• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.539-544
• /
• 1998

Generally, welding gap is a serious factor of a falling-off in weld quality among various kind of weld defect. Welding gap is created between two work piece in GMAW(Gas Metal Arc Welding) of horizontal fillet weld because surface of workpiece is not flat by cutting process. In these days, there were many attempts to detect welding gap. though we prevalently use the vision sensor or arc sensor in welding process, it is difficult to detect welding gap for improvement of welding quality. But we have a trouble to find relationship between welding gap and many welding parameters due to non-linearity of welding process. As mentioned about the various difficult problem, we can detect welding gap precisely using neural networks which are able to model non-linear function. Also, this paper was proposed real-time monitoring of weld bead shape to find effect of welding gap and to estimate weld quality. Monitoring of weld bead shape examined the correlation of welding parameters with bead eometry using learning ability of neural networks. Finally, the developed system, welding gap detecting system and bead shape monitoring system, is expected to the successful capability of automation of welding process by result of simulation.

• International Journal of Korean Welding Society
• /
• v.2 no.2
• /
• pp.47-50
• /
• 2002

Because of the environmental problems, automotive companies are trying to reduce the weight of car body. Therefore, TRIP(TRansformation Induced Plasticity) steels, which have high strength and ductility have been developed. Welding process is a complex process; therefore deciding the optimal welding conditions on the basis of experimental data is an effective method. However, trial-and-error method to decide the optimal conditions requires too many experiments. To overcome these problems, response surface methodology was used. Response surface methodology is a collection of mathematical and statistical techniques that are used in the modeling and analysis of problems in which a response of interest is influenced by several variables and the objective is to optimize this response. This method was applied to the resistance spot welding process of the TRIP steel to optimize the welding parameters.

• International Journal of Korean Welding Society
• /
• v.1 no.2
• /
• pp.7-11
• /
• 2001

Almost every die for automobiles must be corrected or remodeled for minor geometrical changes or fur better hardness characteristics by an arc welding process. Although many other kinds of arc welding processes have been automated with robots, the molten metal deposition process for die remodeling still depends entirely on experienced welders. In this study, a database for bead shapes with respect to welding parameters is constructed through experiments to automate molten metal deposition by the arc welding process. Changes in the welding parameters for inclined base metal are studied to consider the effect of die geometries on the welding process.

• Journal of Welding and Joining
• /
• v.31 no.6
• /
• pp.58-64
• /
• 2013

Several joining methods involving resistance welding, laser welding, ultrasonic welding and mechanical joining are currently applied in manufacturing lithium-ion batteries. Cu and Al alloys are used for tab and bus bar materials, and laser welding characteristics for these alloys were investigated with similar and dissimilar material combinations in this study. The base materials used were Al 1050 and oxygen-free Cu 1020P alloys, and a disk laser was used with a continuous wave mode. In bead-on-plate welding of both alloys, the joint strength was higher than the strength of O tempered base material. In overlap welding, the effect of welding parameters on the tensile shear strength and bead shape was evaluated. Tensile shear strength of overlap welded joint was affected by interfacial bead width and weld defect formation. The tensile-shear specimen was fractured at the heat affected zone by selecting proper laser welding parameters.

• 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.33 no.2
• /
• pp.85-90
• /
• 2015

Recently many studies for improvement of productivity and automation of process are in progress, and among others, laser-arc hybrid welding that combined laser and arc has attracted much attention. Since parameters by interactions as well as the parameters of each heat source should be considered, There are a lot of hardship in actual application, even though many researches have been done so far. Therefore in this study, bead welding was done to examine the effects of the flow rate of shield gas and the distance between laser and arc during laser-arc hybrid welding. As for hybrid heat source, disk laser and MIG were used. As experiment result, sound bead and weld with no defect were formed when the flow rate of front and rear shield gas were respectively 20 l/min and 15 l/min, and deep penetration was done at DLA=3 mm.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.4
• /
• pp.87-92
• /
• 2007

The full automation 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 models using three different training algorithms in order to select an adequate neural network model for prediction of top-bead height.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.170-174
• /
• 2004

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 paper, an attempt has been made to develop an Radial basis function network model to predict the weld top-bead width as a function of key process parameters in the robotic CO$_2$ welding. and to compare the developed model and a simple neural network model using two different training algorithms in order to verify performance. of the developed model.

• 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 Ocean Engineering and Technology
• /
• v.27 no.5
• /
• pp.77-81
• /
• 2013

The effects of the welding parameters, contact tip-to-workpiece distance (CTWD), current, and voltage on the diffusible hydrogen content in weld metal deposited by self-shielded flux cored arc welding were investigated and rationalized by comparing the amount of heat generated in the extension length of the wire. This showed that as CTWD increased from 15mm to 25mm, the amount of heat generated was increased from 71.1J to 174.8J, and the hydrogen content was decreased from 11.3mL/100g to 5.9mL/100 g. Even if little difference was observed in the amount of heat generated, the hydrogen content was increased with an increase in voltage because of the longer arc length. A regression analysis showed that the regression coefficient of voltage in self-shielded flux cored arc welding is greater than that in $CO_2$ arc welding. This implies that voltage control is more important in self-shielded flux cored arc welding than in $CO_2$ arc welding.