• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.6
• /
• pp.1379-1386
• /
• 2005

For efficient welding it is necessary to maintain stability of the welding process and control the shape of the welding bead. The welding quality can be controlled by monitoring important parameters, such as, the Arc Voltage, Welding Current and Welding Speed during the welding process. Welding systems use either a vision sensor or an Arc sensor, both of which are unable to control these parameters directly. Therefore, it is difficult to obtain necessary bead geometry without automatically controlling the welding parameters through the sensors. In this paper we propose a novel approach using fuzzy logic and neural networks for improving welding qualify and maintaining the desired weld bead shape. Through experiments we demonstrate that the proposed system can be used for real welding processes. The results demonstrate that the system can efficiently estimate the weld bead shape and remove the welding detects.

• Proceedings of the KWS Conference
• /
• 2002.10a
• /
• pp.600-605
• /
• 2002

The keyhole formed by high energy density laser-material interaction periodically collapses due to surface tension of the molten metal in partial penetration welds. The collapse sometimes traps a void at the bottom of the keyhole, and it remains as welding defects. This phenomenon is seen as one cause of the instability of the keyhole during laser beam welding. Thus, it seems likely that improving the stability of the keyhole can reduce voids and uniform the penetration depth. The goal of this work is to develop techniques for controlling laser weld keyhole dynamics to reduce weld defects such as voids and inconsistent penetration. Statistical analysis of the penetration depth signals in glycerin determined that keyhole dynamics are chaotic. The chaotic nature of keyhole fluctuations and the ability of laser power modulation to control them have been demonstrated by high-speed video images of laser welds in glycerin. Additionally, an incident leading beam angle is applied to enhance the stability of the keyhole. The quasi-sinusoidal laser beam power of 400Hz frequency and 15$^{\circ}$ incident leading beam angle were determined to be the optimum parameters for the reduction of voids. Finally, chaos analyses of uncontrolled signals and controlled signals were done to show the effectiveness of modulation on the keyhole dynamics. Three-dimensional phase plots for uncontrolled system and controlled system are produced to demonstrate that the chaotic keyhole dynamics is converted to regular periodic behavior by control methods: power modulation and incident leading beam angle.

• Journal of the Korean Institute of Navigation
• /
• v.23 no.4
• /
• pp.105-114
• /
• 1999

Generally, though we use the vision sensor or arc sensor in welding process, it is difficult to define the welding parameters which can be applied to the weld quality control. Especially, the important Parameters is Arc Voltage, Welding Current, Welding Speed in arc welding process and they affect the decision of weld bead shape, the stability of welding process and the decision of weld quality. Therefore, it is difficult to determine the unique relationship between the weld bead geometry and the combination of various welding condition. Due to the various difficulties as mentioned, we intend to use Fuzzy Logic and Neural Network to solve these problems. Therefore, the combination of Fuzzy Logic and Neural network has an effect on removing the weld defects, improving the weld quality and turning the desired weld bead shape. Finally, this system can be used under what kind of welding recess adequately and help us make an estimate of the weld bead shape and remove the weld defects.

• Journal of the Korean Society of Industry Convergence
• /
• v.5 no.2
• /
• pp.111-118
• /
• 2002

In GMAW(Gas Metal Arc Welding) processes, bead geometry (penetration, bead width and height) is a criterion to estimate welding quality, Bead geometry is affected by welding current, arc voltage and travel speed, shielding gas, CTWD (contact-tip to workpiece distance) and so on. In this paper, welding process variables were selected as welding current, arc voltage and travel speed. And bead geometry was reasoned from the chosen welding process variables using neuro-fuzzy algorithm. Neural networks was applied to design FLC(fuzzy logic control), The parameters of input membership functions and those of consequence functions in FLC were tuned through the method of learning by backpropagation algorithm, Bead geometry could he reasoned from welding current, arc voltage, travel speed on FLC using the results learned by neural networks. On the developed inference system of bead geometry using neuo-fuzzy algorithm, the inference error percent of bead width was within ${\pm}4%$, that of bead height was within ${\pm}3%$, and that of penetration was within ${\pm}8%$, Neural networks came into effect to find the parameters of input membership functions and those of consequence in FLC. Therefore the inference system of welding quality expects to be developed through proposed algorithm.

• Proceedings of the KWS Conference
• /
• 2006.05a
• /
• pp.295-297
• /
• 2006

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.189-193
• /
• 1997

Generally, though we use the vision sensor or arc sensor in welding process, it is difficult to define the welding parameters which can be applied to the weld quality control. Especially, the important parameters is Arc Voltage, Welding Current, Welding Speed in arc welding process and they affect the decision of weld bead shape, the stability of welding process and the decision of weld quality. Therefore, it is difficult to determine the unique relationship between the weld bead geometry and the combination of various welding condition. Due to the various difficulties as mentioned, we intend to use Fuzzy Logic and Neural Network to solve these problems. Therefore, the combination of Fuzzy Logic and Neural network has an effect on removing the weld defects, improving the weld quality and turning the desired weld bead shape. Finally, this system can be used under what kind of welding process adequately and help us make an estimate of the weld bead shape and remove the weld defects.

• Journal of Ocean Engineering and Technology
• /
• v.25 no.6
• /
• pp.1-8
• /
• 2011

This paper describes a new method for a digital gas metal arc welding (GMAW) system. The GMAW system is an arc welding process that incorporates the GMAW power source (PS-GMAW) with a wire feed unit (WFU). The PS-GMAW requires an electric power of constant voltage. A constant magnitude is maintained for the arc current by controlling the wire-feed speed of the WFU. A mathematical model is derived, and a self-tuning fuzzy proportional-integral-derivative (PID) controller is designed and applied to control the welding current. The electrode wire feeding mechanism with this controller is driven by a DC motor, which can compensate for both the molten part of the electrode and undesirable fluctuations in the arc length during the welding process. By accurately maintaining the output welding current and welding voltage at constant values during the welding process, excellent welding results can be obtained. Simulation and experimental results are shown to prove the effectiveness of the proposed controller.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.8
• /
• pp.706-713
• /
• 2016

In this study, the welding characteristics of friction stir welding were investigated in accordance with the tool plunge position and cooling to the base materials for the joining of dissimilar materials (A6005-AZ61). Other different welding conditions, such as the tool rotation speed and welding speed, were fixed to 500rpm-30mm/min, respectively, and welding was then carried out by placing the Mg alloy (AZ61) on the advancing side and Al alloy(A6005) on the retreating side. Welding was conducted under six different conditions. To investigate the welding characteristic, tensile test and microstructure observations using an optical microscope were carried out. As the tensile test result, the maximum strength appeared under the condition in which the tool is moved 1 mm to the Mg alloy direction and cooling to the base materials. Under the same welding conditions, the strength with cooling was approximately two times higher than that without cooling. The tool was located in each direction of 1.7 mm from the weld line. Therefore, in the excessive off-set of tool position, the welding integrity was in an extremely poor condition due to the lack of stirring. This study was confirmed by the A6005-AZ61 dissimilar friction stir welding the welding speed and the tool rotation speed. In addition, the temperature control and tool plunge position are important welding parameters.

• Proceedings of the KIPE Conference
• /
• 2013.07a
• /
• pp.461-462
• /
• 2013

In this paper, a studied the SAW system being developed shipbuilding and plant industry with changing welding method to progress productivity. It studies a SAW system using one sensor instead previous one which is using two sensors. It suggests SAW system which has AC output with high current makes high speed welding and DC output with accurate arcing makes detailed control.

• 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.