Explore the vast range of titles available.

This study optimized friction stir welding (FSW) parameters for 1.6 mm thick 2024T3 aluminum alloy sheets. A 3 × 3 factorial design was employed to explore tool rotation speeds (1100 to 1300 rpm) and welding speeds (140 to 180 mm/min). Static tensile tests revealed the joints’ maximum strength at 87% relative to the base material. Hyperparameter optimization was conducted for machine learning (ML) models, including random forest and XGBoost, and multilayer perceptron artificial neural network (MLP-ANN) models, using grid search. Welding parameter optimization and extrapolation were then carried out, with final strength predictions analyzed using response surface methodology (RSM). The ML models achieved over 98% accuracy in parameter regression, demonstrating significant effectiveness in FSW process enhancement. Experimentally validated, optimized parameters resulted in an FSW joint efficiency of 93% relative to the base material. This outcome highlights the critical role of advanced analytical techniques in improving welding quality and efficiency.

Machine learning has yielded proficient controllers for welding tasks. However, these controllers have limitations in evaluating the interaction between welding process parameters and welding quality. To address these shortcomings, this article investigates the modeling of welding quality and the optimization of welding process parameters through the support vector machine and particle swarm optimization (SVM-PSO) algorithm. The SVM model is used to establish the relationship model between the welding process parameters and the welding quality, and the PSO algorithm is used to search and finally output the optimized welding process parameters. During the welding process, according to the online inspection results of welding quality and the weld geometry information, the SVM-PSO algorithm can be used to optimize the welding process parameters to reduce the occurrence of welding defects.

Currently, in pipe welding, it is nearly difficult for a human welder to weld the whole circumference of a pipe in a single uninterrupted pass using MIG welding causing inconsistencies in weld quality around the welded pipe. The aim of this study was to develop an automated orbital pipe MIG welding system and to optimize welding parameters for enhancing ultimate tensile strength and Rockwell hardness of mild steel 1020 grade pipe. Three levels of variation were applied to the four input parameters that were chosen. Nine experiments were carried out using orthogonal array of L9. In this experimental investigation, the highest ultimate tensile strength (UTS) of 411.2 MPa and Rockwell hardness (RH) of 95 HRB were achieved at 110 A of current, 24 V of voltage, welding gun travel speed of 30 cm/min, and 3 mm of arc length. For modeling the orbital pipe MIG welding process experimental input parameters and response results, a hybrid artificial neural network and genetic algorithm (ANN-GA) model was constructed. This model was used to forecast and optimize UTS and RH, as well as the process factors that go with it. The results indicated that the ANN-GA model could predict the output responses with a mean square error of 5.06e-05. During optimization, a 4–9-2 network trained with neural network of back propagation by Bayesian regularization approach was determined to have the greatest prediction capability, with maximum UTS and RH of 417.857 MPa and 96.5364 HRB, respectively. From the confirmation tests, the average results of 412.7 MPa of UTS and 95 HRB of HR were obtained. The percentage of errors between the ANN-GA predicted optimal responses’ results and the confirmatory experimental results were found 1.23% and 1.59% for UTS and RH, respectively.

Due to gravity, a change in the welding position will significantly affect the flow of the molten pool, thus affecting the weld bead shape. An all-position welding process of low-power pulsed laser-MAG (metal active gas) hybrid welding was proposed to improve the welding efficiency and quality of all-position welding. This paper used the response surface method (RSM) to develop the weld bead geometry mathematical model. The analysis of variance confirmed the significance and accuracy of the model. The results show that the models can accurately predict the weld geometry, percentage errors for any models are less than 8.1%. Then, the effects of welding parameters and welding position on weld width, weld reinforcement, and weld penetration were analyzed. Finally, the optimal welding parameters at five positions of 0°, 45°, 90°, 135°, and 180° were obtained by numerical optimization with RSM. The study results can provide a reference for applying laser-MAG hybrid welding in all-position welding.

In multi-pass welding processes, achieving a uniform and smooth weld surface is crucial for mechanical performance and dimensional accuracy. However, the complex nonlinear relationships between welding parameters and weld bead geometry present significant challenges for traditional optimization methods. This study proposes an intelligent prediction and optimization framework that integrates a backpropagation (BP) neural network with an improved hill-climbing algorithm to enhance weld surface smoothness in automated multi-bead overlay welding. Experimental data collected under varying arc voltages, wire feed rates, and welding speeds were used to train the neural network. The improved hill-climbing algorithm adaptively adjusts weights and biases in the BP model to overcome issues of local minima and slow convergence. Comparative results demonstrate that the proposed method significantly outperforms conventional BP approaches in terms of prediction accuracy and convergence efficiency. Furthermore, optimal welding parameters identified by the model yield smoother weld surfaces, reducing the need for post-processing. This work provides a novel solution for intelligent control and real-time optimization in advanced welding systems.

The influence of welding parameters on temperature distribution during plunging and dwelling phase of friction stir welding (FSW) 2219 aluminum alloy thick plate has not been studied. Improper selection of welding parameters will result in uneven temperature distribution along with the thickness of the weldment, leading to welding defects and ultimately affecting the mechanical properties of the weldment. To achieve the prediction of temperature distribution and the optimization of welding parameters, a simulation process model of FSW 18-mm-thick 2219 aluminum alloy is established based on DEFORM. The validity of the simulation is verified by experiments. With the minimum temperature difference in the core area of the weldment as the target value and weldable temperature range of 2219 aluminum alloy as the constraint conditions, orthogonal experiments are conducted considering the rotational speed, the press amount, the tool tilt angle, the plunging traverse speed and the dwelling time. The results of variance analysis show that the rotational speed and the dwelling time are significant factors affecting the temperature field during the plunging and dwelling phase. Through single factor simulation, the welding parameters during the plunging and dwelling phase are optimized. This study guides the selection of welding parameters of the FSW 2219 aluminum alloy thick plate.

In order to withstand the competitive nature of the industrial market and maintain the longevity of products, researchers try to enhance current technologies and create cost-effective solutions. Aside from acquiring new machinery, it also involves successfully managing actual process variables. To get the desired and financially advantageous results, it is necessary to measure, control, and optimize these process variables. The welding process is significantly influenced by its characteristics, which play a major role in assessing the weld quality and reducing the welding time while ensuring the elimination of defects. This study provides a comprehensive overview of the research findings, developments, and remarkable techniques. First, the effective old-trade techniques applied for welding optimization are discussed. Then, the sophisticated methods depending on AI are handled for adaptive welding control, such as ANN in tandem with GA models, ant colony optimization technique, and the NSGA-III algorithm. After that, summarize the relevant research related to building models with supportive vision sensing elements for seam tracking, monitoring the weld pool, and handling feedback control. Finally, the future research difficulties and directions toward real-time intelligent monitoring are highlighted. This review will help aspiring and ambitious researchers gain a comprehensive understanding of welding optimization for robotics applications.

In large welding structures, maintaining a uniform assembly condition and machined dimension in the pre-welding groove is challenging. The assembly condition and machined dimension of the pre-welding groove significantly impact the selection of the welding parameters. In this study, laser–arc hybrid welding is used to perform butt welding on 6 mm Q345 steel in various assembly conditions, and we propose an adaptive model of the BP neural network optimized by a genetic algorithm (GA) for laser–arc welding. By employing the GA algorithm to optimize the parameters of the neural network, the relationship between the pre-welding groove parameters and welding parameters is established. The mean square error (MSE) of the GA-BP neural network is 0.75%. It is verified via experiments that the neural network can predict the welding parameters required to process a specific welding morphology under different pre-welding grooves. This model provides technical support for the development of intelligent welding systems for large and complex components.

In this paper, a double pulse gas metal arc welding (DP-GMAW) for an AA6061-T6 aluminum alloy based on fewer basic welding parameters than the traditional DP-GMAW is proposed. This study compared the difference in pulse base currents (ΔIb) and the difference in the pulse peak currents (ΔIp) by analyzing the electrical signal and morphology properties of welded samples. The results indicated that changing ΔIp caused welding defects or even welding failure easily. The welding stability after changing ΔIb was much better than that after changing ΔIp. The individual fish-scale width of the weld joint remained unchanged when  ΔIb was at different values. In addition, the average absorbed work, tensile strength, yield strength and elongation of the weld joints obtained by different ΔIb values reached 31.1%, 60.2%, 52.9% and 37.9% of the base metal, respectively.

A study of polyvinylchloride-coated woven polyester fabric welding potential was conducted using continuous ultrasonic welding machines. The effect of cooling air, anvil wheel status, anvil wheel width, material surface contact, and welding gap on seam strength was studied. Three main welding parameters with different levels were selected based on 5 and 10 mm welding widths using old and new anvil wheels with and without cooling air. A lapped type of seam was applied under full factorial design. A microstructure was captured to examine the formation of welding joints, and seam tensile properties were determined. Comparative analysis of comparable welding parameters was analyzed for a gap against pressure and amplitude against power. The actual weld phenomenon was also analyzed based on the recorded machine parameters. The results showed that auxiliary parameters had a significant effect on seam strength. A microscopic image of a welded seam indicated that cooling air reduced the number and size of holes produced. Weld seam with controlled pressure or power provided higher seam strength than that of the controlled gap or amplitude. The actual phenomenon of welding parameters was important to evaluate weld seam quality, whereby the obtained results indicated good quality at lower power and pressure.