• Journal of Welding and Joining
• /
• v.17 no.5
• /
• pp.40-46
• /
• 1999

The sensors employed in the robotic are welding system must detect the changes in weld characteristics and produce the output that is in some way related to the change being detected. Such adaptive systems, which synchronise the robot arm and eyes using a primitive brain will form the basis for the development of robotic GMA(Gas Metal Arc) welding which increasingly higher levels of artificial intelligence. The objective of this paper is to realize the mapping characteristics of bead height through learning. After learning, the neural estimation can estimate the bead height desired from 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 height with reasonable accuracy and guarantee the uniform weld quality.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.4
• /
• pp.79-86
• /
• 2007

The shape of excessive penetration mainly depends on welding conditions(welding current and welding voltage), and welding process(groove gap and welding speed). These conditions are the major affecting factors to width and height of back bead. In this paper, back-bead prediction and weldability estimation using artificial neural network were investigated. Results are as follows. 1) If groove gap, welding current, welding voltage and welding speed will be previously determined as a welding condition, width and height of back bead can be predicted by artificial neural network system without experimental measurement. 2) From the result applied to three weld quality levels(ISO 5817), both experimented measurement using vision sensor and predicted mean values by artificial neural network showed good agreement. 3) The width and height of back bead are proportional to groove gap, welding current and welding voltage, but welding speed. is not.

• International Journal of Korean Welding Society
• /
• v.4 no.1
• /
• pp.30-37
• /
• 2004

There have been continuous efforts on automating welding processes. This automation process could be said to fall into two categories, weld seam tracking and weld quality evaluation. Recently, the attempts to achieve these two functions simultaneously are on the increase. For the study presented in this paper, a vision sensor is made, a vision system is constructed and using this, the 3 dimensional geometry of the bead is measured on-line. For the application as in welding, which is the characteristic of nonlinear process, a fuzzy controller is designed. And with this, an adaptive control system is proposed which acquires the bead height and the coordinates of the point on the bead along the horizontal fillet joint, performs seam tracking with those data, and also at the same time, controls the bead geometry to a uniform shape. A communication system, which enables the communication with the industrial robot, is designed to control the bead geometry and to track the weld seam. Experiments are made with varied offset angles from the pre-taught weld path, and they showed the adaptive system works favorable results.

• Special Issue of the Society of Naval Architects of Korea
• /
• 2005.06a
• /
• pp.192-197
• /
• 2005

A welding bead height is closely related to the efficiency of welding work, and the height of 3mm is used in the conventional practice of butt welding. in the present paper, the modification of bead height from 3mm to 6mm is considered to increase the efficiency and work productivity of butt welding on bottom plate (of BONGA FPSO actually built in SHI shipyard). Therefore, fatigue analysis has been carried out using simplified method based on the DNV Rules. It is found that the minimum fatigue life is about 594 years and the butt welding details with 6mm bead height has sufficient strength and resistance against fatigue.

• Journal of the Society of Naval Architects of Korea
• /
• v.35 no.3
• /
• pp.62-70
• /
• 1998

This paper is a study on the fatigue Strength depending on bead height. According to the AWS CODE D1.1, reinforcement shall not exceed 1/8"(3.2mm) in height. Most of the bead heights exceed AWS rule in actual welding. So we estimated the fatigue Strength of the as-welded specimens and the removed bead specimens of which height is 3mm with SAW 2 pole process. As a result, this paper presents that fatigue Strength is not concerned with as welded condition and removed 3mm bead height, also fatigue Strength obtained as welled specimens are satisfied with those proposed by the UK DEN, DNV and AWS.

• Journal of Ocean Engineering and Technology
• /
• v.16 no.2
• /
• pp.53-59
• /
• 2002

This paper shows the experimental results controlling the height of surface and back bead in GMAW by analyzing the unexpected gaps between base metals produced in welding and by controlling welding velocity due to the variation of the gap between base metals in thin-plate welding. The back bead behavior and burn-through in I-type butt joint $CO_2$ welding of thin mild steel are analyzed in the views of short circuit time ratio and short circuit frequency. It is shown through experimental consideration that the short circuit time ratio method is more reasonable than the short circuit frequency method in analyzing the formulation of back bead under changing the gap between base metals. Based on the these results, welding manipulator is designed so as to satisfy the bead height control in real time by measuring the short circuit time ratio. To show the effectiveness of the developed bead formulation control system, the experiment is implemented under two welding conditions such as increasing gap from 0mm to 0.8mm and gradually increasing gap from 0mm to 1.2mm. The experimental results show that the bead formulation can be controlled uniformly in spite of the variation of the gap between base metals.

• 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.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.4
• /
• pp.132-139
• /
• 2002

In GMAW(Gas Metal Arc Welding) processes, bead geometry (penetration, bead width and height) is a criterion to estimate welding quality. Bead geometry is affected by welding current, arc voltage and travel speed, shielding gas, CTWD (contact-tip to workpiece distance) and so on. In this paper, welding process variables were selected as welding current, arc voltage and travel speed. And bead geometry was reasoned from the chosen welding process variables using neuro-fuzzy algorithm. Neural networks was applied to design FL(fuzzy logic). The parameters of input membership functions and those of consequence functions in FL were tuned through the method of learning by backpropagation algorithm. Bead geometry could be reasoned from welding current, arc voltage, travel speed on FL using the results learned by neural networks. On the developed inference system of bead geometry using neuro-furzy algorithm, the inference error percent of bead width was within $\pm$4%, that of bead height was within $\pm$3%, and that of penetration was within $\pm$8%. Neural networks came into effect to find the parameters of input membership functions and those of consequence in FL. Therefore the inference system of welding quality expects to be developed through proposed algorithm.

• Journal of Welding and Joining
• /
• v.27 no.1
• /
• pp.95-101
• /
• 2009

In case of manufacturing the high quality welds or pipeline, the full penetration weld has to be made along the weld joint. Thus the root pass welding is very important and has to be selected carefully. In this study, an experimental method for the selection of optimal welding condition was proposed in the root pass welding which was done along the V-grooved butt weld joint. This method uses the response surface analysis in which the width and height of back bead were chosen as the quality variables of the weld. The overall desirability function, which is the combined desirability function for the two quality variables, was used as the objective function for getting the optimal welding condition. In the experiments, the target values of the back bead width and the height are 6mm and zero respectively for the V-grooved butt weld joint of 8mm thickness mild steel. The optimal welding conditions could predict the back bead profile(bead width and height) as 6.003mm and -0.003mm. From a series of welding test, it was revealed that a uniform and full penetration weld bead can be obtained by adopting the optimal welding condition which was determined according to the method proposed.

• International Journal of Automotive Technology
• /
• v.6 no.2
• /
• pp.191-196
• /
• 2005

A full-bead of multi-layer-steel (MLS) engine head gasket is used to seal the combustion gas. Finite element analyses were conducted to assess the dependence of the sealing performance of full-bead on the forming process consisting of embossing and flatting operations. It is demonstrated that the sealing performance is enhanced with more severe deformation of the bead plate during the embossing, i.e., with the increase in the punching depth, the punch height, the punch width and the friction coefficient of the bead plate against the punch and die, and with the decrease in the width of die cavity. Meanwhile, the flatting process that is employed to adjust the height of the embossed full-bead has no influence on the sealing performance.