• 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.

• Journal of Welding and Joining
• /
• v.29 no.3
• /
• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.754-758
• /
• 2005

Optimization of process variables such as arc current, welding voltage and welding speed in terms of the weld characteristics desired is the key step in achieving high quality and improving performance characteristics without increasing the cost. Consequently, incorrect settings of those process variables give rise to deviations in the welding characteristics from the desired bead geometry. Therefore, trainee welders are referred to the tabulated information relating different metal types and thickness as to recommend the desired values of process variables. Basically, the bead geometry plays an important role in determining the mechanical properties of the weld. So that it is very important to select the process variables for obtaining optimal bead geometry. However, it is difficult for the traditional identification methods to provide an accurate model because the optimized welding process is non-linear and time-dependent. In this paper, the possibilities of the Infra-red sensor in sensing and control of the bead geometry in the automated welding process are presented. Infra-red sensor is a well-known method to deal with the problems with a high degree of fuzziness so that the sensor is employed to build the relationship between process variables and the quality characteristic the proposed above respectively. Based on several neural networks, the mathematical models are derived from extensive experiments with different welding parameters and complex geometrical features. The developed system enables to select the optimal welding parameters and control the desired weld dimensions during arc welding process.

• International Journal of Korean Welding Society
• /
• v.1 no.2
• /
• pp.36-44
• /
• 2001

To get the appropriate welding process variables, mathematical modeling in conjunction with many experiments is necessary to predict the magnitude of weld bead shape. Even though the experimental results are reliable, it has a difficulty in accurately predicting welding process variables for the desired weld bead shape because of nonlinear and complex characteristics of welding processes. The welding condition determined for the desired weld bead shape may cause the weld defect if the welding current/voltage/speed combination is improperly selected. In this study, the $2^{n-1}$ fractional factorial design method and correlation parameter were used to investigate the effect of the welding process variables on the fillet joint shape, and the multiple non-linear regression analysis was used for modeling the gas metal arc welding(GMAW）parameters of the fillet joint. Finally, a fuzzy rule-based method and a neural network method were proposed so that the complexity and non-linearity of arc welding phenomena could be effectively overcome. The performance of the proposed neuro-fuzzy system was evaluated through various experiments. The experimental results showed that the proposed neuro-fuzzy system could effectively check the welding conditions as to whether or not weld defects would occur, and also adjust the welding conditions to avoid these weld defects.

• Journal of Welding and Joining
• /
• v.24 no.5
• /
• pp.37-42
• /
• 2006

The robotic arc welding is widely employed in the fabrication industry fer increasing productivity and enhancing product quality by its high processing speed, accuracy and repeatability. Basically, the bead geometry plays an important role in determining the mechanical properties of the weld. So that it is very important to select the process variables for obtaining optimal bead geometry. In this paper, the possibilities of the Infrared camera in sensing and control of the bead geometry in the automated welding process are presented. Both bead width and thermal images from infrared thermography are effected by process parameters. Bead width and isotherm radii can be expressed in terms of process parameters(welding current and welding speed) using mathematical equations obtained by empirical analysis using infrared camera. A linear relationship exists between the isothermal radii producted during the welding process and bead width.

• Journal of Welding and Joining
• /
• v.30 no.3
• /
• pp.66-70
• /
• 2012

Welding is an essential process in the automotive industry. Most welding processes that are used for auto body is spot welding. And $CO_2$ arc welding is used in a small part. In production field, $CO_2$ arc welding process is decreased and spot welding process is increased due to welding quality is poor and defects are occurred in $CO_2$ arc welding process frequently. But $CO_2$ arc welding process should be used at robot interference parts and closed parts where spot welding couldn't. $CO_2$ welding is divided into lap welding and plug arc spot welding. In case of plug arc spot welding, burn through and under fill were caused in various welding environment such as different thickness combinations of base metal, teaching point, over the two steps welding and inconsistent voltage/current. It makes some problem like poor quality of welding area and decrease the productivity. In this study, we will evaluate the effect of teaching point through the weld pool behavior and bead geometry in the arc spot welding at the plut hole. Welding position is horizontal position. And galvanized steel sheet of 2.0mm thickness that has plug hole of 6mm diameter was used. Teaching point was changed by center, top, bottom, left and right of the plug hole. At each condition, the phenomenon of weld pool behavior was confirmed using a high-speed camera. As the result, we find the center of plug hole is the most optimal teaching point. In the other teaching point, under fill was occurred at the plug hole. This phenomenon is caused by gravity and surface tension. For performance of arc spot welding at the plug hole, the teaching condition should be controlled at a center of plug hole.

• Journal of Korean Society for Quality Management
• /
• v.31 no.1
• /
• pp.123-131
• /
• 2003

This paper considers a six sigma project for reducing the defects rate of the welding process in manufacturing firms. The project follows a disciplined process of five macro phases. define, measure, analyze, improve and control(DMAIC). The need of customers is used to identify critical to quality(CTQ) of project. And a process map is used to identify process input factors of CTQ. Four key process input factors are selected by using an input factor evaluation of teams; an interval of welding, an abrasion, an electric current and a moving freely. DOE is utilized for finding the optimal process conditions of the three key process input factors. Another one key input factor improved to welding machine. The six sigma level of defects rate becomes a 2.01 from a 1.61 at the beginning of the project.

• Journal of Welding and Joining
• /
• v.17 no.4
• /
• pp.85-92
• /
• 1999

In GMAW, the spatter is generated because of the variation of the arc state. If the arc state is quantitatively assessed, the control method to make the spatter be reduced is able to develop. This study was attempted to develop the optimal model that could estimate the arc state quantitatively. To do this, the generated spatters was captured under the limited welding conditions, and the waveforms of the arc voltage and of the welding current were collected. From the collected waveforms, the waveform factors and their standard deviations were produced, and the linear and non-linear regression models constituted using the factors and their standard deviations are proposed to estimate the arc state. the performance test to the proposed models was practiced. Obtained results are as follow. From the results of correlation analysis between the factors and the amount of the generated spatters, the standard deviations of the waveform factors have more the multiple regression coefficients than the waveform factors. Because the correlation coefficient between T and {TEX}$T_{a}${/TEX}, and s[T] and s[{TEX}$T_{a}${/TEX}] was nearly one, it was found that these factors have the same effect to the spatter generation. In the regression models to estimate the arc state, it was fond that the linear and the non linear models were also consisted of similar factors. In addition, the linear regression model was assessed the optimal model for estimating the arc state because the variance of data was narrow and multiple regression coefficient was highest among the models. But in the welding conditions which the amount of the generated spatters were small, it was found that the non linear regression model had better the estimation performance for the spatter generation than the linear.

• 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.19 no.5
• /
• pp.520-525
• /
• 2001

The Sn-Pb eutectic solder bump formation ($150\mu\textrm{m}$ diameter, $250\mu\textrm{m}$ pitch) by electroplating was studied for flip chip package fabrication. The effect of current density and plating time on Sn-Pb deposit was investigated. The morphology and composition of plated solder surface was examined by scanning electron microscopy. The plating thickness increased wish increasing time. The plating rate became constant at limiting current density. After the characteristics of Sn-Pb plating were investigated, Sn-Pb solder bumps were fabricated in optimal condition of $7A/dm^$. 4hr. Ball shear test after reflow was performed to measure adhesion strength between solder bump and UBM (Under Bump Metallurgy). The shear strength of Sn-Pb bump after reflow was higher than that of before reflow.