Search Results (52)

During the cold metal transfer plus pulse (CMT+P) welding process of medium-thick plates, problems such as incomplete penetration (IP) and burn-through (BT) are prone to occur, and weld pool morphology is important information reflecting the penetration states. In order to acquire high-quality weld pool images under complex welding conditions, such as smoke and arc light, a welding monitoring system was designed. For the purpose of predicting weld penetration states, the improved Inception-ResNet prediction model was proposed. Squeeze-and-Excitation (SE) block was added after each Inception-ResNet block to further extract key feature information from weld pool images, increasing the weight of key features beneficial for predicting the penetration states. The model has been trained, validated, and tested. The results demonstrate that the improved model has an accuracy of over 96% in predicting penetration states of aluminum alloy medium-thick plates compared to the original model. The model was applied in welding experiments and achieved an accurate prediction. Full article

Laser deep penetration welding has been widely applied in industrial fields. However, keyhole depth during the welding process significantly affects the service performance of final products. Based on the spectral signals generated in the laser welding process, this study employs a Long Short-Term Memory (LSTM) neural network to predict keyhole depth in titanium alloy welding. A coaxial plasma optical information acquisition system is established to collect spectral signals emitted from the welding plasma and analyze the relationship between keyhole depth and plasma spectral features. By analyzing the spectral signals and calculating the plasma temperature, the mapping model between the plasma temperature and keyhole depth is built. The LSTM network prediction results show that the average relative error between the predicted and actual values is 2.31%, which demonstrates that the method proposed in this study has high accuracy for predicting keyhole depth in laser deep penetration welding. Full article

Accurate prediction of weld bead geometry is critical for optimizing laser overlap welding of low-carbon galvanized steel, as it directly affects joint quality and mechanical performance. Traditional finite element method (FEM)-based models provide reliable predictions but are computationally expensive and impractical for real-time applications. This study presents an artificial neural network (ANN)-based predictive model trained on a combination of experimental data and validated FEM simulations to estimate key weld characteristics, including depth of penetration (DOP), weld bead width at the surface (WS), and weld bead width at the interface (WI). The ANN model was evaluated using various improved statistical metrics. Results demonstrated a strong correlation between ANN predictions and experimental measurements, with R² values exceeding 95% for WS and DOP and 92% for WI, and mean errors below 7%. A comparative analysis between ANN, FEM, and experimental data confirmed the model’s reliability across different welding conditions. Additionally, ANN significantly reduced computational time compared to FEM while maintaining high accuracy, making it a practical tool for real-time process optimization. These findings highlight the potential of ANN models as efficient alternatives to conventional simulation techniques in laser overlap welding applications. Future improvements may involve integrating real-time sensor data and deep learning techniques to further enhance predictive performance. Full article

One of the prospective methods of robotic welding with a consumable electrode in shield gas metal arc welding is the GMAW Rapid HF process (GRHF, HF-high frequency), in which welded joints with deep penetration welds are obtained thanks to the specially programmed welding characteristics of the arc. A pulsed frequency equalized to 5000 Hz was used to achieve consumable electrode arc stabilization and improve penetration. This work consists of two main sections, including the research and analysis of wire electrode melting and weld pool formation in the innovative GRHF process and its influences on joint strength and the economic advantages of welding. As a result of our research and strength tests, as well as an image analysis of phenomena occurring in the welding arc and weld pool, assumptions were developed about the use of the GRHF process, which is characterized by deep penetration welds without welding imperfections that reduce the quality of the welded joints and their strength. Welding conditions and parameters leading to welded joints characterized by high relative strength related to the weight of the used filler material were proposed. As a result of our research, it was found that the use of welding processes with deep penetration leads to material savings related to the reduced consumption of filler materials while maintaining the required high strength of welded joints. Savings of filler materials reaching 80% were achieved compared with hitherto used methods. At the same time, the maximum load-carrying capacity of welding joints was maintained. Full article

In this study, a new deep-penetration variable-polarity tungsten inert gas (DP-VPTIG) welding process, which is performed by a triple-frequency-modulated pulse, was employed in the welding fabrication of 8 mm AA7075 aluminum plates. The electric signal, arc shape, and weld pool morphology of the welding process were obtained by means of high-speed photography and an electric signal acquisition system under varying parameters of the intermediate frequency (IF) pulse current. The principle of the arc characteristics and the dynamic mechanism of the weld melting during the process are explained. In addition, the macroforming, microstructure, and microhardness of the welded joints were investigated. The results indicate that, with an intermediate frequency pulse of 750 Hz, the arc displayed a higher energy density and a more effective arc contraction, which improved weld appearance and penetration. Moreover, the impact and stirring action of the arc refined the microstructure grains of the weld center. Therefore, this new welding method is feasible for welding medium-thickness aluminum alloy plates without a groove. Full article

This study investigates the effects of a back plate preheating assistance system and deep rolling (DR) on axial force and tunnel defects during friction stir welding (FSW). Different preheating configurations—advancing side (AS), retreating side (RS), and both sides—were examined to evaluate their impact on axial force reduction, temperature distribution, and defect minimization. Axial force measurements were taken using a dynamometer, and temperature histories were recorded with a thermal camera. The results demonstrate that a preheating temperature of 200 °C is optimal, reducing axial force by 30.24% and enhancing material flow. This temperature also facilitated deeper tool penetration, especially when preheating was applied to both sides. Preheating on the AS resulted in the smallest tunnel defects, reducing defect size by 80.15% on the RS and 96.91% on the AS compared to the non-preheated condition. While DR further reduced tunnel defects, its effectiveness was limited by the proximity of defects to the surface. These findings offer significant insights for improving the FSW process. Full article

Vision-based laser penetration control has become an important research area in the field of welding quality control. Due to the complexity and large number of parameters in the monitoring model, control of the welding process based on deep learning and the reliance on long-term information for penetration identification are challenges. In this study, a penetration recognition method based on a two-stage temporal convolutional network is proposed to realize the online process control of laser welding. In this paper, a coaxial vision welding monitoring system is built. A lightweight segmentation model, based on channel pruning, is proposed to extract the key features of the molten pool and the keyhole from the clear molten pool keyhole image. Using these molten pool and keyhole features, a temporal convolutional network based on attention mechanism is established. The recognition method can effectively predict the laser welding penetration state, which depends on long-term information. In addition, the penetration identification experiment and closed-loop control experiment of unequal thickness plates are designed. The proposed method in this study has an accuracy of 98.96% and an average inference speed of 20.4 ms. The experimental results demonstrate that the proposed method exhibits significant performance in recognizing the penetration state from long sequences of welding image signals, adjusting welding power, and stabilizing welding quality. Full article

Keyhole tungsten inert gas (keyhole TIG) welding is renowned for its advanced efficiency, necessitating a real-time defect detection method that integrates deep learning and enhanced vision techniques. This study employs a multi-layer deep neural network trained on an extensive welding image dataset. Neural networks can capture complex nonlinear relationships through multi-layer transformations without manual feature selection. Conversely, the nonlinear modeling ability of support vector machines (SVM) is limited by manually selected kernel functions and parameters, resulting in poor performance for recognizing burn-through and good welds images. SVMs handle only lower-level features such as porosity and excel only in detecting simple edges and shapes. However, neural networks excel in processing deep feature maps of “molten pools” and can encode deep defects that are often confused in keyhole TIG. Applying a four-class classification task to weld pool images, the neural network adeptly distinguishes various weld states, including good welds, burn-through, partial penetration, and undercut. Experimental results demonstrate high accuracy and real-time performance. A comprehensive dataset, prepared through meticulous preprocessing and augmentation, ensures reliable results. This method provides an effective solution for quality control and defect prevention in keyhole TIG welding process. Full article

Surface tension is an important characteristic of materials. In particular at high temperatures, surface tension values are often unknown. However, for metals, these values are highly relevant in order to enable efficient industrial processing or simulation of material behavior. Plasma, electron or laser beam processes can induce such high energy inputs, which increase the metal temperatures to, and even above, boiling temperatures, e.g., during deep penetration welding or remote cutting. Unfortunately, both theoretical and experimental methods experience challenges in deriving surface tension values at high temperatures. Material models of metals have limitations in explaining complex ion interactions, and experimentally measuring temperature and surface tension at high temperatures is a challenge for methods and equipment. Therefore, surface wave analysis was conducted in this work to derive surface tension values around the boiling temperature of steel and identify trends. In addition, a simple ion interaction calculation was used to simulate the impacting parameters that define the surface tension. Since both the experimental values and simulation results indicate an increasing trend in surface tension above the boiling temperature, it is concluded that the dominating attractive forces above this temperature should increase with increasing temperature and lead to increasing surface tension forces in the surface layers of liquid metal. Full article

The Keyhole Plasma Arc Welding (KPAW) process utilizes arc plasma highly constricted by a water-cooled cupper nozzle to produce great arc pressure for opening a keyhole in the weld pool, achieving full penetration to the thick plate. However, advanced control of welding is known to still be difficult due to the complexity of the process mechanism, in which thermal and dynamic interactions among the arc, keyhole, and weld pool are critically important. In KPAW, two large eddies are generally formed in the weld pool behind the keyhole by plasma shear force as the dominant driving force. These govern the heat transport process in the weld pool and have a strong influence on the weld pool formation process. The weld pool flow velocity is much faster than those of other welding processes such as Tungsten Inert Gas (TIG) welding and Gas Metal Arc (GMA) welding, enhancing the heat transport to lower the weld pool surface temperature. Since the strength and direction of this shear force strongly depend on the keyhole shape, it is possible to control the weld pool formation process by changing the keyhole shape by adjusting the torch design and operating parameters. If the lower eddy is relatively stronger, the heat transport to the bottom side increases and the penetration increases. However, burn-through is more likely to occur, and heat transport to the top side decreases, causing undercut. In order to realize further sophistication of KPAW, a deep theoretical understanding of the process mechanism is essential. In this article, the recent progress in studies regarding the interaction mechanism of arc, keyhole, and weld pool in KPAW is reviewed. Full article

For the welding process of thick-walled structural components in liquid rocket engines, the activated-flux TIG method can effectively address issues such as the formation of intermetallic phases in the weld seams, thereby enhancing mechanical performance. The present study investigates the activated-flux TIG welding technique on 10mm thick 1Cr21Ni5Ti duplex stainless steel plates. Various activated-flux, including -SiO₂, TiO₂, V₂O₅, NiO, MnO₂, CaO, AlCl₃, CaF₂, B₂O₃ Cr₂O₃, and Al₂O₃, were examined to understand their impact on the weld-bead geometry. The aim was to determine the optimal activator ratio for the effective welding of 1Cr21Ni5Ti duplex stainless steel. The weld-shift experiment confirmed that the deep penetration observed in flux-assisted welding is attributed to Marangoni convection in the molten pool. Comprehensive evaluations and analyses were performed on the microstructure and mechanical properties of the normal welded joint and the A-TIG welded joint. Finally, the study delves into a discussion on the factors influencing changes in the weld penetration, microstructure, and mechanical properties of the weld. Full article

This paper investigated evolutions of α-Al sub-grains’ morphology and crystalline orientation in the fusion zone during laser welding of 2A12 aluminum alloys. Based on this, a new method for assessing the weldability of materials was proposed. In laser deep-penetration welding, in addition to the conventional columnar and equiaxed dendrites, there also exhibited a corrugated structure with several ‘fine-coarse-fine’ transformations. In such regions, an abnormal α-Al coarsening phenomenon was encountered, with a more dispersed crystalline orientation arrangement and a decreased maximum pole density value. Particularly, structural alterations appeared more frequently in the weld bottom than the top. The above results indicated that the laser-induced keyhole presented a continually fluctuating state. Under such a condition, the solid–liquid transformation exhibited an unstable solidification front, a fluctuant undercooling, and a variational solidification rate. Meanwhile, the welding quality of this material is in a critical state to generate pores. Therefore, the appearance and relevant number of corrugated regions can be considered as a new way for judging the weldability, which will help to narrow the processing window with better welding stability. Full article

Background. Spatter formation at melt pool swellings at the keyhole rear wall is a major issue for laser deep penetration welding at speeds beyond 8 m/min. A gas nozzle directed towards the keyhole, that supplies shielding gas locally, is advantageous in reducing spatter formation due to its simple utilization. However, the relationship between local gas flow, laser spot size, and the resulting effects on spatter formation at high welding speeds up to 16 m/min are not yet fully understood. Methods. The high-alloy steel AISI 304 (1.4301/X5CrNi18-10) was welded with laser spot sizes of 300 μm and 600 μm while using a specially designed gas nozzle directed to the keyhole. Constant welding depth was ensured by Optical Coherence Tomography (OCT). Spatter formation was evaluated by precision weighing of samples. Subsequent processing of high-speed images was used to evaluate spatter quantity, size, and velocity. The keyhole oscillation was determined by Fast Fourier Transform (FFT) analysis. Tracking the formation of melt pool swellings at the keyhole rear wall provided information on the upward melt flow velocity. Results. The local gas flow enabled a significant reduction in the number of spatters and loss of mass for both laser spot sizes and indicated an effect on surface tension by shielding the processing zone from the ambient atmosphere. The laser spot size affected the upward melt flow velocity and spatter velocity. Full article

The development of robust and efficient methods for constructing and joining complex metal specimens with high bonding quality and durability is of paramount importance for various industries, e.g., aerospace, deep space, and automobiles. This study investigated the fabrication and characterization of two types of multilayered specimens prepared by tungsten inert gas (TIG) welding: Ti–6Al–4V/V/Cu/Monel400/17-4PH (Specimen 1) and Ti–6Al–4V/Nb/Ni–Ti/Ni–Cr/17-4PH (Specimen 2). The specimens were fabricated by depositing individual layers of each material onto a Ti–6Al–4V base plate, and subsequently welding them to the 17-4PH steel. The specimens exhibited an effective internal bonding without any cracks, accompanied by a high tensile strength, with Specimen 1 exhibiting a significantly higher tensile strength than Specimen 2. However, the substantial interlayer penetration of Fe and Ni in the Cu and Monel layers of Specimen 1 and the diffusion of Ti along the Nb and Ni–Ti layers in Specimen 2 resulted in a nonuniform elemental distribution, raising concerns about the lamination quality. This study successfully achieved elemental separation of Fe/Ti and V/Fe, which is vital for preventing the formation of detrimental intermetallic compounds, particularly in the fabrication of complex multilayered specimens, representing the prime novelty of this work. Our study highlights the potential of TIG welding for the fabrication of complex specimens with high bonding quality and durability. Full article

Deep learning technology has advanced rapidly and has started to be applied for the detection of welding defects. In the manufacturing process of power batteries for new energy vehicles, welding defects may occur due to the high directivity, convergence, and penetration of the laser beam. The accuracy of deep learning prediction relies heavily on big data, but balanced big data of welding defects is hard to acquire at the battery production site. In this paper, the authors construct a dataset named RIAM, which consists of images captured from an industrial environment for laser welding of power battery modules. RIAM contains four types of images: Normality, Lack of fusion, Surface porosity, and Scaled surface. The characteristics of RIAM are carefully considered in the application scenarios. Moreover, this paper proposes a gradient-based unsupervised model named Grad-MobileNet, which can be trained with only a few normal images and can extract the feature gradients of the input images. Welding defects can then be classified by the gradient distribution. This model is based on MobileNetV3, which is a lightweight convolutional neural network (CNN), and achieves 99% accuracy, which is higher than the accuracy expected from supervised learning. Full article