Welding Process Variables Research Articles

Tensile strength prediction in monel 400 weldments using classification and regression algorithms in machine learning

Abstract Selecting the most effective welding settings impacts mechanical strength and weld quality, with parameters like current, voltage, and speed playing pivotal roles. The mechanical part encompasses material properties, welding process variables, and structural integrity, all contributing to the overall weld quality and strength. By integrating these mechanical factors with predictive modelling, a comprehensive understanding of weld performance can be achieved, enabling optimized welding settings and enhanced weld quality assurance. This study assesses and compares machine learning algorithms such as a random tree, random forest, and C4.5 to determine their predictive capability regarding the tensile strength in Monel 400 Weldments. By utilizing a dataset comprising 32 instances with attributes like Current, Voltage, and Speed, models were developed and assessed using K-Fold cross-validation. Among these algorithms, the random tree models emerge as the most proficient in accurately predicting the tensile strength for Monel 400 Weldments through classification ML techniques. Similarly, regression algorithms have been deployed to assess the dataset by varying the train-test split ratio and gradient boosting, which exhibited superior performance with a higher R2 value of 0.99. Both random tree and Gradient boosting algorithms have commonly been recommended, with current being the most influential factor affecting tensile strength.

Use of Tungsten Inert Gas Welding on Mild Steel Weldment to Optimize Welding Process Variables on Electrode Melting Rate

One of the most crucial factors taken into account when evaluating the performance of Tungsten Inert Gas (TIG) welding is the Electrode Melting Rate, which shows how much of the heat deposited by the welding operation is used to generate melting. A dense weld pool forms in the field of welding when there is a good melting rate. Therefore, this paper investigates the use of tungsten inert gas welding on mild steel weldment to optimize welding process variables on electrode melting rate employing Artificial Neural Networks and Response Surface Methodology in the analysis. The ideal electrode melting rate of 4.6539 mm/s can be achieved by combining the following parameters: wire diameter of 2.55 mm, welding speed of 3.02 mm/s, and welding current of 208.22A, according to the RSM results. R values of 0.9119 were displayed by the RSM for the electrode melting rate. A regression plot of the ANN results indicates that the total R value is 0.93807. Because the Artificial Neural Network's output fits the experimental data more closely than the Response Surface Methodology's, it is chosen as the superior predictive model.

Computational modeling and virtual analysis using a moving heat source to join AZ61A and AA7075 alloys with the application of a titanium alloy interlayer

Laser beam welding (LBW) uses a concentrated laser beam to fuse materials, providing benefits such as a smaller heat-affected zone (HAZ), speed, accuracy, adaptability across multiple materials, and seamless adoption into automation processes. Achieving optimal weld quality with LBW remains difficult due to the need to select the appropriate welding process variables and proper interlayer between dissimilar materials. Due to the high cost and safety risks to operators and equipment in LBW, it is challenging to use the practical experiment. Additionally, welding materials with high thermal conductivity and lower melting temperatures, such as AZ61A and AA7075, is a considerable challenge. Previous research focused on process parameters in laser beam welding of various metals, but not enough consideration has been given to the effect of a titanium interlayer on AA7075 and AZ61A using virtual data. This study aims to fill these gaps by using simulation data to assess the effects of process parameters and the titanium interlayer during LBW of dissimilar materials. A backpropagation neural network with the gradient descent learning rule was used for optimization, and a central composite design was used to predict the optimal process parameter interaction. The result indicates the optimum equivalent strain is obtained at the values of beam radius between 4.5 to 5 mm. The maximum equivalent stress reached during welding speed is between 4 to 4.5 mm/s. The maximum residual stress was obtained at the number of segments of 160. The predicted maximum and average anticipated errors for peak temperature are 0.1655 % and 0.0210 %, while for residual stress it is computed as 0.1766 % and 0.0754 %. The Ti-interlayer in magnesium and aluminum laser welding reduces peak temperatures, allows for uniform energy distribution, minimizes localized heating, and enhances weld quality while lowering residual stress.

High geometric fidelity through closed-loop control of the weld pool size in gas metal arc welding based direct energy deposition

Arc based direct energy deposition combines the flexibility of additive manufacturing with high build rates and low investment costs. However, high geometric fidelity of manufactured components is not possible with state-of-the-art methods. Highly varying and geometry-dependent boundary conditions, e.g. heat dissipation and the interpass temperature, are quasi-random influences with a strong impact on the geometric fidelity and the manufactured microstructure. Without adjusting for these variations, process stability decreases, geometric deviations become more likely and defects accumulate from layer to layer. A high geometric fidelity of the manufactured components can therefore not be guaranteed with the state of the art. Due to the large number of influencing variables in the arc-based manufacturing process, this problem cannot be solved by the definition of simple setpoints. Closed-loop control, however, offers the opportunity to flexibly counteract any deviations that occur by adjusting the process parameters in real time. Since the manufactured part is created by solidification from the weld pool, a closed-loop control of the weld pool size is being developed. The developed controller uses the weld pool properties and the interpass temperature as feedback variables and takes into account the non-linear system behaviour as well as the process noise and the parameter uncertainties. The subordinate control of the welding power source is further used for improved process stability. To the best of our knowledge, this solution provides a level of robustness, steady-state accuracy and geometric fidelity that has not been achieved by previous approaches reported in the literature. To illustrate the performance of this closed-loop control for components with low heat dissipation, we demonstrate the fabrication of thin-walled components with high geometric accuracy for a fast 3D printing process and investigate the influence of the welding process variables on the microstructure, the evaluation of the geometric fidelity is based on EN ISO 1101.

A Study on the Optimization of Welding Parameters for Titanium Drums Using Optimization Algorithms

An electrolytic copper foil uses titanium drums, which exhibit excellent corrosion resistance and can produce thin electrodeposited copper foils. The appropriate technology for producing thin copper foils is required as electronic products become lighter, thinner, shorter, and smaller. Thus, the importance of titanium drum manufacturing technology, which affects the specifications of electrolytic copper foils, is emphasized. In this study, thermo-elastic-plastic analysis is performed to select an appropriate range of welding process parameters for titanium drums. In addition, using a range of welding process variables derived from analysis, GBO and GPS algorithms, which are optimization algorithms, are developed to derive objective and restriction functions as well as to select the optimal algorithm.

Sensitivity Analysis of Gas Tungsten Arc Welding Process Variables for Angular Distortion in Chromium Manganese Stainless Steel Using Design Thinking Approach

An approach to problem solving that is solution-based is provided by the design methodology known as Design Thinking (DT). To address complicated problems, the five stages of design thinking can be applied. This research article focuses on using the DT method, which includes empathising, defining, and coming up with ideas, to produce high-quality weld joints. The selection of welding process parameters plays a vital role in determining the quality of weld. The weld should be free from weld defects to ensure good performance. One of the major defects that affect the weld quality is angular distortion. During welding the rapid heating and cooling of the work piece results in uneven expansion and contraction in all directions. This results in the work piece getting distorted. It becomes imperative to predict distortion in the work piece so that it can be reduced by providing initial angular distortion in the negative direction. Through empathy, it has been found that the welding process parameters such as welding current (I), welding gun angle (θ), shielding gas flow rate (Q), plate length (L), and welding speed (V), significantly contribute to angular distortion of the weld joint. From the ideation process the following suggestions were arrived to predict angular distortion and identify the factor that has significant effect on angular distortion. A statistical prediction model was developed correlating the welding process parameters with angular distortion. Central Composite Rotatable Design with five factor and five levels was used to develop mathematical models. The experiments were conducted on Chromium Manganese Stainless Steel Grade AISI 202 in GTAW process. Optimization of process parameters was done using Simulated Annealing algorithm. From the sensitivity analysis it was found that the lower values of welding current, welding gun angle and higher values of welding speed, shielding gas flow rate and plate length resulted in minimum angular distortion.

Parameter Optimization of Gas Metal Arc Welding Process for Welding Dissimilar Steels

Welding is a method of joining similar and dissimilar metals through the use of coalescence. GMAW is a semi-mechanized, fully-mechanized, or automatic process that is widely used in fabrication. GMAW is expected to evolve further to allow for better arc control, bead contour control, deposition control, and higher productivity. The goal of this study is to enhance welding process variables for dissimilar steel metal joints made of duplex stainless steel (DSS) to ASTM/UNS S32205 and erosional steel CORTEN-A to ASTM A242. Such a dissimilar metal joint finds use in the transportation sector, particularly in the construction of rail cars. The square butt joint between two 2 mm-thick sheets was investigated using the gas metal arc welding (GMAW) process with CO₂ as the shielding gas and flux-cored wire of grade 309L as the filler material. The L₉ Taguchi array was used to optimize the tensile strength of the resulting weld joint, which was the desired quality characteristic. GMAW process parameters such as voltage, wire feed rate, and welding speed are optimized at three levels. Using ANOVA, the effects of each factor have been studied. It was found that the ideal set of parameters exists and that the voltage is the most crucial factor. A confirmation test was performed to validate the results, and it was accompanied by a figure and tables.

Gas Metal Arc Welding Process Variables Enhancement for Welding Significantly different Steels

The goal of this study is to enhance welding process variables for dissimilar steel metal joints made of duplex stainless steel (DSS) to ASTM/UNS S32205 and erosional steel CORTEN-A to ASTM A242. Such a dissimilar metal joint finds use in the transportation sector, particularly in the construction of rail cars. The square butt joint between two 2mm thick sheets was investigated using the gas metal arc welding (GMAW) process with CO2 as the shielding gas and flux cored wire of grade 309L as the filler material. The L9 Taguchi array was used to optimize the tensile strength of the resulting weld joint, which was the desired quality characteristic. GMAW process parameters such as voltage, wire feed rate, and welding speed are optimized at three levels. Using ANOVA, the effects of each factor have been studied. It was found that the ideal set of parameters exists, and that the voltage is the most crucial factor. A confirmation test was performed to validate the results, and it was accompanied by a figure and tables.

Effect of Process Parameters and Nugget Growth Rate on Liquid Metal Embrittlement (LME) Cracking in the Resistance Spot Welding of Zinc-Coated Steels

Although the influence of weld process variables on LME cracking was known to be significant, limited studies have been conducted on the effect of process variables with systematic approaches in the equivalent nugget growth behavior and heat input. This study aimed to identify the effect of weld process variables on LME sensitivity with the equivalent nugget diameter and underlying mechanism with induced tensile stress for cracking. Among the welds with equivalent nugget diameters in the combination of different welding current and time, higher LME sensitivity was observed with the high welding current and short welding time combination than that with the low welding current and long welding time combination for the equivalent nugget diameter. Because a high current and short time combination resulted in faster weld nugget growth than the low welding current and long welding time combination, it rapidly increased the surface temperature along with the cooling from the electrode. These combined effects induced a higher thermal gradient and thermally induced tensile stress on the weld surface, satisfying the conditions of the LME cracking. The simulation results also confirmed that the critical weld cycle time of the LME cracking (<i>t<sub>c</sub></i>), which is the cross point between the nugget growth diameter and a contact diameter of the electrode, could be different with the combination of the weld process variables with the equivalent weld nugget size. Therefore, <i>tc</i> can be applied for the sensitivity index of LME cracking of the resistance spot weldment considering complex weld variables.

Assessment of the influence of FSSW parameters on shear strength of dissimilar materials joint (AA6061/AZ31B)

Due to their distinctive qualities, ultra-lightweight alloys like AA6061 and AZ31B find use in a variety of significant applications. However, they are challenging to fusion weld due to incompatible metallurgical properties that result in significant cooling stresses and solidification defects like hot cracking and porosity. To address the problems brought on by the fusion welding process, solid state technology is employed to combine various materials. The goal of this study is to pinpoint the impacts of friction stir spot welding process variables on shear fracture stress, including rotation speed, plunge rate, dwell period, and shoulder to pin diameter ratio. At a rotational speed of 1000 rpm, a plunge rate of 16 mm/min, a dwell time of 5 min, and a tool shoulder to pin diameter ratio of 2.5, the FSSW joint encounters a greater shear fracture strain. According to the hook height, width, and initiation point, an appropriate fracture load was discovered, which improved the mechanical and metallurgical qualities of the joints.

Bead Geometry Prediction in Pulsed GMAW Welding: A Comparative Study on the Performance of Artificial Neural Network and Regression Models

Weld bead geometry is a critical factor for determining the quality of welded joints, for this the welding process input parameters play a key role. In this study, the relationships between welding process variables and the size of the weld bead produced by pulsed GMAW process were investigated by a neural network trained with Bayesian-Regulation Back Propagation algorithm and a second degree regression models. A series of experiments were carried out by applying a Box-Behnken design of experiment. The results showed that both models can predict well the bead geometry. However, the neural network model had a slightly better performance than the second-order regression model. Both models can be used for further analyses and using them may surmount or reduce the need of experimental procedures especially in thermal analysis validations of welding finite element modelling.

Comparative Study of Classification Algorithms for Quality Assessment of Resistance Spot Welding Joints From Pre- and Post-Welding Inputs

Resistance spot welding (RSW) is a widespread manufacturing process in the automotive industry. There are different approaches for assessing the quality level of RSW joints. Multi-input-single-output methods, which take as inputs either the intrinsic parameters of the welding process or ultrasonic nondestructive testing variables, are commonly used. This work demonstrates that the combined use of both types of inputs can significantly improve the already competitive approach based exclusively on ultrasonic analyses. The use of stacking of tree ensemble models as classifiers dominates the classification results in terms of accuracy, F-measure and area under the receiver operating characteristic curve metrics. Through variable importance analyses, the results show that although the welding process parameters are less relevant than the ultrasonic testing variables, some of the former provide marginal information not fully captured by the latter.

Characterization of friction stir welded AA 3003-H24 aluminum alloy plates

AA 3003-H24 aluminum alloy plates were butt-welded in order to investigate the effect of friction stir welding process variables on the structural properties of the welded joints. The welded joints were characterized using macro-structural investigations; and tunnel-type defects with varied sizes were detected to occur. At a welding speed of 50 mm/min, tunnel-type defects with large size were found to occur in joints welded with the tool rotational speed of 500 and 1000 rpm. The tunnel-type defects were detected to occur in welded joints produced with the process parameters of 80 mm/min welding speed and 500 and 800 rpm tool rotational speed. However, cavity-type defects were observed to occur at both welding speeds. Even, defects were found to occur in the welded joints, all welded joints were detected to fracture between the base metal and the heat-affected zone, except for the joints welded under the process parameters of 50 mm/min welding speed, 500 and 1000 rpm tool rotational speed. The highest ultimate tensile strength among all the welded joints was measured to be 128 MPa produced under the process parameters of 50 mm/min welding speed and 800 rpm tool rotational speed. It has been revealed that there is a good correlation between the size of the defects and the tensile properties of welded joints. An examination on the fracture surface of the welded joints revealed that welded joints were fractured in ductile manner except the joint produced under the process parameters of 50 mm/min welding speed and 500 rpm tool rotational speed.

Optimization of tensile strength for heat treated micro-alloyed steel weldment

Welding and post weld heat treatment process variables play important roles in determining the quality of welds. Thus, to produce welded joints of desired microstructure with the requisite mechanical properties for optimal performance in service, the need for the analysis of the process variables requiring optimization to determine their influence on the response (output) is very vital. In this study, the optimal design approach was used to optimize the main influencing process variables of welding current, tempering temperature and holding time to determine their impact on the observable response (tensile strength). Through multiple regression analysis of the experimental data, the predicted response was expressed by the second-order polynomial equation in terms of coded values. The derived model was statistically analyzed to determine its significance and predictive capacity. The ANOVA results of the quadratic regression model used to fit the response showed that it is significant (P < 0.00001). The high coefficient of regression and adjusted regression coefficient values of 94.73% and 89.99% respectively, is an expression of the model degree of fitness. The model F-value of 19.99 greater than the P-value also attest to the model significant. Validation of the optimized predicted results revealed that they are in close consonant with the experimental results. This investigation has shown that the optimum values of welding current, tempering temperature and holding time for achieving optimal tensile strength of 258.141KN/m2 in the heat treated micro-alloyed steel weldment were 90.530 amp, 250.002 °C and 60.000 min respectively.

Experimental assessment of FSW process to join AA6061/Rutile composite and parametric optimization using TGRA

Present study is focused on investigating the effect of various friction stir welding (FSW) process variables on AA6061/Rutile composites welding quality. FSW of composites was performed considering tool geometry (Tg), welding speed (Ws) and rotational speed (Ns) as ideal parameters for multi-response optimization. Experiments were designed based on the L9 orthogonal array. Analysis of variance (ANOVA) was utilized to evaluate the effects of these welding process variables on output responses namely hardness and ultimate tensile strength (UTS). Main effects plots were drawn to found out the optimal levels of these process parameters. Multi-response optimization of the welding process has been performed using Taguchi’s grey relational analysis (TGRA). Analysis revealed that welding speed of 90 mm min−1, a tool with a square pin, and rotational speed of 1000 rpm produced an FSW joint with excellent mechanical properties. Microstructure analysis revealed that refinement in the grain structure and redistribution of reinforced particles helped in improved joint strength.

A Study on the Optimization of Welding Conditions for Titanium Drums Using GPS

The importance of the titanium drum manufacturing technology, which influences the specification of electrolytic copper foils, is being greatly emphasized, and an immediate research is required. The challenges in the current titanium drum production process are that the welding beads generated by the welding of the heat affected zone during the welding process may cause stains or discoloration during the generation of electrolytic copper foils, and hot spot defects may occur in the current density operation range. Consequently, the quality of the copper foil is significantly deteriorated. Therefore, it predicts the strain, stress, and safety rate by the heat transfer analysis of titanium drums for the electrolytic copper foil and optimizes welding process variables according to the case-by-case strain, stress, and safety rate by considering the inhibition of the residual stress.

Weld Characteristic Analysis for Weld Process Variables of Tip-Rotating Arc Welding in Butt Joint of Shipbuilding Steels

Weld Characteristic Analysis for Weld Process Variables of Tip-Rotating Arc Welding in Butt Joint of Shipbuilding Steels

Bead geometry modeling on uneven base metal surface by fuzzy systems for multi-pass welding

This paper presents a modeling method of weld bead profiles deposited on uneven base metal surfaces and its application in multi-pass welding. The robotized multi-pass tungsten inert gas welding requires precise positioning of the weld beads to avoid welding defects and achieve the desirable welding join since the weld bead shapes depend on the surface of the previously deposited beads. The proposed model consists of fuzzy systems to estimate the coefficients of the profile function. The characteristic points of the trapezoidal membership functions in the rule bases are tuned by the Bacterial Memetic Algorithm during supervised training. The fuzzy systems are structured as multiple-input-single-output systems, where the inputs are the welding process variables and the coefficients of the shape functions of the segments underlying the modeled bead; the outputs are the coefficients of the bead shape function. Each segment surface is approximated by a second-order polynomial function defined in the weld bead’s local coordinate system. The model is developed from empirical data collected from single and multi-pass welding. The performance of the proposed model is compared with a multiple linear regression model. During the experimental validation, first, the individual beads are evaluated by comparing the estimated coefficients of the profile function and other bead characteristics (bead area, width, contact angles, and position of the toe points) with the measurements, and the estimations of a multiple linear regression model. Second, the sequential placement of the weld beads is evaluated while filling a straight V-groove by comparing the estimated bead characteristics with the measurements and calculating the accumulated error of the filled groove cross-section. The results show that the proposed model provides a good estimation of the bead shapes during deposition on uneven base metal surfaces and outperforms the regression model with low error in both validation cases. Furthermore, it is experimentally validated that the derived bead characteristics provide a suitable measure to identify locations sensitive to welding defects.

Modeling and optimization of weld bead profile with varied welding stages for weathering steel A606

The profile of the welding bead changes with the welding process parameters during the gas metal arc welding (GMAW) process, the top reinforcement disappears, and the penetration becomes sunken when the excessive welding heat input is applied. However, little research work is specially planned to cope with the studying of welding bead under these circumstances. A systematic study of the relationships among the welding process variables and welding bead geometric features as well as optimization of the welding quality is presented. The influences of the welding technological parameters (voltage, welding speed, and wire feed speed) on the welding geometry were revealed, and the models correlating them were established. The features of the weld bead geometry were composed of top reinforcement width, top reinforcement height, penetration depth, bottom reinforcement width, and bottom reinforcement height. By the desirability function approach, the recommendation of suitable welding parameters to meet the contradicting demands of multiple bead geometric features is fulfilled. The microstructure in different welding regions and mechanical performances of the welding joints produced by the verification test were also studied.

Optimizing process parameters for joint strength efficiency improvement in friction stir welding of polycarbonate sheets

AbstractThe present work addresses optimization of these friction stir welding process variables to maximize joint strength efficiency of welded polycarbonate sheets by using particle swarm optimization algorithm over response surface method based regression model. Initially, parametric influence on weld quality characteristics namely weld bead profile, bead geometry with associated microstructure along with micro‐hardness deviation through the weld centerline and stress‐strain behavior of the weld have been studied in detail as per full factorial design of experiments by using three different tool pin profiles such as cylindrical, square and triangular. The center point experiment i. e. tool rotational speed of 1800 min−1 and welding speed of 20 mm/min, and square tool pin profile were found to be the optimum combination with a maximum joint strength efficiency of 60.06 %. The regression model of weld ultimate tensile strength was developed by using response surface methodology which was found to be significant. Therefore, this model was further used for parametric optimization by using both response surface methodology and intelligent particle swarm optimization approaches. A slight improvement in joint strength efficiency with better optimization capability was found by using particle swarm optimization technique as compared to response surface methodology.