This paper describes several advances in sensor and process control techniques for applications in Submerged Arc Welding (SAW), which combine to give a fully automatic system capable of controlling and adapting the overall welding process. This technology has been applied in longitudinal and spiral pipe mills and in pressure vessel production.

Real time monitoring has become critical as the use of laser welding increases. Plasma and spatter are measured and used as the signal for estimating weld quality. The estimating algorithm was made using the fuzzy pattern recognition with the area of data that is beyond the tolerance boundary. Also, an algorithm that detects the spatter and the localized defect was created in order to kd the partially produced pit and the sudden loss of weld penetration. These algorithms were used in quality monitoring of the $CO_2$ laser tailored blank weld. Statistical program that can display the laser weld quality result and the signal transition was made for the first stage of the remote control system.

High speed seam weldability of tin coated steels was investigated. Welding was performed by the laboratory wire seam welder that was equipped with process monitoring system Test results showed that increase in applied current and pressure reduced the total resistance across the welding electrodes. Lower and upper limits of welding current increased as the sheet thickness increased, while the acceptable welding condition range decreased. However, extremely low electrode pressure produced unstable welding condition range. The results also demonstrated that slower welding speeds widened the optimum welding heat input range.

Because the quantitative relationships between welding parameters and welding result are not yet blown, optimal values of welding parameters for $CO_2$ robotic arc welding is a difficult task. Using the various artificial data processing methods may solve this difficulty. This research aims to develop an expert system for $CO_2$ robotic arc welding to recommend the optimal values of welding parameters. This system has three main functions. First is the recommendation of reasonable values of welding parameters. For such work, the relationships in between the welding parameters are investigated by the use of regression analysis and fuzzy system. The second is the estimation of bead shape by a neural network system. In this study the welding current voltage, speed, weaving width, and root gap are considered as the main parameters influencing a bead shape. The neural network system uses the 3-layer back-propagation model and a generalized delta rule as teaming algorithm. The last is the optimization of the parameters for the correction of undesirable weld bead. The causalities of undesirable weld bead are represented in the form of rules. The inference engine derives conclusions from these rules. The conclusions give the corrected values of the welding parameters. This expert system was developed as a PC-based system of which can be used for the automatic or semi-automatic $CO_2$ fillet welding with 1.2, 1.4, and 1.6mm diameter the solid wires or flux-cored wires.

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.

For the horizontal fillet welding with one plate in a vertical position, there will be a higher tendency of weld metal falling down rather than for the butt-welding in flat position. Such phenomenon could bring about the overlap or deflection of weld pool, and consequently induce the poor mechanical strength of weldments. Therefore, a precise position control of welding torch in conjunction with the weld qualify plays an important role in welding robot applications. In the present study, an experimental method was proposed for deriving a mathematical model between the leg length and the welding conditions. Finally, an algorithm was proposed for weld seam tracking and improvement of the weld quality. The reliability of the proposed algorithm was evaluated through various experiments, which showed that the proposed algorithm can be very effective for tracking the weld line and simultaneously achieving the sound weld bead.

In this paper, the neutron diffraction is applied to the residual stress measurement on the 20mm-thick welded stainless steel plate ($100^{\circ}$$\times$100$mm^2$). The High Resolution Powder Diffractormeter of the Korea Atomic Research Institute The power of nuclear reactor was 24 MWt and the measured reflection in the 220 plane (2$\theta$ is $95^{\circ}$and wavelength is 1.8340 ${\AA}$ . The Poisson ratio of 0.265 and elastic constant of 211 GPa are applied to the calculation of stresses and strains. Three directional components such as normal, transverse, and longitudinal stresses are measured and the results show that the most of longitudinal stress is tensile and decreases, changing to compressive depending on the distance away from the welded spot. However, transverse component is changing from tensile to compressive along the depth of the welded point.

A genetic algorithm was applied to the arc welding process as to determine the near-optimal settings of welding process parameters that produce the good weld quality. This method searches for optimal settings of welding parameters through the systematic experiments without the need for a model between the input and output variables. It has an advantage of being capable to find the optimal conditions with a fewer number of experiments rather than conventional full factorial designs. A genetic algorithm was applied to the optimization of the weld bead geometry. In the optimization problem, the input variables were wire feed rate, welding voltage, and welding speed. The output variables were the bead height bead width, and penetration. The number of levels for each input variable is 16, 16, and 8, respectively. Therefore, according to the conventional full factorial design, in order to find the optimal welding conditions,2048 experiments must be performed. The genetic algorithm, however, found the near optimal welding conditions in less than 40 experiments.

Effect of the joint details on the stress distribution over a slot structure has been studied in order to improve its fatigue life using a finite element analysis. The joint details of interest are the radius and height of scallop at the stiffener as well as the mis-alignment between the stiffener and longitudinal member. For a slot structure currently used, the stiffener heel is subjected to the maximum stress for a given external load, where is a potential fatigue crack initiation site. The stresses at the stiffener heel and toe decrease both by increasing the scallop radius and more significantly by increasing the mis-alignment while no notable effect of the scallop height on it is appreciated. A proper combination of these factors makes it possible to reduce the stresses at the stiffener heel and In, theoretically, more than 50%. This is attributed to the modification of the stress distribution over the slot structure including the transition of the maximum stressed region from the stiffener heel to the slot surface of the transverse web. Such then results in a g[eat improvement of the fatigue life of the slot structure.

The surface of AC8A Ah alloy was modified by adding the Cu powder using a Plasma Transferred Arc (PTA) welding process. Under the optimum fabricating conditions, the modified surface of AC8A Ah alloy was observed to possess the sound microstructure with a minimum porosity. Hardness and wear resistance properties of the as-fabricated alloy were compared with those of the 76 heat-treated one. In case of the as-fabricated alloy, the hardness of the modified layer was twice that of the matrix region. Although significant increase in the hardness of the matrix region was observed after T6 heat treatment, the hardness of the modified layer was not observed to change. The wear resistance of the modified layer was significantly increased compared to that of the matrix region. The microstructure of a weld zone and the matrix region were investigated using the optical microscope, scanning electron microscope (SEM), electron probe microanalysis (EPMA), and transmission electron microscope (TEM). The primary and eutectic silicon in the weld zone were finer and more curved than in the matrix region, while some precipitates has had been found therein. According to the TEM observation, the predominant precipitate present in the weld zone was the $\theta$'phase, which is precipitated during cooling by rapid solidification in PTA welding process. Improvement of hardness and wear properties in the weld zone in the as-fabricated condition can be explained based on the presence of $\theta$’precipitates and fine primary and eutectic silicon distribution.

The solidification cracking susceptibilities of Al-Mg alloy laser welds were assessed using self-restraint tapered specimen crack test. The dependence of cracking susceptibility of Al-Mg alloy laser welds on Mg contents was observed to be similar to that of arc welds in the same materials. The cracking susceptibility of Al-Mg alloy laser welds increased as Mg content increased up to 1.6-1.9 wt.% and then it decreased as Mg content increased further. The peak cracking susceptibility occurred at around 1.6 to 1.9 wt.% Mg for both autogenous and wire feed welds. It was also observed that the cracking susceptibility decreased as the grain size of Al-Mg alloy laser welds decreased, when Mg content was in the range higher than 1.9 wt.%.

The characteristics of the fume generation in a flux cored arc welding were investigated using the fume collection chamber developed. The Korean Standard concerning the method for the evaluation of the fume generation rate(FGR) was updated by the evaluation method obtained through this study. It was found that the effect of humidity in the test environment should be considered and the automatic welding method had to be employed for the purpose of the exact evaluation of the fume generation rate. The results showed that the fume generation rate was influenced by the welding parameters. The important factors were the welding current arc voltage, travel speed, and contact tip to work distance(CTWD) that affected the heat input as well as the torch angle and the shielding gas flow rate that influenced the shielding effect. The fume generation rate increased as the heat input increased and the shielding effect decreased. It was also observed that the effect of the welding current is much grater than the other welding parameters.