• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.6
• /
• pp.57-63
• /
• 1998

An adaptive control in the robotic GMA welding is employed to monitor information about weld characteristics and process parameters as well as to modify those parameters to hold weld quality within acceptable limits. Typical characteristics are the bead geometry, composition, microstructure, appearance, and process parameters which govern the quality of the final weld. The main objectives of this thesis are to realize the mapping characteristics of bead width through learning. After learning, the neural estimation can estimate the bead width desired form the learning mapping characteristic. The design parameters of the neural network estimator(the number of hidden layers and the number of nodes in a layer) are chosen from an estimation error analysis. A series of bead of bead-on-plate GMA welding experiments was carried out in order to verify the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can predict the bead width with reasonable accuracy and guarantee the uniform weld quality.

• Journal of Welding and Joining
• /
• v.18 no.6
• /
• pp.55-61
• /
• 2000

Dynamic monitoring of weld pool formation and seam deviations using infrared vision is described in this paper. Isothermal contours representing heat dissipation characteristics during the process of arc welding were analysed and processed using imaging techniques. Maximum bead width and penetration were recorded and the geometric position in relation to the welding seam was measured at each sampling point. Deviations from the desired bead geometry and welding path were sensed and their thermographic representations were digitised and welding path were sensed and their thermographic representations were digitised and subsequently identified. Evidence suggested that infrared thermography can be utilized to compensate for inaccuracies encountered in real-time during robotic arc welding.

• Journal of the Korean Institute of Navigation
• /
• v.23 no.4
• /
• pp.105-114
• /
• 1999

Generally, though we use the vision sensor or arc sensor in welding process, it is difficult to define the welding parameters which can be applied to the weld quality control. Especially, the important Parameters is Arc Voltage, Welding Current, Welding Speed in arc welding process and they affect the decision of weld bead shape, the stability of welding process and the decision of weld quality. Therefore, it is difficult to determine the unique relationship between the weld bead geometry and the combination of various welding condition. Due to the various difficulties as mentioned, we intend to use Fuzzy Logic and Neural Network to solve these problems. Therefore, the combination of Fuzzy Logic and Neural network has an effect on removing the weld defects, improving the weld quality and turning the desired weld bead shape. Finally, this system can be used under what kind of welding recess adequately and help us make an estimate of the weld bead shape and remove the weld defects.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.6
• /
• pp.1379-1386
• /
• 2005

For efficient welding it is necessary to maintain stability of the welding process and control the shape of the welding bead. The welding quality can be controlled by monitoring important parameters, such as, the Arc Voltage, Welding Current and Welding Speed during the welding process. Welding systems use either a vision sensor or an Arc sensor, both of which are unable to control these parameters directly. Therefore, it is difficult to obtain necessary bead geometry without automatically controlling the welding parameters through the sensors. In this paper we propose a novel approach using fuzzy logic and neural networks for improving welding qualify and maintaining the desired weld bead shape. Through experiments we demonstrate that the proposed system can be used for real welding processes. The results demonstrate that the system can efficiently estimate the weld bead shape and remove the welding detects.

• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.596-599
• /
• 2004

The robotic $CO_2$ welding is a manufacturing process to produce high quality joints for metal and it could provide a capability of full automation to enhance productivity. 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 research, an attempt has been made to develop an intelligent algorithm to predict the weld geometry (top-bead width, top-bead height, back-bead width and back-bead height) as a function of key process parameters in the robotic $CO_2$welding. To achieve this above objective, Taguchi method was employed using five different process parameters (tip gap, gas flow rate, welding speed, arc current, welding voltage) as a guide for optimization of process parameters.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.189-193
• /
• 1997

Generally, though we use the vision sensor or arc sensor in welding process, it is difficult to define the welding parameters which can be applied to the weld quality control. Especially, the important parameters is Arc Voltage, Welding Current, Welding Speed in arc welding process and they affect the decision of weld bead shape, the stability of welding process and the decision of weld quality. Therefore, it is difficult to determine the unique relationship between the weld bead geometry and the combination of various welding condition. Due to the various difficulties as mentioned, we intend to use Fuzzy Logic and Neural Network to solve these problems. Therefore, the combination of Fuzzy Logic and Neural network has an effect on removing the weld defects, improving the weld quality and turning the desired weld bead shape. Finally, this system can be used under what kind of welding process adequately and help us make an estimate of the weld bead shape and remove the weld defects.

• International Journal of Korean Welding Society
• /
• v.1 no.1
• /
• pp.23-30
• /
• 2001

Among the various welding conditions, the welding current that is inversely proportional to the tip-to-work-piece distance is an essential parameter as to monitor the GMAW process and to implement the welding automation. Considering the weld pool surface geometry including weld defects, it should modify the signal processing method for automatic seam tracking in horizontal fillet welding. To meet the above necessities, a mathematical model related with the weld pool geometry was proposed as in a conjunction with the two-dimensional heat flow analysis of the horizontal fillet welding. The signal processing method based on the artificial neural network (Adaptive Resonance Theory) was proposed for discriminating the sound weld pool surface from that with the weld defects. The reliability of the numerical model and the signal processing method proposed were evaluated through the experiments of which showed that they are effective for predicting the weld bead shape with or without the weld defects in a horizontal fillet welding.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.128.5-128
• /
• 2001

This paper presents investigation of an arc force sensor for a robotic welding control system. Arc force sensor is employed in this research to monitor the bead geometry of the arc welding process. Arc force sensor mounted at the end of the robot wrist was employed to measure the arc force applied to the weld. Experimental configuration for measurement of arc force was used to quantify the changes in the arc force distributions of the plate being welded. A relationship between the bead dimension and the arc force distributions was established. The sensor information was used to establish a relationship between welding current and arc force. Arc force sensor have shown to be one of the most sophisticated technique to monitor perturbations that occurred during robotic arc welding process.

• 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.