• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.5
• /
• pp.937-942
• /
• 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 quality 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.

• International Journal of Korean Welding Society
• /
• v.1 no.2
• /
• pp.36-44
• /
• 2001

To get the appropriate welding process variables, mathematical modeling in conjunction with many experiments is necessary to predict the magnitude of weld bead shape. Even though the experimental results are reliable, it has a difficulty in accurately predicting welding process variables for the desired weld bead shape because of nonlinear and complex characteristics of welding processes. The welding condition determined for the desired weld bead shape may cause the weld defect if the welding current/voltage/speed combination is improperly selected. In this study, the $2^{n-1}$ fractional factorial design method and correlation parameter were used to investigate the effect of the welding process variables on the fillet joint shape, and the multiple non-linear regression analysis was used for modeling the gas metal arc welding(GMAW）parameters of the fillet joint. Finally, a fuzzy rule-based method and a neural network method were proposed so that the complexity and non-linearity of arc welding phenomena could be effectively overcome. The performance of the proposed neuro-fuzzy system was evaluated through various experiments. The experimental results showed that the proposed neuro-fuzzy system could effectively check the welding conditions as to whether or not weld defects would occur, and also adjust the welding conditions to avoid these weld defects.

• International journal of advanced smart convergence
• /
• v.4 no.1
• /
• pp.145-153
• /
• 2015

Friction Stir Welding (FSW) is a solid state welding that could successfully weld the difficult-to-weldmaterials such as an aluminum alloy. In this welding process, the stirrer of the welding tool is one of the important factors for producing the perfect sound joint that indicates the higher joint strength. So, this report aims to apply the friction stir welding using various stirrer geometries to weld the AA6063-T1 aluminum alloy butt joint, investigates the mechanical properties of the joint and then compares the mechanical properties with the microstructure of the joint. An experiment was started by applying the friction stir welding process to weld a 6.3 mm thickness of AA6063-T1 aluminum alloy butt joint. A study of the stirrer geometries effect such as a cylindrical geometry, a cone geometry, a left screw geometry and a right screw geometry at a rotational speed of 2000 rpm and a welding speed of 50-200 mm/min was performed. The mechanical properties such as a tensile strength and a hardness of the joint were also investigated and compared with the microstructure of the joint. The results are as follows. A variation of FSW Stirrer shape directly affected the quality AA6063-T1 aluminum alloy butt joint. A cylindrical stirrer shape and a cone stirrer shape produced the void defect at the bottom part of the weld metal and initiated the failure of the joint when the joint was subjected to the load during the tensile test. Left and right screw stirrer shapes gave the sound joint with no void defect in the weld metal and affected to increase the joint strength that was higher than that of the aluminum base metal.

• Journal of Welding and Joining
• /
• v.16 no.2
• /
• pp.100-110
• /
• 1998

In this paper, the laser weldability of thin gage steels for automobile application is discussed. Welding was carried out with a high power carbon dioxide laser system, and the laser energy was concentrated through a plano-convex lens. Test results showed that the joint gap in the butt welding proved to be one of the critical conditions for an acceptable weld. In the case where the ratio of the gap clearance to the material thickness was slightly bigger than optimal value, the weld strength was reduced showing weld metal fracture. It was possible to obtained a weld penetration ratio of 0.91 when the vertical offset ratio was controlled to be 0.4 or smaller. Results also demonstrated that the weld strength of the lap joint was influenced by travel speed. At the travel speeds lower than 37 mm/s, the weld strength indicated higher value than that of class A recommendation strength of a resistance spot weld based on the KS code. It was clear that the complicated effect of specimen alignment should be considered so as to make a sound weld with high integrity when the laser process was applied to the long weld line.

• Journal of Welding and Joining
• /
• v.34 no.3
• /
• pp.6-11
• /
• 2016

Joining Al/Fe dissimilar metals is becoming a subject of special interest in the assembly of automotive parts as a trade-off between the weight lightening and the cost reduction. Although various studies have been introduced to join Al alloy with the steel sheet by fusion welding, weak joint strength and galvanic corrosion still remained as problems to be solved. As a solid state welding, friction stir welding has been preferred to fusion welding processes in the dissimilar metal joints. This study investigated friction stir spot welding (FSSW) of Al alloy to the thin steel sheet with a thickness of 0.65 mm. The conventional FSSW is a stationary spot welding process but new approach adopted an additional circumferential movement in company with high speed tool rotation. A full factorial experimental design was implemented, and the main and interaction effects of parameters were analysed on the failure load in the tensile shear test. The direction and radius of rotation were statistically significant parameters and these two parameters affected the joint width and the shape of the hook.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.12 no.1
• /
• pp.32-37
• /
• 2003

Evaluation of fatigue strength on the spot welded part is very important for strength design of spot welded steel structures. In this paper, we could get the life cycle of the spot welded part using the lethargy coefficient obtained through the quasi-static tensile shear test for the specimen welded by current 10kA. The reliability evaluation of the life cycle is completed by comparing the life cycle calculated under the constant loading rate with the life cycle obtained by dynamic fatigue test. And then the result calculated by the lethargy coefficient is verified through the lift cycle calculated using the dynamic final tensile stress formula under the increased loading speed. This way can make save the time and cost in processing of predicting the life cycle of a structure.

• Proceedings of the KWS Conference
• /
• 2000.10a
• /
• pp.159-161
• /
• 2000

• Plant Journal
• /
• v.4 no.2
• /
• pp.66-72
• /
• 2008

In this inquiry, I would suggest jet ventilation system for effective elimination of welding flaw at machinery material welding shop on plant and evaluate the airstream on inner space and property of welding flaw's density through the examination. We can know outer atmosphere inflows at the speed of about 0.05m/s from western entrance in case of stopping the jet ventilation system, but airstream is accumulated on entire space. At height of worker's breathing surface(Ground Level = 1.5 m, below of GL) and welding work center, density of welding flaw on upper part(GL = 12m) is appeared 4 times higher than outer atmosphere at surplus range besides nearby of western entrance. At operation of jet ventilation system, since the smooth air current transfer at inner space and exhaust effect the wind speed is maintained at 0.932 m/s at the point of height of worker's breathing surface on inner space and it's concluded about the working conditions have been better than before operation of jet ventilation system because of that results show that inner space density of welding flaw at height of worker's breathing surface is 40.5%, and in the work shop, it is 20.3% at upper part.

• Journal of Welding and Joining
• /
• v.14 no.5
• /
• pp.87-94
• /
• 1996

It has been well known in GMA welding process that wire feeding speed (WFS) or deposition rate increases linealy with the increase of wire extension. In this investigation, however, such an well-known relationship was .reconsidered in terms of contact-tube to work distance (CTWD) instead of wire extension. To verify the proposed relationship between WFS and CTWD, bead-on-plate welding was performed with various CTWDs in the range of 15∼35mm under the condition of near-constant voltage and current As expected, the test results showed an excellent linear relation between WFS and CTWD. Furthermore, the value of the slope turned out to be quite similar to those of previous investigators obtained either theoretically or experimentally through the Precise measurement of electrode extension. Present result also demonstred that the increase of CTWD could be very practical measure for increaring deposition rate without any increase of heat input Depending on the tip recess the practical maximum of CTWD was appeared to be limited somewhere in 25∼30mm mainly due to the entrappment of porocity.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.10a
• /
• pp.642-646
• /
• 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, md' 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.