• Journal of Welding and Joining
• /
• 제29권6호
• /
• pp.45-48
• /
• 2011

In this research, laser welding of automotive transmission components was investigated to replace electron beam welding which is normally conducted under vacuum condition. Fiber laser welding was applied to the automotive transmission components - hub clutch and annulus gear. In the component welding, the laser welding parameters were optimized to eliminate spatters and the end crater. By applying laser welding to the transmission parts, the process time could be reduced up to 70% compared with the current electron beam welding process.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.166-166
• /
• 2000

This paper describes for applications of neural networks in the field of arc welding. Conventional, automated process generally involves sophisticated sensing and control techniques applied to various processing parameters. Welding parameters affecting quality include the arc voltage, the welding current and the torch travel speed. The relationship between the welding parameters and weld qualify is not a direct one, and in addition, the effect of the weld parameter variables are not independent of the each other - changing the welding current will affect the arc voltage, and so on. Finally, a suitable proposal to improve the construction of the model has also been presented in the paper.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2002년도 춘계학술발표대회 개요집
• /
• pp.19-21
• /
• 2002

• Journal of Welding and Joining
• /
• 제24권4호
• /
• pp.27-31
• /
• 2006

Optimization of process parameters for laser-arc hybrid welding process is intrinsically sophisticated because the process has three kinds of parameters-arc, laser and hybrid welding parameters. In this paper, the relationship between weldability and several process parameters such as laser beam-arc distance, electrode height, welding current and welding speed, were investigated by the full factorial experimental design. Weld quality was evaluated by using weight of spatters which is related with the pore area. It was found that the weld quality was increased with the increases in laser beam-arc distance and welding current, and decreased with the increases in electrode height and welding speed.

• 한국정보통신학회논문지
• /
• 제4권4호
• /
• pp.885-893
• /
• 2000

The use of neural-fuzzy system to model mesh seam welding is described in this paper. Conventional, automated process generally involves sophisticated sensing and control techniques applied to various processing parameters. Welding parameters affecting quality include the arc voltage, the welding current, torch travel speed and the pressure and so on. The relationship between the welding parameters and weld quality is not a direct one, and in addition, the effect of the weld parameter variables are not independent of the each other. The effectiveness of the proposed neuro-fuzzy algorithms is demonstrated by computer simulations.

• Journal of Welding and Joining
• /
• 제32권6호
• /
• pp.70-74
• /
• 2014

On this study, we researched the in-process monitoring during fiber laser welding as well as on the first paper. On the previous/formal study, we analyzed the change of emission signal on thin plate welding. On this study, however, we analyzed RMS and FFT with emission signals in laser welding on lap joint and butt joint of 8mm-thick 316L stainless steel. As the result, the movement of specific frequency peak was observed according to welding speed changes. Furthermore, frequency peak as a result of FFT on the thick plate welding are much clearer than on the thin plate welding. Therefore, it is expected that the welding parameter changes can be predicted in case of applying FFT to in-process monitoring.

• 한국공작기계학회논문집
• /
• 제12권3호
• /
• pp.58-67
• /
• 2003

Welding characteristics of austienite 304 stainless and SM45C using a continuous wave Nd:YAG laser n experimentally investigated Laser beam welding is increasingly being used in welding of structural steels. The laser welding process is one of the most advanced manufacturing technologies owing to its high speed and deep penetration. The thermal cycles associated with laser welding are generally much Inter than those involved in conventional welding processes, leading to a rather small weld zone. Experiments are performed for 304 stainless steel plates changing several process parameter such as laser power, welding speed, shielding gas flow rate, presence of surface pollution, with fixed or variable gap and misalignment between the similar and dissimilar and plates, etc. The Nd:YAG laser welding process is one of the most advanced manufacturing technologies owing to its high speed and penetration. This paper describes the weld ability of SM45C carbon steel for machine structural use by Nd:YAG laser. The follow conclusions can be drawn that laser power and welding speed have a pronounced effect on size and shape of the fusion zone. Increase in welding speed resulted in an increase in weld depth/aspect ratio and hence a decrease in the fusion zone size. The penetration depth increased with the increase in laser power.

• 한국공작기계학회논문집
• /
• 제16권4호
• /
• 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.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 추계학술대회 논문집
• /
• 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.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2005년도 춘계학술대회 논문집
• /
• 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.