Weld Bead Research Articles

AI-driven autonomous adaptative feedback welding machine

Abstract The gas tungsten arc welding (GTAW) is a primary method for nuclear component fabrication and repair. Recent advancements in monitoring and automation technologies have made the shift toward fully automated arc welding more feasible, reducing the necessity for continuous human oversight. Two artificial intelligence-based networks were developed that utilize sensor-based feedback on a mechanized GTAW head. We present an image-based semantic segmentation convolutional neural network that identifies crucial features such as the weld pool, groove, wire, and electrode based on which geometric measurements are derived. A separate novel neural network predicts the weld bead geometry for multi-pass welds and inconsistent groove geometries. The application of both neural networks is a pre-requisite that enables the autonomous planning and execution of multi-pass welds to fill a groove.

TIG welding process on IS 2062A steel of 5 mm plate, utilizing a 2.5 mm diameter tungsten solid wire as electrode along with direct current straight polarity and argon inert gas was employed for shielding purpose

The quality as well as efficient welding is crucial to fulfil the consumer satisfaction and getting returns from production, which is mostly depends on weld bead properties for any welding process, which is influence by the selected welding method and its process variables. So, the significant efforts are to choose the appropriate welding process in addition the process parameters as well as their level. In an atmosphere of welding different technique have been developed in last few decades, the demand of Gas Tungsten arc welding (GTAW) or Tungsten inert gas welding (TIG) has been increasing day by day owing to it has potential to fabricate multiple metallic materials (similar/dissimilar), quality joint, smooth modification for industrialization, higher efficiency, and low capital cost. However, published literature regarding research on TIG welding of IS 2062A steel is notably scarce. Detailed discussions on the optimization techniques exploring the impact of process parameters such as welding current, traversing speed, and gas flow rate on both weld quality and bead geometry in TIG welding of mild steel are conspicuously absent in prior works. So it is very crucial for quality joint to applied process optimization on TIG Welding parameters. The study focused on tungsten inert gas welding process on 5 mm thick plate of IS 2062A steel, utilizing a 2.5 mm diameter tungsten solid wire as electrode along with direct current straight polarity and argon inert gas was employed for shielding purpose. To streamline experimentation, a multi-response optimization technique was employed, using Taguchi's L16 experimental design method. Among several welding parameters, the significant parameters like current (I), traversing speed (S), and gas flow rate (Gf) were considered, others parameters were kept constant. The study measured various aspects of bead properties, including penetration, bead width, and depth of HAZ, along with HAZ hardness. The optimized parameter settings, derived from the signal-to-noise (S/N) ratio, has been validated as improved the weldment properties along with possess highest grey relation grade, which highlighting the effectiveness of the Grey-based Taguchi method in enhancing joints properties as product quality together with efficiency in manufacturing. Quantitative assessment via the analysis of variance method was conducted to determine the relative significance of each variable on the overall output characteristics of the weldment.

A Study on the Effects of Welding Parameters on Weld Bead Geometry in TIG Welding Process of Zircaloy Fuel Pins Using Response Surface Methodology

This paper investigates influences of welding parameters on weld bead geometry in the tungsten inert gas welding process of Zircaloy-2. Initially, a “Definitive screening design” was employed for identifying the key factors affecting weld bead geometry. Subsequently, response surface methodology was utilized to generate an experimental matrix, and experiments were conducted to analyze the effects of each welding parameter on weld bead geometry. Mathematical models were developed using analysis of variance for two-weld bead geometrical parameters, and their validity was assessed by comparing experimentally obtained values with those predicted by the model. Finally, a dimensionless parameter, the aspect ratio, indicative of the weld quality, was optimized.

The control of fully equiaxed microstructure in laser welding Al-mg-Er-Zr alloy

The Al-Mg-Er-Zr alloy with higher strength and thermal stability was focused on as promising candidate in shipbuilding field. However, when this material was joined and manufactured with high-efficiency laser welding technology, the unmelted strengthening Al3(Er,Zr) particles segregated in weld bead and formed the discontinuous fine equiaxed and column grain zone simultaneously which decreased the joint strength. In order to solve the segregation behavior of precipitates and obtain the fully equiaxed microstructure of weld seam, the transverse scanning adjustable-ring-mode laser technology was employed. The stirring effect in the molten pool pushed the unmolten Al3(Er,Zr) dispersoids from the fusion line to the weld center. At the same time, the temperature distribution of weld seam was more homogeneous as inhibited the growth of column grain. Finally, the homogeneously distributed Al3(Er,Zr) particles as well as higher supercooling degree in the molten pool refined the microstructure. The optimal weld joint was obtained, which displayed remarkable mechanical performance with tensile strength of 389 ± 1 MPa, up to 93.3 % of base metal.

A predictive model of weld bead cross-section morphology during laser deep penetration welding considering energy coupling law in keyhole

A predictive model of weld bead cross-section morphology during laser deep penetration welding considering energy coupling law in keyhole

Selection of the Process of Arc Welding of Sealing Surfaces of Power Valves with a Consumable Electrode in the Shielding Gas

Introduction. One of the main requirements to the methods of weld overlay of sealing surfaces of power valve trim parts is to obtain a high-quality wear-resistant pad with minimal penetration and optimal process performance. Currently, arc, electroslag, plasma, beam, induction and other surfacing techniques have been developed and introduced into production. However, the influence of various arc welding processes with a consumable electrode in shielding gas on the geometric parameters of weld beads and metal hardness of sealing surfaces is understudied. The presented research is intended to fill this gap. The objective of its authors is to select such a process of arc welding of beads on parts of the power valve trim with a consumable electrode in shielding gases, which would provide the best workability of the deposited metal.Materials and Methods. Arc surfacing with a consumable electrode in a mixture of gases was performed on steel plates. The welding torch was moved in a straight line, without transverse oscillations, using the FRC-9 mechanism (Fronius). A microprocessor-controlled inverter-type digital current source TransPulsSynergic 3200 CMT (Fronius) was used as the power supply. The following welding processes were analyzed: MIG/MAG process with self-regulation (Standard mode), synergic process of MIG/MAG method (Synergic mode), short arc process with mechanical separation of electrode metal droplets (CMT-ColdMetalTransfer), and synergic pulse-arc process (PulseSynergic). The short-cut process of bead surfacing was evaluated by the stability of the values of the energy parameters of the bead surfacing mode in time at the same electrode wire feed rates, which were recorded by oscilloscopes, as well as by comparing the geometric characteristics of the deposited beads and the hardness of the deposited metal.Results. The analysis of experimental data of the geometrics of the weld beads and their complex dimensional characteristics made it possible to establish that the welding engineering requirements for the welded beads are most fully met by long-arc surfacing by the PulseSynergic pulse-arc process.Discussion and Conclusion. The study and the resulting data make a certain contribution to solving the problem of the influence of arc welding processes on the parameters of weld beads and on the hardness of the metal of sealing surfaces. A detailed analysis of the modes of arc surfacing of beads with a consumable electrode in shielding gases on the trim parts of power valves can be used in further research on this topic. The conclusions of the authors will not only provide considerable theoretical assistance to scientists, but will also make adjustments to the activities of practitioners.

Optimizing Process Parameters for ASTM A36 Steel Welding with a Locally Manufactured Arc Welding Machine

In many different industries, welding is a common joining technique. However, due to a lack of finance, tiny fabrication businesses in Nigeria frequently use simple manual arc welding equipment. Although these systems enable necessary joining activities, their erratic performance over time degrades output and quality. Welds are unreliable and may need to be redone if the process parameters are not systematically understood. This also restricts the thickness of materials that may be employed. Through experiment design, this study sought to optimize the characteristics of a manually operated shielded metal arc welding (SMAW) machine. Current, voltage, electrode diameter, and travel speed were found to be important adjustable parameters. To examine how changes in these variables affect the results of weld quality, an experimental design was created. The manual SMAW machine's ideal parameters were determined to be 46.498 amps of current, 28.662 volts of voltage, 2.920 mm of electrode diameter, and 100 mm/min of travel speed. The anticipated tensile shear strength at these levels was 502.362 MPa, the micro hardness was 437.736 kgf/mm2, and the weld bead width was 6.124 mm. When compared to the machine's initial capabilities, performance under optimal conditions demonstrated increases in productivity, dependability, and defect reduction. To assist Nigeria's industrialization objectives, local technical skills can be sustainably developed through the methodical improvement of current resources.

Efficient weld bead recognition for robotic grinding using laser vision and machine learning

Efficient weld bead recognition for robotic grinding using laser vision and machine learning

Multiobjective optimization of welding process variables in RMD and FCAW techniques using a heat transfer search algorithm for 316LN stainless steel

This study aims to identify the optimal parameters for regulated metal deposition (RMD) and flux-cored arc welding (FCAW) processes when joining 316LN stainless steel. The objective was to determine the optimal settings for current (A), voltage (V), and gas flow rate (GFR, L/min) to achieve the desired weld bead characteristics, including bead width (BW), bead height (BH), depth of penetration (DOP), and heat-affected zone (HAZ). A Box–Behnken design based on response surface methodology was employed for the bead-on-plate trials. Mathematical models were developed from the experimental data and validated through analysis of variance and residual analysis, with R-squared values confirming model accuracy. The heat transfer search (HTS) algorithm was used for both single objective and multiobjective optimization. For RMD, optimal results were achieved with a BW of 9.95 mm, BH of 4.39 mm, DOP of 2.26 mm, and HAZ of 0.29 mm, at 130 A, 18 V, and 20 L/min GFR. For FCAW, optimal values were a BW of 11.45 mm, BH of 3.59 mm, DOP of 2.15 mm, and HAZ of 0.40 mm, at 210 A, 24 V, and 10 L/min GFR. The Pareto solutions offered a most suitable choice of the optimal configuration, balancing the desired BW, BH, DOP, and HAZ values. The effectiveness of the HTS algorithm is demonstrated by the minimal differences between predicted and measured values, highlighting its high accuracy in optimizing 316LN stainless steel welding parameters.

Influence of shielding gas flow rate on residual stresses in GMAW weld beads using LCR waves

Influence of shielding gas flow rate on residual stresses in GMAW weld beads using LCR waves

Comparative Analysis of the Effects of Additives of Nanostructured Functional Ceramics on the Properties of Welding Electrodes

The synthesis of special photocatalysts of nanostructured functional ceramics (PNFC) under the ZKHM brand under the influence of concentrated solar radiation showed the effectiveness of these ceramic materials in multifunctional use, in particular as additives for coatings of welding electrodes. However, problems with producing these materials in solar ovens on an industrial scale did not allow the widespread use of this method. This problem was solved using the technique of PNFC synthesis, followed by activation by pulsed radiation generated by functional ceramics. The ceramic material obtained by this method under the brand name ZB-1 also showed its effectiveness when used as an additive in welding electrode coatings. A comparative analysis of the effectiveness of the actions of additives from the ZKHM and ZB-1 brands on the welding and technological properties of welding electrodes from the MR-3 brand was carried out. Comparative results for the formation of weld beads showed that beads with high-quality formation without external defects were achieved when surfaced with electrodes with additives from both brands at concentrations up to 1%. Also, at concentrations up to 1%, these additives increased the breaking length of the arc and the stability of arc welding. The different effects of these additives were observed in a comparative analysis of their impacts on the size of the visor at the end of the electrode, the coefficients of melting and surfacing, and the loss factor for fumes and splashing of electrode metal.

Comparative Analysis of Shielded Metal Arc Welding (SMAW) Beads in Dry and Wet Environments

Shielded Metal Arc Welding (SMAW) is a versatile and reliable welding process widely used across various industries. The environment in which SMAW is performed can significantly impact the characteristics of the weld bead, influencing factors such as bead appearance, penetration depth, and weld integrity. This paper presents a comparative analysis of SMAW weld beads produced in dry and wet environments, specifically underwater conditions. The study reveals that welds made underwater exhibit greater penetration due to the shorter arc length required to maintain stability, with a measured penetration depth of 1.44 mm compared to 2.05 mm for dry welds. Additionally, underwater welds demonstrate a higher convexity (2.28 mm) and narrower width (6.72 mm) compared to dry welds (1.67 mm convexity and 10.75 mm width). The increased hardness observed in underwater welds (88 HRB versus 74 HRB for dry welds) is attributed to the rapid cooling effect of the water, which acts as a quenching medium. Both dry and wet welds show no signs of porosity, indicating that underwater welding can produce structurally sound and dense welds in shallow water using conventional welding machines and electrodes designed for dry environments. Understanding these differences is essential for optimizing welding processes and ensuring weld quality in varying environmental conditions.

A deep learning-based model for defect reorganisation in welding/wire arc additive manufacturing

Welding and Wire Arc Additive Manufacturing (WAAM) are crucial processes in various industries, but defects can significantly impact the quality and integrity of the final product. The study proposes a deep learning-based model for automated defect recognition in WAAM. The primary objective is to develop a robust and accurate system that can identify welding defects using Convolutional Neural Networks (CNN), a deep learning model. The research methodology involves inputting weld bead images into the model, which is then trained to recognise different defects. During the training phase, images depicting various defects were used to train the DL model, enabling it to learn the distinctive features and patterns associated with each type of defect. The trained model was later tested, and it demonstrated an accuracy rate of 88% in classifying welding defects, showcasing its potential for real-time monitoring and quality control in welding/WAAM applications. The findings of this study contribute to the advancement of intelligent manufacturing systems and highlight the effectiveness of deep learning techniques in enhancing the reliability and efficiency of welding processes.

Effect of wire feed speed and arc length on weld bead geometry in synergistic controlled pulsed MIG/MAG welding

Abstract Arc welding is one of the most commonly applied methods in the welded manufacturing industry. The pulse MIG/MAG welding method (GMAW-P) was developed to prevent problems that may occur in the weld bead due to high heat input to the base metal during the feeding of the weld metal in MIG/MAG welding applications. The synergistic controlled welding machines have been developed that facilitate the selection of welding parameters and provide simultaneous feeding of pulsed welding wire by adjusting the variables to the most appropriate values relative to each other. Weld bead geometry is greatly influenced by welding process parameter, i.e., welding speed, welding current, shielding gas flow rate, voltage, arc travel speed, type of shielding gas, etc. In this study, steel welding samples in T-joint shape were produced with synergistic controlled GMAW-P. The effect of welding parameters on weld bead geometry was investigated. As a result of this study, it was determined that increases in weld wire feed speed, arc voltage, and welding current increased weld depths of penetration and weld bead thickness.

Quality of weld bead in laser metal deposition of titanium wire using pulsed laser

Quality of weld bead in laser metal deposition of titanium wire using pulsed laser

Thermal and residual stress analysis of multi-pass welded stainless steel pipes using DEFLUX and FILM subroutine

This study presents an in-depth investigation of the influence of welding parameters (welding speed and number of passes) on the residual stress distribution in AISI 304 (Z7CN18-09) austenitic stainless-steel tubes. A three-dimensional finite element modeling (FEM), developed in ABAQUS, was implemented to simulate the circumferential welding process. The DFLUX and FILM subroutines were implemented to model the double ellipsoid mobile heat source and thermal boundary conditions, respectively. Model validation was performed by comparing weld bead profiles and thermal cycles with experimental results, showing excellent correlation (deviation < 5%). The coupled thermal and mechanical analyses allowed evaluation of the spatiotemporal evolution of the temperature field for different welding speeds (80-160-240 mm/min) and the distribution of axial and circumferential residual stresses as a function of tube thickness. The numerical results demonstrate a significant influence of these parameters on the amplitude and distribution of residual stresses, with a notable reduction in maximum stresses for optimized welding speeds and better stress homogenization with multi-pass welding.

Numerical Study of the Effects of Residual Stress in Welded Pipe Joints

In general, welding processes can be understood as the establishment of the union of parts, generally metallic, using a heat source to promote the fusion of materials, with or without the presence of pressure efforts. Studies related to the distributions and levels of residual resistance arising from the thermal cycles involved in welding processes are of vital importance for evaluating and guaranteeing the integrity of welded pipes. This work proposes the implementation of a routine in PYTHON language to automate the production of thermomechanical coupling welding models using the ABAQUS® CAE finite element tool, considering the heat distribution model of the welding source according to Goldak et al. (1984), better known as the double ellipsoid model. The studies are produced considering an ambient temperature of 20 °C and another with preheating of the tubes to 300 °C. The results achieved by this study are related solely to analyzes of the residual stress fields in a thin walled tube joint manufactured in AISI 304 stainless steel, welded using TIG (Tungsten Inert Gas) processes in a single pass. Thus, this study seeks to analyze the hoop and axial residual stress distributions on the internal or external walls of post-welded tubes in angular positions 0°, 90°, 180° and 270°, whether or not there is uniform preheating of the pre-welding pipes. The results show that, in general, residual stresses differ slightly with the angular position, being relatively high when compared to the yield stress of the steel, and therefore have a considerable impact on reducing the mechanical strength of the welded joint. It should also be noted that when considering the preheating of the pipes there is a significant decrease in the peak temperatures reached in the transfer process, in the cooling rates and in the residual stress levels of the joints, especially in the most critical regions, located in the proximity from the center of the weld beads.

Machine learning-based prediction of CoCrFeNiMo0.2 high-entropy alloy weld bead dimensions in wire arc additive manufacturing

Wire arc additive manufacturing (WAAM) is a promising method to fabricate large-sized components. By adjusting WAAM process parameters, dimensions of WAAM-produced weld beads can be optimized. To this end, the current study adopted the cold metal transition (CMT) process to produce different-sized beads of CoCrFeNiMo0.2 high-entropy alloy (HEA), varying WAAM parameters and linking them with the formed bead dimensions and bead-substrate contact angles. Three machine learning algorithms, namely back propagation neural network (BPNN), support vector regression (SVR), and random forest regression (RFR), were used to predict bead dimensions and contact angles under various WAAM parameters. The BPNN model has great prediction performance in the height of beads. The SVR model has the highest accuracy in predicting the width and cross-sectional area of beads. The RFR outperforms the other two models in contact angles prediction. This work not only provides a reference for the WAAM of high-entropy alloys, but also provides new ideas for predicting bead size in WAAM.

Operational Performance and Weld Bead Characteristics of Experimental Tubular-Wires for Underwater Welding

Operational Performance and Weld Bead Characteristics of Experimental Tubular-Wires for Underwater Welding

Optimization of elements transfer in low carbon steel welds during submerged arc welding

This study suggests that the optimal flux can be designed and selected for the Mn/S ratio in the weld and high penetration. Fuzzy logic optimization technique has been used for the selection of flux. The Mn/S ratio is important in the welds as the mechanical properties such as impact strength, toughness and tensile strength also depends upon the ratio of Mn/S in the welds. This ratio also affects the weld bead geometry like weld width, penetration and reinforcement. The fluxes were designed using RSM and were made by agglomeration technique. The optimized flux contains CaF2, FeMn and NiO each as 8, 2 and 2%