• Nuclear Engineering and Technology
• /
• v.56 no.10
• /
• pp.4149-4157
• /
• 2024

Welding processes are used to connect several components in nuclear power plants. These welding processes can induce residual stress in welding joints, which has been identified as a significant factor in primary water stress corrosion cracking. Consequently, the assessment of welding residual stress plays a crucial role in determining the structural integrity of welded joints. In this study, a deep fuzzy neural networks (DFNN) with a rule-dropout method, which is an artificial intelligence (AI) method, was used to predict the residual stress of dissimilar metal welding. ABAQUS, a finite element analysis program, was used as the data collection tool to develop the AI model, and 6300 data instances were collected under 150 analysis conditions. A rule-dropout method and genetic algorithm were used to optimize the estimation performance of the DFNN model. DFNN with the rule-dropout model was compared to a deep neural network method, known as a general deep learning method, to evaluate the estimation performance of DFNN. In addition, a fuzzy neural network method and a cascaded support vector regression method conducted in previous studies were compared. Consequently, the estimation performance of the DFNN with the rule-dropout model was better than those of the comparison methods. The welding residual stress estimation results of this study are expected to contribute to the evaluation of the structural integrity of welded joints.

• Fashion & Textile Research Journal
• /
• v.15 no.3
• /
• pp.452-460
• /
• 2013

This study conducted a performance evaluation of protective clothing materials used for welding in a hazardous shipbuilding industry work environment. The welding process was selected as the one that most requires industrial protective clothing according to work environment characteristics. Flame proofing and convection heat protection performance (HTI) in the heat transfer characteristics of protective clothing material were indicated in the order of SW1(Oxidant carbon)>SW2(silica coated Oxidant carbon)>SW4(Oxidant carbon/p-aramid)>SW3(flame proofing cotton). However, radiant heat protection performance (RHTI) and the heat transfer factor (TF) were indicated in the order of SW1>SW4>SW2>SW3 and showed different patterns from the convection heat protection performance. SW1 showed superior air permeability and water vapor permeability. The tensile strength and tear strength of welding protective clothing material were indicated in the order of SW4>SW2>SW3>SW1 and showed that a blend fabric of p-aramid was the most superior for the mechanical properties of SW4. SW1 had excellent heat transfer properties in yet met the minimum performance requirements of tensile strength proved to be inappropriate as being a material for welding protective clothing. The abrasion resistance of woven fabric proved superior compared to nonwoven fabric; however, seam strength and dimensional change both met the minimum performance requirements and indicated that all samples appeared non-hazardous. Finally, oxidant carbon/p-aramid blend fabric appeared appropriate as a protective clothing materials for welding.

• Coupled systems mechanics
• /
• v.7 no.5
• /
• pp.627-634
• /
• 2018

Laser beam welding is more advantageous compared to conventional methods. Titanium/Aluminium dissimilar alloy thin sheet metals are difficult to weld due to large difference in melting point. The performance of the weldment depends upon interlayer formation and distribution of intermetallics. During welding, aluminium gets lost at the temperature below the melting point of titanium. Therefore, it is needed to improve a new metal joining techniques between these two alloys. The present work is carried for welding TI6AL4V and AA2024 alloy by using Nd:YAG Pulsed laser welding unit. The performance of the butt welded interlayer structures are discussed in detail using hardness test and SEM. Test results reveal that interlayer fracture is caused near aluminium side due to low strength at the weld joint.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.1
• /
• pp.9-18
• /
• 2007

There have been continuous efforts for automation of joint tracking system. This automation process is mainly used to do in root pass of gas metal arc welding in the field of heavy industry and shipbuilding etc. For automation, it is important using of vision sensor. Welding robot with vision sensor is used for weld seam tracking on welding fabrication. Recently, it is used to on post-weld inspection for weld quality evaluation. For real time seam tracking, it is very important role in vision process technique. Vision process is included in filtering and thinning, segmentation processing, feature extraction and recognition. In this paper, it has shown performance comparison results of seam tracking for real time root pass on gas metal arc welding. It can be concluded better segment splitting method than iterative averaging technique in the performance results of seam tracking.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.4 no.4
• /
• pp.54-60
• /
• 2005

In a $CO_2$ inverter welding machine, stable arcs can be generated and a welding performance that is a goal of welding can be improved when stable electric power with a low voltage and a high current is supplied to a electrode that is the secondary part (output load terminal) and the base metal. For such a stable power supply, therefore, the AC arc welding machine, the thyristor welder, and the inverter welder have been developed in order according to development of the power electronics techniques. Up to now, the thyristor welding machine is still broadly used but the application volume is gradually reduced by development of the inverter welder. Because the welding performance of the inverter welder is very good and the weight and size of the welder is remarkably light and small. The final goal of this research is to develop the voltage loss compensator that is a drawback of the inverter welder and improve the welding performance using the developed compensator.

• Proceedings of the KIPE Conference
• /
• 1998.10a
• /
• pp.1012-1016
• /
• 1998

According to the adoption of inverter circuit topology for welding machine area, the improvement of welding performance can be achieved. However conventional CO2 inverter arc welding machine uses the constant voltage characteristics. So the metal transfer is performed under unoptimum condition in the sence of spatter generation. In this paper the new control algorithm is proposed for welding machine, which is the instantaneous output current control method using single chip microprocessor. But the optimum waveform of welding current is still uncertain, as a first step for figuring out the optimized waveforms, this study was performed. And as a result of performance test of the proposed system, it was demonstrated that all of the waveform variation parameter could be set individually and the generated spatter is reduced compared to conventional inverter arc welding machine.

• Journal of Welding and Joining
• /
• v.33 no.4
• /
• pp.50-56
• /
• 2015

In general, discontinuity of metallurgical and structural points of weld zone could decline the fatigue strength. For the lightweight trend, the AHSS application in automotive chassis is in-progress. However, there are few research reports on AHSS welds fatigue strength in especially automotive chassis parts. Therefore, in this study, we evaluated the effects of the factors affecting the AHSS welding fatigue strength. As the result, the stress concentration of weld bead is the most important factor for welding fatigue strength. For the enhancement of welding fatigue strength, we focused on reducing the stress concentration of the welding beads. So, we applied and proved the plasma welding process and GTAW (Gas Tungsten Arc Welding) dressing method. It was verified by uniaxial fatigue specimen, fatigue performance increased from 40 to 60% by applying TIG dressing method compared to the conventional GMAW (Gas Metal Arc Welding). These results could be recommended the enhancement of fatigue performance of AHSS.

• Proceedings of the KWS Conference
• /
• 2000.10a
• /
• pp.238-239
• /
• 2000

• Proceedings of the KWS Conference
• /
• 2006.10a
• /
• pp.120-122
• /
• 2006

This study deals with characterizations of microstructure and wear performance of a cladding layer, product on 1.9 mm-thick mild steel plate by the electric resistance welding, of composite metal powder of Coarse WC-6.5%Co and high carbon alloy(SHA). The cladding layer was examined and tested fur microstructural features, chemical composition, hardness, wear performance and wear mechanism. The cladding layer have two different matrix were observed by an optical microscope and EPMA. The one was the coarse WC-6.5Co structure. The other was the melted SHA with surrounding the WC-6.5Co structure. The hardness of WC-6.5Co was 1210HV. The hardness of SHA was 640HV. In comparison by wear rate, the cladding layer showed the remarkable wear performance that was 15 times of SM490 and about 62% of D2.

• Proceedings of the KIPE Conference
• /
• 1997.07a
• /
• pp.40-44
• /
• 1997

Along with the rapid growth in microelectronics and power electronics technologies, various advanced control methods have been successfully implemented in real time and shown to be useful in controlling CO2 arc welding systems with high dynamic performance. In this paper, the slope of welding currents is controlled not to be so high in the case of short circuit welding mode. This results in less spatter. In addition, the data-base is constructed for the optimal welding conditions.