• 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.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.6
• /
• pp.49-55
• /
• 2008

Arc welding process is one of the most important technologies to join metal plates. Robotic welding offers the reduced manufacturing cost sought, but its widespread use demands a means of sensing and correcting for inaccuracies in the part, the fixturing and the robot. A number of problems that need to be addressed in robotic arc welding processes include sensing, joint tracking, and lack of adequate models for process parameter prediction and quality control. Problems with parameter settings and quality control occur frequently in the GMA(Gas Metal Arc) welding process due to the large number of interactive process parameters that must be set and accurately controlled. The objectives of this paper are to realize the mapping characteristics of bead width using a sensitivity analysis and develop the neural network and multiple regression method, and finally select the most accurate model in order to control the weld quality(bead width) for fillet welding. The experimental results show that the proposed neural network estimator can predict bead width with reasonable accuracy, and guarantee the uniform weld quality.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.33 no.8
• /
• pp.842-848
• /
• 2009

Fatigue failures are often occurred at welded joints where stress concentrations are relatively high due to the joint geometry. Although employing good detail design practices by upgrading the welded detail class enables to improve the fatigue performance, in many cases, the modification of the detail may not be practicable. As an alternative, the fatigue life extension techniques that reduce the severity of the stress concentration at the weld toe region, remove imperfections and introduce local compressive welding residual stress, have been applied. These techniques are also used as definite measures to extend the fatigue life of critical welds that have failed prematurely and have been repaired. In this study, a hammer peening procedure for using commercial pneumatic chipping hammer was developed, and the effectiveness is quantitatively evaluated. The pneumatic hammer peening makes it possible to give the weld not only a favorable shape reducing the local stress concentration, but also a beneficial compressive residual stress into material surface. In the fatigue life calculation of non-load carrying cruciform specimen treated by the pneumatic hammer peening, the life was lengthened about ten times at a stress range of 240MPa, and fatigue limit increased over 65% for the as-welded specimen.

• 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.

• Journal of Power System Engineering
• /
• v.18 no.3
• /
• pp.51-58
• /
• 2014

Injection molding simulation provided optimized design results by analyzing quality problems while the product is in assembly or in the process of manufacturing with make automobile plastics. Frequent change of design, change of injection molding, repetition of test injection which was held in the old way can now be stopped. And quality upgrade is expected instead. This report deals with the effect which the position of injection molding automobile console gate and number has on product quality including pressure at end of fill, bulk temperature at end of fill, shear stress of end of fill, residual stress at post filling end, product weld lines and warpage results. Simpoe-Mold simulates the complete manufacturing process of plastic injected parts, from filling to warpage. Simpoe-Mold users, whether they are product designers, mold makers or part manufacturers, can identify early into the design stage potential manufacturing problems, study alternative solutions and directly assess the impact of such part modification, whatever the complexity and geometry of such parts, shell part as plain solid parts.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2002.05a
• /
• pp.48-53
• /
• 2002

Sheet or plate bending is one of the most important industrial metal forming processes. And considerable attention has been focused on gaining a better understanding of many of bending characteristics. One of defaults in bending process is the springback. In this study, the springback characteristics of tailor-welded strips in U-bending process was investigated. Furthermore, not only the relationships between the springback and the process variables such as the geometry of the tools and thickness combination of workpiece but also the heat effect which affects the springback due to welding process was experimentally considered. First, tailor-welded strips are joined by the laser welding process and consisted of two types of thickness combinations of the SCPI sheet, 0.8t${\times}$1.2t and 0.8${\times}$1.6t to investigate the effect of different thickness combination on the springback. Secondly, two different directionally welded strips, one was welded along the centerline of the strip-width and the other was along the centerline of strip-length, were adopted to compare the effects of the location of weld line on the springback. And three punch profile radii of 3, 9, and 15 m were used. Some cases of the experimental results were simulated by using a commercial FEM code, PAM-STAMP to compare the experimental results to the analytical ones.

• Journal of Welding and Joining
• /
• v.32 no.1
• /
• pp.28-33
• /
• 2014

In this paper, I-butt welding with 6mm thickness using Plasma-GMA welding was carried out. And weld characteristics of the Al-5083 aluminium alloy for Plasma-GMA hybrid welding was evaluated. The orthogonal experimental design was used to investigate the influence of plasma-MIG welding parameters such as plasma current, wire feeding rate, MIG-welding voltage and welding speed on the weld bead geometry and tensile strength using the ANOVA(Analysis of Variation). Then we conducted evaluation of contribution for process parameters. ANOVA results show that bead dimensions are affected by wire feeding speed, welding voltage and welding speed and tensile strength is mainly affected by welding speed and plasma arc current. Tensile strength was decreased by rise in plasma welding current because GMA welding current was decreased by plasma arc.

• 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.

• Transactions of Materials Processing
• /
• v.12 no.5
• /
• pp.440-448
• /
• 2003

Sheet or plate bending is one of the most important industrial metal forming processes. Considerable attention has been focused on gaining a better understanding of bending characteristics. One of defaults in bending process is the springback. In this study, the springback characteristics of tailor-welded strips in U-bending process was investigated. Furthermore, effect of the process variables such as the geometry of the tools, thickness combination of workpiece, and welding prcoessing on springback were experimentally clarified. First, tailor-welded strips are joined by the laser welding process and consisted of two types of thickness combinations of the SCPl sheet, $0.8t{\times}1.2t$ and $0.8t{\times}1.6t$ to investigate the effect of different thickness combination on the springback. Secondly, two different directionly welded strips, one was welded along the centerline of the strip-width and the other was along the centerline of strip-length, were adopted to compare the effects of the location of weld line on the springback. Some cases of the experimental results were compared to the results simulated by using a commercial FEM code, PAM-STAMP and the theoretical results using the springback formula as well.

• Journal of Advanced Marine Engineering and Technology
• /
• v.29 no.8
• /
• pp.891-898
• /
• 2005

Inertia welding is a solid-state welding process in which butt welds in materials are made in bar and in ring form at the joint race, and energy required lot welding is obtained from a rotating flywheel. The stored energy is converted to frictional heat at the interface under axial load. The quality of the welded joint depends on many parameters, including axial force, initial revolution speed and energy amount of upset. working time, and residual stresses in the joint. Inertia welding was conducted to make the large exhaust valve spindle for low speed marine diesel engine. superalloy Nimonic 80A for valve head of 540mm and high alloy SNCrW for valve stem of 115mm. Due to different material characteristics such as, thermal conductivity and flow stress. on the two sides of the weld interface, modeling is crucial in determining the optimal weld geometry and Parameters. FE simulation was performed by the commercial code DEFORM-2D. A good agreement between the Predicted and actual welded shape is observed. It is expected that modeling will significantly reduce the number of experimental trials needed to determine the weld parameters. especially for welds for which are very expensive materials or large shaft. Many kinds of tests, including macro and microstructure observation, chemical composition tensile , hardness and fatigue test , are conducted to evaluate the qualify of welded joints. Based on the results of the tests it can be concluded that the inertia welding joints of the superalloy exhaust valve spindle are better properties than the material specification of SNCrW.