Ill-Soo Kim

Optimal design of neural networks for control in robotic arc welding

Robotic gas metal arc (GMA) welding is a manufacturing process which is used to produce high quality joints and has to a capability to be utilized in automation systems to enhance productivity. Despite its widespread use in the various manufacturing industries, the full automation of the robotic GMA welding has not yet been achieved partly because mathematical models for the process parameters for a given welding tasks are not fully understood and quantified. In this research, an attempt has been made to develop a neural network model to predict the weld bead width as a function of key process parameters in robotic GMA welding. The neural network model is developed using two different training algorithms; the error back-propagation algorithm and the Levenberg–Marquardt approximation algorithm. The accuracy of the neural network models developed in this study has been tested by comparing the simulated data obtained from the neural network model with that obtained from the actual robotic welding experiments. The result shows that the Levenberg–Marquardt approximation algorithm is the preferred method, as this algorithm reduces the root of the mean sum of squared (RMS) error to a significantly small value.

An investigation into the performance of solar cured adhesive bonded joints

Abstract In this research work attempts were made to study the bonding of thermoplastics with adhesives using solar radiation. In order to study the curing behaviour, experiments were conducted under varying conditions of temperature, exposure time and power. The cured samples were then studied under the optical microscope before subjecting them to tensile testing in order to study their mechanical properties. The fracture surfaces were further studied under the scanning electron microscopy in order to study the microstructural changes that are taking place during curing. In order to measure the performance of the solar radiation cured joints, features such as bond strength, surface morphology, microstructural changes, variation in properties of adhesives bonded joints are compared to those of specimens cured at ambient conditions and specimen cured using microwave techniques. From the present study, it is evident that curing under higher solar radiation temperature generally improves the bond strength and quality of the adhesive joints when compared to other modes of the curing process expect for the microwave curing process.

Development of Working Coil for Magnetic Pulse Welding

출원번호출원명 출원인출원연도US6977361 Molecular bonding of vehicle frame components using magnetic impulse welding techniquesDana Co. Ltd. 2005US687596 Apparatus for electromagnetic forming, joining and weldingFord Motor Company 2005US6548791 Energy storage apparatus and inductor tools for magnetic pulse welding and formingInli, LLC 국외 전자기 펄스 용접 기술은 이스라엘 Pulsar사의 2003US6389697 Fabricating automotive spaceframes using electromagnetic forming or magnetic pulse weldingFuel Cell and Integrators, Inc. 2002US6104012Molecular bonding of vehicle frame components using magnetic impulse welding techniquesDana Co. Ltd. 2000US5981921Method of magnetic pulse welding an end fitting to a driveshaft tube of a vehicular driveshaftDanaCo. Ltd. 1999US5824998Joining or welding of metal objects by a pulsed magnetic forcePulsar Welding Ltd. 1998* 「마그네틱 응용기술 및 시장분석」 (주) 비아글로벌 2006

A Study on HAZ Softening Characteristics of Fiber Laser Weldment for High-Strength Steel

Laser welding sector in the automotive industry has been widely recognized as one of the most important bonding processes, such as parts welding. Efforts to improve productivity and weld quality have been progressing steadily. In addition, laser welding is suitable for welding process that can produce high-quality welds suitable for flexible production and small quantity batch productions. In order to ensure the rigidity of the material, high strength material are applied to more than 1 GPa class body parts and automotive bumper beams. However, not only the situation is that the trend of domestic research, but also development is based on product molding considering freedom of shape where reinforcement is applied to meet the safety regulations and high-speed crash performance, despite the use of high strength materials. The tendency for heat-affected zone (HAZ) softening phenomenon common in areas of laser welded high tensile steel welding confirmed the occurrence of weld softening effect according to the process parameters. Based on this, range of process parameters could be selected for ensuring weld quality.

A Study on Development of STACO Model to Predict Bead Height in Tandem GMA Welding Process

One of the main challenges of the automatic arc welding process which has been widely used in various constructions such as steel structures, bridges, autos, motorcycles, construction machinery, ships, offshore structures, pressure vessels, and pipelines is to create specific welding knowledge and techniques with high quality and productivity of the production-based industry. Commercially available automated arc welding systems use simple control techniques that focus on linear system models with a small subset of the larger set of welding parameters, thereby limiting the number of applications that can be automated. However, the correlations of welding parameters and bead geometry as welding quality have mostly been linked by a trial and error method to adjust the welding parameters. In addition, the systematic correlation between these parameters have not been identified yet. To solve such problems, a new or modified models to determine the welding parameters for tandem GMA (Gas Metal Arc) welding process is required. In this study, A new predictive model called STACO model, has been proposed. Based on the experimental results, STACO model was developed with the help of a standard statistical package program, MINITAB software and MATLAB software. Cross-comparative analysis has been applied to verify the reliability of the developed model.

A Study about Analysis of Weld Distortion using Genetic Algorithm

Abstract In the process to manufacture for metallic structures, control of welding deformation is one of an importantproblems connected with reliability of the manufactured structures so that welding deformation should be measured and controlled with quickly and actively. Also, welding parameters which have as lot of effects on welding deformation such as arc voltage, welding current and welding speed can also be controlled. Theobjectives for this study were to develop a simple 2-D FEM to calculate not only the transient thermalhistories but also the sizes of fusion and heat-affected zone (HAZ) in multi pass arc welds including the butt and fillet weld type with dissimilar thickness, and to concentrate on a developed model for the finding the parameters of Godak’s moving heat source model based on a GA. The developed model includes a GA program using MATLB and GA toolbox, and a batch mode thermal model using ANSYS software. Not only the thermal model was verified by comparison with Goldak’s work but also the developed model was validated with molten zone section experimental data.Key Words : Weld distortion, Genetic algorithm, Double-ellipse heat input model, Finite element method

A Experiment Study of Torch Distance on Automated Tandem GMA Welding System

Abstract The tandem welding process is one of the most efficient welding processes widely used in material joining technique such as manufacturing of strong and durable structures. It facilitates high rate of joint fillingwith little increase in the overall rate of heat input due to the simultaneous deposition from two electrode wires. The two electrodes in tandem welding process helps in high-efficiency and high productive of welding process. In this study a automated tandem welding system is developed to determine the correlation between cathodeand anode and compared with current ratio of the two electrode torch. Three different inter-electrode distanceswere chosen, 25mm, 35mm and 45mm to perform the experiment with three different current ratio. From the experiment results, the current ratio between two torch has a large impact on width, height and depth of penetration. In addition, a stable bead geometry is obtained when inter-electrode distance is 35mm.Key Words : Tandem GMAW, Interface controller, Torch distance, Current ratio

Prediction model for bead reinforcement area in automatic gas metal arc welding

Automatic welding systems are widely used for high-volume production industries, where the cost of related equipment is justified by the large number of pieces to be made. Detailed movement devices are required, including predetermined welding parameter sequences and timers, to form the weld joints. Automatic gas metal arc welding processes require new mathematical models to predict optimal welding parameters for a given bead geometry to accomplish the desired mechanical properties of the weldment. The developed algorithm should be able to be employed across a wide range of material thicknesses and all welding positions, and available in analytical form to be easily applied to the welding robot with high degree of confidence in predicting bead dimensions. Therefore, this study investigated welding voltage, arc current, welding speed, contact tube weld distance, and welding angle on bead reinforcement area for automated gas metal arc welding processes using a central composite design to generate response surface methodology and artificial neural network models. Average absolute deviation was used to compare accuracy between the two models. Analysis of variance showed coefficients of determination of 0.894 and 0.948 with average absolute deviation 4.01% and 3.11% for the response surface methodology and artificial neural network models, respectively. This suggests that artificial neural network is a better modeling technique for predicting bead reinforcement area compared to response surface methodology.

An Experimental Study on Prediction of Bead Geometry for GTA Multi-pass Welding in Underhead Position

Abstract The automatic arc welding is generally accepted as the preferred joining technique and commonly chosen for assembly of large metal structures such as in areas of automotive, aircraft and shipbuilding due to its joint strength, reliability, and low cost compared to other joint processes. Recently, several mathematical models have been developed and studied for control and monitoring welding quality, productivity, microstructure and weld properties in arc welding processes. This study indicates the prediction of process parameters for the expected welding quality with accordance to the adaptive GTA welding process. Furthermore, the mathematical models is also develop to aid the selection of an optimal welding process as the generation of process controls to predict the bead geometry as a function output parameters in the GTA welding process. The developed models through this study showed comparatively excellent predicted results, and will extend to other welding processes to integrate an optimized system for the robotic welding process.Key Words : GTAW, Multi-pass welding, Mathematical model, Curvilinear model, Main effects plot

Development on Tandem GMA Welding System using Seam Tracking System in Pipe Line

In this study to improve the productivity, advantage Tandem circumferential weld process of seam tracking system was applied for the laser vision sensor. Weld geometry scanning laser vision sensor and PLC control unit are used to scan correct positioning of welding torch when the program is implemented so that it can correctly track the welding line. The welding experiment was conducted to evaluate the performance of laser vision seam tracking sensor in tandem welding process. The seam tracking several experiments was to determine the reliability of the system, welding experiments relatively good quality welding bead was confirmed. Furthermore, the PLC program for seam tracking was used to confirm the validity of the application of tandem welding process according to the benefits of increased productivity, which is expected to contribute to national competitiveness.