applied in pipeline construction than expected, despite of its high welding speed and deep penetration. In this study, internal welding was adopted to ensure the offset tolerance and sound back bead. The effect of welding parameters on bead shape was investigated at the flat position. Also tolerances for gap and edge misalignment were verified as 0.5 mm and 2.0 mm, respectively. The position welding trials were conducted at several welding positions from the flat to the overhead position in a downward direction. With the fixed welding speed, arc current for gas metal arc welding current and laser output power, adequate welding voltages for gas metal arc welding were suggested for each position.

• Journal of Welding and Joining
• /
• v.34 no.4
• /
• pp.48-54
• /
• 2016

The use of Zn coated steel has increased in the automotive industry due to its excellent corrosion resistance. Conventionally the BIW(body-in-white) structure and the hang-on parts have been made of Zn coated steel and more recently Zn coated steel began to be applied in the chassis parts. During gas metal arc (GMA) welding of the chassis part, lap fillet joint used to be adopted but spatter generation and porosities are most important concerns. In the industrial applications, an intentional joint gap was made to avoid the weld defects but it is not easy to control the size of joint gap. In this research, gas tungsten arc (GTA) is combined with GMA welding where GTA precedes GMA. As pulsed arc was adopted as GMA, GTA was oscillated along the longitudinal direction by pulsing GMA, but the arc oscillation did not disturb the molten droplet transfer of GMA welding. By increasing the distance between GTA and GMA, the length of weld pool increased and porosity could be reduced. Moreover porosity in the welds was fully removed when the distance between two arcs was 15 mm.

• Journal of Welding and Joining
• /
• v.33 no.4
• /
• pp.17-23
• /
• 2015

Laser-gas metal arc hybrid welding has been considered as an alternative process of gas metal arc welding for offshore pipe laying. Fiber delivered high power lasers which enable deep penetration welding were recently developed but high power welding characteristics were not fully understood yet. In this study, the influence of shielding gas composition on welding phenomena in high power laser welding was investigated. Bead shapes, melt ejection and dropping were observed after autogenous laser welding with 100% Ar, Ar-20% $CO_2$, Ar-50% $CO_2$, and 100% $CO_2$ shielding gas. Process parameter window was widest with Ar-50% $CO_2$ shielding gas and the penetration was deepest with 100% $CO_2$ shielding gas. The melt dropping was not observed when Ar-50% $CO_2$ or 100% $CO_2$ shielding gas was supplied.

• Journal of Welding and Joining
• /
• v.16 no.2
• /
• pp.93-99
• /
• 1998

The effects of welding conditions of gas metal arc welding on the elements loss of solid wire, oxygen content and impact toughness of weld metals were studied. Deoxidizing elements loss was increased with increase of arc voltage in both short-circuit transfer mode and globular transfer mode. It is believed that increase of arc voltage results in increase of reaction time between elements in the droplet and surrounding gas at the end of wire and in the arc column. Based on the thermodynamic equilibrium model, the oxygen content of weld metal can be predicted with the content of silicon and manganese as following : [%O] = $K([%Si][%Mn])^{-0.25}$, K = -15518/T+6.01. The equilibrium temperature was dependent on shielding gas, and it was 187$0^{\circ}C$ for $CO_2$ gas and 180$0^{\circ}C$ for 20%$CO_2$-80%Ar gas. The oxygen content of weld metal which shows maximum impact toughness was varied with deoxidizing alloy system of wires, 0.041 wt% for Si-Mn type wire and 0.026 wt% for Si-Mn-Ti type wire.

• International Journal of Advanced Culture Technology
• /
• v.3 no.1
• /
• pp.169-178
• /
• 2015

This research aims to study the effects of various welding parameters in gas metal arc welding (GMAW) process on welding penetration, microstructure and hardness of AS3578-A350 high strength steel with the thickness of 10 mm. The welding process parameters were a welding current of 100-200A, an arc voltage of 20-30V, a welding speed of 20-60 cm/min and a gas shielding type of Ar and $Ar+CO_2$. The summarized experimental results are as follows. An increase of the welding current and voltage affected to increase the penetration depth of the joint. However, when the welding speed was decreased, it increased the penetration depth of the joint. Using the Ar gas for shielding the weld area, produced the higher penetration depth and the less narrow weld bead than the joint that was shielded by the mix gas of $Ar+CO_2$. The variation of the welding process parameters affected to produce the various microstructures of weld metal and heat affected zone and also showed the various kind of hardness along the weld joint.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.7
• /
• pp.1065-1070
• /
• 2003

In arc spot welding process, the arc is not moving and heat input is concentrated in one spot so that the heat input efficiency of arc is higher than that of GMAW. In other words, the heat input efficiency of arc change during weld time because arc start is done in spot and weld metal is filled. Therefore, the heat input model of arc spot welding should be different from that of general GMAW. In present study, the calculating model of heat input efficiency in arc spot welding was suggested by temperature monitoring near spot in arc spot welding of copper plate. The result showed that the heat input efficiency of arc was changed three times during weld time. The accuracy of calculating method of heat input efficiency was verified by heat transfer analysis of arc spot welding process using finite element method.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.1
• /
• pp.9-18
• /
• 2007

There have been continuous efforts for automation of joint tracking system. This automation process is mainly used to do in root pass of gas metal arc welding in the field of heavy industry and shipbuilding etc. For automation, it is important using of vision sensor. Welding robot with vision sensor is used for weld seam tracking on welding fabrication. Recently, it is used to on post-weld inspection for weld quality evaluation. For real time seam tracking, it is very important role in vision process technique. Vision process is included in filtering and thinning, segmentation processing, feature extraction and recognition. In this paper, it has shown performance comparison results of seam tracking for real time root pass on gas metal arc welding. It can be concluded better segment splitting method than iterative averaging technique in the performance results of seam tracking.