• 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 Welding and Joining
• /
• v.28 no.5
• /
• pp.51-57
• /
• 2010

Brittle microstructure created in a heat affected zone (HAZ) during the welding of low alloy steel can be eliminated by post-weld heat treatment (PWHT). If the PWHT is not possible during a repair welding, the controlled bead depositions of multi-pass welding should be applied to obtain tempering effect on the HAZ without PWHT. In order to anticipate and control the tempering effect during the temper bead welding, the definition of temperature curve obtained from the analytical solution was suggested in this research. Because the analytical solution for heat flow is expressed as a mathematical equation of weld parameters, it may be effective in anticipating the effect of each weld parameter on the tempering in HAZ during the successive bead depositions. The reheating effect by the successive bead layer on the brittle coarse grained HAZ formed by earlier bead deposition was estimated by comparing the overlapped distance between the temperature curves in the HAZ. Three layered weld specimens of SA508 base metal with A52 filler were prepared by controlling heat input ratio between layers. The tempering effect anticipated by using the overlapped distance between the temperature curves was verified by measuring the micro-hardness distribution in the HAZ of prepared specimens. The temperature curve obtained from analytical solution was expected as a good tool to find optimal temper bead welding conditions.

• Proceedings of the KWS Conference
• /
• 2003.11a
• /
• pp.169-171
• /
• 2003

In this paper, the prediction for the optimized bead geometry such as bead width, height, penetration and bead area in the Gas Metal Arc (GMA) welding with Taguchi method is presented. An orthogonal array, and the Signal-to-Noise (S/N) ratio employed to investigate the welding quality characteristics together in the selection of process parameters in the GMA welding process, to analyze the effect of each process parameter on the bead geometry and to finally determine the process parameters with the optimal bead geometry. Experimental results fi-om this research show that the Taguchi method provides an effective tool to enhance the accuracy of the optimized bead geometry.

• Journal of Welding and Joining
• /
• v.30 no.6
• /
• pp.126-132
• /
• 2012

The GMA welding process involves large number of interdependent variables which may affect product quality, productivity and cost effectiveness. The relationships between process parameters for a fillet joint and bead geometry are complex because a number of process parameters are involved. To make the automated GMA welding, a method that predicts bead geometry and accomplishes the desired mechanical properties of the weldment should be developed. The developed method should also cover a wide range of material thicknesses and be applicable for all welding position. For the automatic welding system, the data must be available in the form of mathematical equations. In this study a new intelligent model with genetic algorithm has been proposed to investigate interrelationships between welding parameters and bead geometry for the automated GMA welding process. Through the developed model, the correlation between process parameters and bead geometry obtained from the actual experimental results, predicts that data did not show much of a difference, which means that it is quite suitable for the developed genetic algorithm. Progress to be able to control the process parameters in order to obtain the desired bead shape, as well as the systematic study of the genetic algorithm was developed on the basis of the data obtained through the experiments in this study can be applied. In addition, the developed genetic algorithm has the ability to predict the bead shape of the experimental results with satisfactory accuracy.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.225-232
• /
• 2004

Recently, there has been a rapid development in computer technology, which has in turn led to develop the automated welding system using Artificial Intelligence (AI). However, the automated welding system has not been achieved duo to difficulties of the control and sensor technologies. In this paper, the classification of the optimized bead geometry such as bead width, height penetration and bead area in the Gas Metal Arc (GMA) welding with fuzzy logic is presented. The fuzzy C-Means algorithm (FCM), which is best known an unsupervised fuzzy clustering algorithm is employed here to analysis the specimen of the bead geometry. Then the quality of the GMA welding can be classified by this fuzzy clustering technique and the choice for obtaining the optimal bead geometry can also be determined.

• 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.

• Journal of Welding and Joining
• /
• v.13 no.4
• /
• pp.75-84
• /
• 1995

In GMA welding of sheet metal, the short circuit metal transfer mdoe is preferred because of its low heat input and capability of bridging the root gap. The molten electrode is transferred to the workpiece during repectitive short circuit in the model. The waveform of welding current or voltage and the frequency of short circuiting are affected by a number of factors including: magnitude of welding current and voltage, root gap, electrode extension, power supply characteristics, and so on. In this study experimental models were proposed, which are able to determine the relationship between the root gap and short circuit frequency and the relationship between the root gap and appropriate welding speed that produces the good quality of back bead without burn through. Using the experimental models, the root gap can be obtained from measuring the short circuit frequency, and then the appropriate weldig speed to the root gap can be determined. Thus a back bead control system was constructed by controlling the welding speed for maintaining the quality of back bead. The developed system has shown the successful capability of back bead control.

• International Journal of Korean Welding Society
• /
• v.1 no.1
• /
• pp.17-22
• /
• 2001

Because the quantitative relationships between welding parameters and welding result are not yet blown, optimal values of welding parameters for $CO_2$ robotic arc welding is a difficult task. Using the various artificial data processing methods may solve this difficulty. This research aims to develop an expert system for $CO_2$ robotic arc welding to recommend the optimal values of welding parameters. This system has three main functions. First is the recommendation of reasonable values of welding parameters. For such work, the relationships in between the welding parameters are investigated by the use of regression analysis and fuzzy system. The second is the estimation of bead shape by a neural network system. In this study the welding current voltage, speed, weaving width, and root gap are considered as the main parameters influencing a bead shape. The neural network system uses the 3-layer back-propagation model and a generalized delta rule as teaming algorithm. The last is the optimization of the parameters for the correction of undesirable weld bead. The causalities of undesirable weld bead are represented in the form of rules. The inference engine derives conclusions from these rules. The conclusions give the corrected values of the welding parameters. This expert system was developed as a PC-based system of which can be used for the automatic or semi-automatic $CO_2$ fillet welding with 1.2, 1.4, and 1.6mm diameter the solid wires or flux-cored wires.

• Journal of Welding and Joining
• /
• v.15 no.2
• /
• pp.72-80
• /
• 1997

The spatter generation rate of GMA welding with $CO_2$ gas shielding was measured with the change of welding conditions such as wire feeding rate and welding voltage and then the results were analized with the accompanying changes in metal transfer mode and in bead geometry. The spatter generation rate (SGR) was relatively low not only wit the short circuit transfer but with the truely globular transfer mode. However, the SGR resulted with the mixed mode were consistantly high. The resultant wave pattern of mixed mode was due to the coexistance of short-circuit and globular transfer and characterized by the frequent appearance of instantaneous short circuit. Considering the result of SGR and that of bead geometry, it could be concluded that when the wire feeding rate (or welding current) was either low or high, the optimum bead shape could be obtained along with the low spatter generation. However, in the middle range of wire feeding rate, the optimum bead shape was only obtained in the mixed mode condition resulting in the high spatter generation.

• Journal of Welding and Joining
• /
• v.27 no.3
• /
• pp.60-66
• /
• 2009

The structures distorted by welding have to be corrected. Since the correcting work needs a lot of costs and time, it is very important to minimize the buckling distortion due to welding of thin plate structure. Therefore the aim of this study is to investigate the effect of single bead on plate welding and fillet welding on the buckling distortion. In the single bead on plate welding, it was found that the welding speed and welding sequence were the most dominant factors on distortion. In the fillet welding, there were four typical buckling modes observed, and the welding sequence was the most influential factor on the buckling distortion. However typical distortion measuring method is not considered for the distortion correcting process costs of each buckling modes, therefore, in this study, the measuring method is developed to classify the buckling modes for torsion of specimen and buckling distortion depend on nodal point for the bead on plate welding specimen and fillet welds.