• 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.

• Transactions of Materials Processing
• /
• v.24 no.4
• /
• pp.256-263
• /
• 2015

Electric resistance spot welding has been used to join overlapped steel sheets in automotive bodies. Recently to reduce weight in automotive vehicles, non-ferrous metals are being used or considered in car bodies for hoods, trunk lids, doors parts, etc. Various welding processes such as laser welding, self-piercing rivet, friction stir welding are being used. In the current study, a new electric resistance heated friction stir spot welding is suggested for the spot welding of non-ferrous metals. The welding method can be characterized by three uses of heat -- electric resistance heating, friction stir heating and conduction heating of steel electrodes -- for the fusion joining at the interfacial zone between the two sheets. The welding process has variables such as welding current, diameter of the steel electrodes, revolutions per minute (rpm) of the friction stir pin, and the insert depth of the stir pin. In order to obtain the optimal welding variables, which provide the best welding strength, many experiments were conducted. From the experiments, it was found that the welding strength could be reached to the required production value by using an electrode diameter of 10mm, a current of 7.6kA, a stirring speed of 400rpm, and an insert depth of 0.8mm for the electric resistance heated friction stir spot welding of 5052 aluminum 1.5mm sheets.

• International Journal of Korean Welding Society
• /
• v.1 no.1
• /
• pp.17-22
• /
• 2001

Because the quantitative relationships between welding parameters and welding result are not yet blown, optimal values of welding parameters for $CO_2$ robotic arc welding is a difficult task. Using the various artificial data processing methods may solve this difficulty. This research aims to develop an expert system for $CO_2$ robotic arc welding to recommend the optimal values of welding parameters. This system has three main functions. First is the recommendation of reasonable values of welding parameters. For such work, the relationships in between the welding parameters are investigated by the use of regression analysis and fuzzy system. The second is the estimation of bead shape by a neural network system. In this study the welding current voltage, speed, weaving width, and root gap are considered as the main parameters influencing a bead shape. The neural network system uses the 3-layer back-propagation model and a generalized delta rule as teaming algorithm. The last is the optimization of the parameters for the correction of undesirable weld bead. The causalities of undesirable weld bead are represented in the form of rules. The inference engine derives conclusions from these rules. The conclusions give the corrected values of the welding parameters. This expert system was developed as a PC-based system of which can be used for the automatic or semi-automatic $CO_2$ fillet welding with 1.2, 1.4, and 1.6mm diameter the solid wires or flux-cored wires.

• Journal of Welding and Joining
• /
• v.15 no.2
• /
• pp.43-53
• /
• 1997

The complete joining method for dissimilar press punch materials and its real-time evaluation method is not available at present. Brazing method has been used for joining them, but it is known that the welded joint by the brazing has the lower bonding efficiency and reliability than the diffusion welding. The friction welding with a diffusion mechanism in bonding was applied in this study. This work was carried out to determine the proper friction welding conditions and to analyze mechanical properties of friction welded joints of sintered carbide tool materials (SKNM50 for the blade part of press punch) to alloy steel (SCM440 for the shank part of press punch) using aluminum (A6061 for the interlayer material) as an insert material between the sintered carbide tool materials and the alloy steel. In addition, acoustic emission test was carried out during friction welding to evaluate the weld quality.

• Journal of Welding and Joining
• /
• v.15 no.6
• /
• pp.116-123
• /
• 1997

In GMA welding processes, bead contour and penetration patterns are criterion to estimate weld quality. Bead geometry is commonly defined with width, height and depth. When weaving is taken into account, selection of welding conditions is known to be difficult. Thus, empirical or trial-and-error method are usually introduced. This study examined the correlation of welding process variables including weaving parameters with bead geometry using srtificial neural networks(ANN). The main task of the Ann estimator is to realize the mapping characteristics from the sampled welding process variables to the actual bead geometry through training. After the neural network model is constructed, welding process variables for desired bead geometry is selected by inverse model. Experimental varification of the inverse model is conducted through actual welding.

• Proceedings of the KWS Conference
• /
• 2005.06a
• /
• pp.226-228
• /
• 2005

Of typical welding techniques, to employ the heat for joining process is the most commonly used welding process. But there arise difficulties when this process is applied to light weight alloys such as Aluminium alloy. In this respect, Friction Stir Welding(FSW), a solid-state joining process, is the most effective welding technique with significant potential for various industrial applications. In this study, the characteristics of lapping FSW Al 5052 alloy are shown under a variety of welding parameters such as the rotation speed of FSW tool and welding velocity. Conclusively, the welding properties of lapping FSW Al 5052 were found to be dominated by the deformation of non-joining area near the welding nugget rather than other factors such as the thermal input.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.05a
• /
• pp.269-274
• /
• 1999

Aluminum alloy has not only physical characteristic of very high activated high thermal conductivity and high thermal coefficient expansion but also special characteristic of great difference fusibility of hydrogen between liquid and solid phase. Because of these reasons, Aluminum welding is very different. Therefore, only MIG welding method should be applied instead of other welding methods. In this study, in order to select optimal welding conditions, it has been to investigate the effectiveness on the welding current, welding speed, flow rate of gas and welding voltage to occurrence of spatters, external shape of bead, state of penetration and width and hight of bead by using filer metal of A15356(dia. 1.21mm) on the base material of A16061.

• Proceedings of the KSR Conference
• /
• 2009.05b
• /
• pp.559-564
• /
• 2009

Aluminum extrude is increasing to vehicle body manufacture of a recent railroad vehicle. Conventional welding of this aluminum extrude has been used MIG welding or resistance spot welding mainly. But the advanced manufactures like Japan's tried to apply the friction stir welding and friction spot joining at railroad vehicle body manufacture process. Therefore in this paper we tried to study to apply friction stir welding to AL 6005-T6 extrude which has been manufactured the railroad vehicle mainly. In this study we investigated first the mechanisms to affect the welding strength in friction stir welding. After we made the 3 tools of different shape, we observed how the welding strength changed while changing the welding time and the rotation speed, the plunging depth.

• International Journal of Korean Welding Society
• /
• v.3 no.1
• /
• pp.8-16
• /
• 2003

A major concern in Gas Metal Arc (GMA) welding process is the determination of welding process variables such as wire diameter, gas flow rate, welding speed, arc current and welding voltage and their effects on the desired weld bead dimensions and shape. To successfully accomplish this objective, 81 welded samples from mild steel AS 1204 flats adopting the bead-on-plate technique were employed in the experiment. The experimental results were used to develop a mathematical model to predict the magnitude of bead geometry as follows; weld bead width, weld bead height, weld bead penetration depth, weld penetration shape factor, weld reinforcement shape factor, weld bead total area, weld bead penetration area, weld bead reinforcement area, weld bead dilution, length of weld bead penetration boundary and length of weld bead reinforcement boundary, and to establish the relationships between weld process parameters and bead geomery. Multiple regression analysis was employed for investigating and modeling the GMA process and significance test techniques were applied for the interpretation of the experimental data.

• Journal of Welding and Joining
• /
• v.27 no.6
• /
• pp.17-24
• /
• 2009

The Friction Stir Welding(FSW) has mainly been used for making butt joints in Al alloys. Development of Friction Stir Lap Welding(FSLW) would expand the number of applications. Microstructure of FSLW in A5052-H112 alloy was investigated under varying rotation and welding speed. As the rotation speed was increased and the welding speed was decreased, a amount of heat was increased. As a result, bead interval was narrower, bead width are larger, and experimental bead interval was almost similar to theoretical bead interval. Typical microstructures of FSLW A5052-H112 alloy consist of three zones, including Stir Zone(SZ), Thermo-Mechanically Affected Zone(TMAZ) and Heat Affected Zone(HAZ). As a amount of heat was increased, average grain size was larger in three zones. Nevertheless, the aspect ratio was almost fixed for FSLW conditions. The misorientation of SZ, HAZ and TMAZ was examined. A large number of low angle grain boundaries, which were formed by severe plastic deformation, were showed in TMAZ as comparison with SZ and HAZ. Microhardness distribution was high in order of BM, SZ, TMAZ, and HAZ. The Micro-hardness distribution in HAZ, TMAZ of upper plate were lager than lower plate. Relationship between average grain size and microhardness was almost corresponded to Hall-Petch equation.