• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.679-682
• /
• 2002

Resistance spot welding using air gun has been used for joining the sheet metal in automotive manufacturing process. Although air gun has many advantages, it also has the limitation to control the pressure as a factor to improve weld quality. In this study, we apply servo gun using servo motor to resistance spot welding and find the relationship between welding pressure and welding quality. Trough the experiment to change welding pressure during the welding cycle, we can make it clear that the change of welding pressure is greatly influence on the welding quality. To get in a. using response surface methodology, drew out the optimal welding pressure profile for welding quality progresses. We made an optimal profile of welding pressure which improves welding quality using response surface methodology.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.6
• /
• pp.473-479
• /
• 2019

Welding is one of the most popular joining methods and most welding quality estimation methods are executed using joined material. This paper propose welding quality estimation methods using dynamic current, voltage and resistance which are obtained during welding in real time. There are many kinds of welding method. Among them, we focused on the projection welding and gathered dynamic characteristics from two different types of projection welding. For image learning, graphs are drawn using obtained current, voltage and resistance, and the graphs are converted to images. The images are labeled with two sub-categories - normal and defect. For deep learning of images obtained from welding, Convolutional Neural Network (CNN) is applied, and Tensorflow was used as a framework for deep learning. With two resistance welding test datasets, we conclude that the Convolutional Neural Network helps in predicting the welding quality.

• Journal of Welding and Joining
• /
• v.20 no.6
• /
• pp.45-45
• /
• 2002

This study is a middle report on the development of intelligent spot welding monitoring technology applicable to the production line. An intelligent algorithm has been developed to predict the quality of welding in real time. We examined whether it is effective or not through the In-Line and the Off-Line tests. The purpose of the present study is to provide a reliable solution which can prevent welding defects in production site. In this study, the process variables, which were monitored in the primary circuit of the welding, are used to estimate the weld quality by Hidden Markov Model(HMM). The primary dynamic resistance patterns are recognized and the quality is estimated in probability method during the welding. We expect that the algorithm proposed in the present study is feasible to the applied in the production sites for the purpose of in-process real time quality monitoring of spot welding.

• Journal of Welding and Joining
• /
• v.20 no.6
• /
• pp.769-775
• /
• 2002

This study is a middle report on the development of intelligent spot welding monitoring technology applicable to the production line. An intelligent algorithm has been developed to predict the quality of welding in real time. We examined whether it is effective or not through the In-Line and the Off-Line tests. The purpose of the present study is to provide a reliable solution which can prevent welding defects in production site. In this study, the process variables, which were monitored in the primary circuit of the welding, are used to estimate the weld quality by Hidden Markov Model(HMM). The primary dynamic resistance patterns are recognized and the quality is estimated in probability method during the welding. We expect that the algorithm proposed in the present study is feasible to the applied in the production sites for the purpose of in-process real time quality monitoring of spot welding.

• 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.

• Proceedings of the KSME Conference
• /
• 2001.11a
• /
• pp.791-796
• /
• 2001

Welding using lasers can be mass-produced in high speed. In the laser welding, performing real-time evaluation of the welding quality is very important in enhancing the efficiency of welding. In this study, the plasma and molten metal which are generated during laser welding were measured using the UV sensor and IR sensor. The results of laser welding were classified into five categories such as optimal heat input, little low heat input, low heat input, focus off, and nozzle change. Also, a system was formulated which uses the measured signals with a fuzzy pattern recognition method which is used to perform real-time evaluation of the welding quality and the defects which can occur in laser welding. Weld quality prediction program was developed using previous weld results and statistical program which could show the trend of weld quality and signal was developed.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.15 no.5
• /
• pp.31-38
• /
• 2016

This study proposes an optimal design for a robotic welding system for a high-strength steel armor plate. In order to identify the welding defect parameters, we analyzed the 4M (man, machine, materials, method) characteristics diagram, as well as a cause and effect matrix, to improve the productivity and quality of welding defects. From these analyses, we designed optimal welding conditions and carried out welding tests -- such as mechanical testing and macro structure tests - with positive results. We determined that it was possible to obtain a quality similar to manual welding with our robotic welding system. In the future, we expect that the system will be used as inspiration for future welding system designs.

• Journal of Welding and Joining
• /
• v.18 no.3
• /
• pp.114-121
• /
• 2000

Since resistance spot welding has become one of the most popular sheet metal fabrication processes, a strong emphasis is being put on the quality of the welds. Throughout the years many quality estimation systems have been developed by many researchers to ensure weld quality. In this study, the process variables, which were monitored in the primary circuit of the welding machine, are used to estimate the weld quality with Hopfield neural network. The primary dynamic resistance is vectorized and stored as five patterns in the network. As the welding is done, the dynamic resistance patterns are recognized and the quality is estimated with the proposed method. Due to the primary process variables, it is possible to utilize this algorithms as an in-process real time quality monitoring system.

• International Journal of Korean Welding Society
• /
• v.3 no.1
• /
• pp.45-50
• /
• 2003

Welding using lasers can be mass-produced in high speed. In the laser welding, performing real-time monitoring system of the welding quality is very important in enhancing the efficiency of welding. In this study, the plasma and molten metal which are generated during laser welding were measured using the UV sensor and IR sensors. The results of laser welding were classified into five categories such as optimal heat input, little low heat input, low heat input, partial joining due to gap mismatch, and nozzle deviation. Also, a system was formulated which uses the measured signals with a fuzzy pattern recognition method which is used to perform real-time evaluation of the welding quality and the defects which can occur in laser welding.

• Proceedings of the KWS Conference
• /
• 2002.10a
• /
• pp.606-611
• /
• 2002

Welding using lasers can be mass-produced in high speed. In the laser welding, performing real-time monitoring system of the welding quality is very important in enhancing the efficiency of welding. In this study, the plasma and molten metal which are generated during laser welding were measured using the UV sensor and IR sensors. The results of laser welding were classified into five categories such as optimal heat input, little low heat input, low heat input, partial joining due to gap mismatch, and nozzle deviation. Also, a system was formulated which uses the measured signals with a fuzzy pattern recognition method which is used to perform real-time evaluation of the welding quality and the defects which can occur in laser welding.