Search Results (423)

Accurate weld seam recognition is essential in automated welding systems, as it directly affects path planning and welding quality. With the rapid advancement of industrial vision, weld seam instance segmentation has emerged as a prominent research focus in both academia and industry. However, existing approaches still face significant challenges in boundary perception and structural representation. Due to the inherently elongated shapes, complex geometries, and blurred edges of weld seams, current segmentation models often struggle to maintain high accuracy in practical applications. To address this issue, a novel structure-aware and boundary-enhanced YOLO (SABE-YOLO) is proposed for weld seam instance segmentation. First, a Structure-Aware Fusion Module (SAFM) is designed to enhance structural feature representation through strip pooling attention and element-wise multiplicative fusion, targeting the difficulty in extracting elongated and complex features. Second, a C2f-based Boundary-Enhanced Aggregation Module (C2f-BEAM) is constructed to improve edge feature sensitivity by integrating multi-scale boundary detail extraction, feature aggregation, and attention mechanisms. Finally, the inner minimum point distance-based intersection over union (Inner-MPDIoU) is introduced to improve localization accuracy for weld seam regions. Experimental results on the self-built weld seam image dataset show that SABE-YOLO outperforms YOLOv8n-Seg by 3 percentage points in the AP(50–95) metric, reaching 46.3%. Meanwhile, it maintains a low computational cost (18.3 GFLOPs) and a small number of parameters (6.6M), while achieving an inference speed of 127 FPS, demonstrating a favorable trade-off between segmentation accuracy and computational efficiency. The proposed method provides an effective solution for high-precision visual perception of complex weld seam structures and demonstrates strong potential for industrial application. Full article

High-density polyethylene (HDPE) pipes are widely used in urban natural gas pipeline systems due to their excellent mechanical and chemical properties. However, welding joints are critical weak points in these pipelines, and defects, such as cold welding—caused by reduced temperature or/and insufficient pressure—pose significant safety risks. Traditional non-destructive testing (NDT) methods face challenges in detecting cold welding defects due to the polymer’s complex structure and characteristics. This study presents a microwave-based NDT system for detecting cold welding defects in thermal fusion welds of HDPE pipes. The system uses a focusing antenna with a resonant cavity, connected to a vector network analyzer (VNA), to measure changes in microwave parameters caused by cold welding defects in thermal fusion welds. Experiments conducted on HDPE pipes welded at different temperatures demonstrated the system’s effectiveness in identifying areas with a lack of fusion. Mechanical and microstructural analyses, including tensile tests and scanning electron microscopy (SEM), confirmed that cold welding defects lead to reduced mechanical properties and lower material density. The proposed microwave NDT method offers a sensitive, efficient approach for detecting cold welds in HDPE pipelines, enhancing pipeline integrity and safety. Full article

E36 steel, widely used in shipbuilding and offshore structures, offers moderate strength and excellent low-temperature toughness. However, its welded joints are highly susceptible to fatigue failure. Cracks typically initiate at weld toes or within the heat-affected zone (HAZ), severely limiting the fatigue life of fabricated components. Traditional life prediction methods are complex, inefficient, and lack accuracy. This study proposes a machine learning (ML) framework for efficient fatigue life prediction of E36 welded joints. Welded specimens using SQJ501 filler wire on prepared E36 steel established a dataset from 23 original fatigue test data points. The dataset was expanded via Z-parameter model fitting, with data scarcity addressed using SMOTE. Pearson correlation analysis validated data relationships. After grid-optimized training on the augmented data, models were evaluated on the original dataset. Results demonstrate that the machine learning models significantly outperformed the Z-parameter formula (R² = 0.643, MAPE = 16.15%). The artificial neural network (R² = 0.972, MAPE = 4.45%) delivered the best overall performance, while the random forest model exhibited high consistency between validation (R² = 0.888, MAPE = 6.34%) and testing sets (R² = 0.897), with its error being significantly lower than that of support vector regression. Full article

This paper presents optimization of peak temperatures achieved during friction stir welding (FSW) of Al-6061-T6 alloys. This research work employed a novel approach by investigating the effect of FSW welding process parameters on peak temperatures through the implementation of finite element analysis (FEA), the Taguchi method, analysis of variance (ANOVA), and machine learning (ML) algorithms. COMSOL 6.0 Multiphysics was used to perform FEA to predict peak temperatures, incorporating seven distinctive welding parameters: tool material, pin diameter, shoulder diameter, tool rotational speed, welding speed, axial force, and coefficient of friction. The influence of these parameters was investigated using an L32 Taguchi array and analysis of variance (ANOVA), revealing that axial force and tool rotational speed were the most significant parameters affecting peak temperatures. Some simulations showed temperatures exceeding the material’s melting point, indicating the need for improved thermal control. This was achieved by using three machine learning (ML) algorithms, i.e., Logistic Regression, k-Nearest Neighbors (k-NN), and Naive Bayes. A dataset of 324 data points was prepared using a factorial design to implement these algorithms. These algorithms predicted the welding conditions where the temperature exceeded the melting temperature of Al-6061-T6. It was found that the Logistic Regression classifier demonstrated the highest performance, achieving an accuracy of 98.14% as compared to Naive Bayes and k-NN classifiers. These findings contribute to sustainable welding practices by minimizing excessive heat generation, preserving material properties, and enhancing weld quality. Full article

Based on the engineering background of a new type of segmental-assembled steel temporary beam buttress, the fatigue strength evaluation method of the steel box girders with open longitudinal ribs was taken as the research objective. The fatigue stress calculation analysis and the full-scale fatigue loading test for the steel box girder local component were carried out. The accuracy of the finite-element model was verified by comparing it with the test results, and the rationality of the fatigue strength evaluation methods for welded joints was deeply explored. The results indicate that the maximum nominal stress occurs at the weld toe between the transverse diaphragm and the top plate at the edge of the loading area, which is the fatigue-vulnerable location for the steel box girder local components. The initial static-load stresses at each measuring point were in good agreement with the finite-element calculation results. However, the static-load stress at the measuring point in the fatigue-vulnerable position shows a certain decrease with the increase in the number of cyclic loads, while the stress at other measuring points remains basically unchanged. According to the finite-element model, the fatigue strengths obtained by the nominal stress method and the hot-spot stress method are 72.1 MPa and 93.8 MPa, respectively. It is reasonable to use the nominal stress S-N curve with a fatigue life of 2 million cycles at 70 MPa and the hot-spot stress S-N curve with a fatigue life of 2 million cycles at 90 MPa (FAT90) to evaluate the fatigue of the welded joints in steel box girders with open longitudinal ribs. According to the equivalent structural stress method, the fatigue strength corresponding to 2 million cycles is 94.1 MPa, which is slightly lower than the result corresponding to the main S-N curve but within the range of the standard deviation curve. The research results of this article can provide important guidance for the anti-fatigue design of welded joints in steel box girders with open longitudinal ribs. Full article

Aluminum alloy, due to its low melting point and high thermal conductivity, deforms and contracts significantly during welding. To mitigate this and achieve full penetration in a single pass, this study uses GTAW (Gas Tungsten Arc Welding) additive manufacturing and optimizes welding groove parameters via the Box-Behnken Response Surface Methodology. The focus is on improving tensile strength and penetration depth by analyzing the effects of groove angle, root face width, and root gap. The results show that groove angle most significantly affects tensile strength and penetration depth. Hardness profiles exhibit a W-shape, with base material hardness decreasing and weld zone hardness increasing as groove angle rises. Root face width reduces hardness fluctuation in the weld zone, and an appropriate root gap compensates for thermal expansion, enhancing joint performance. The interaction between root face width and root gap most impacts tensile strength, while groove angle and root face width interaction most affects penetration depth. The optimal welding parameters for 7xxx aluminum alloy GTAW are a groove angle of 70.8°, root face width of 1.38 mm, and root gap of 0 mm. This results in a tensile strength of 297.95 MPa and penetration depth of 5 mm, a 90.38% increase in tensile strength compared to the RSM experimental worst group. Microstructural analysis reveals the presence of β-Mg₂Si and η-MgZn₂ strengthening phases, which contribute to the material’s enhanced mechanical properties. Fracture surface examination exhibits characteristic ductile fracture features, including dimples and shear lips, confirming the material’s high ductility. The coexistence of these strengthening phases and ductile fracture behavior indicates excellent overall mechanical performance, balancing strength and plasticity. Full article

In order to accurately calculate the efficiency of electric vehicle drive motors in the full speed range during the design phase, this paper proposes a comprehensive motor loss fast calculation method. Firstly, a high-fidelity joint simulation model of control and design was established to simulate the real excitation sources in actual operation. Secondly, detailed modeling was conducted for each loss. Regarding iron loss, this paper considers the effects of PWM harmonics, as well as cutting, welding, and other processes, on the loss based on finite element calculations. This paper proposes a semi-analytical AC copper loss calculation method, which superimposes the effective section and end winding separately. A fast improvement simulation method is proposed for the eddy current loss of permanent magnets, which equivalently combines 2D finite element and 3D finite element, while considering factors such as segmentation. Finally, a loss separation scheme was designed and experimentally verified for each loss and motor efficiency, proving that the efficiency calculation error of most operating points was less than 1.5%. Full article

As key nodes in the energy transmission network, oil and gas pipeline stations are crucial in ensuring national energy security and stable economic development. The traditional construction mode of “on-site prefabrication and installation” has problems, such as low efficiency, high cost, and large quality fluctuations, which make it difficult to meet current construction needs. Factory prefabrication technology for pipelines has become a key path to solving industry pain points. This article focuses on the factory prefabrication technology of oil and gas station pipelines. By integrating key technologies, such as 3D modeling, automated welding, modular transportation, and intelligent detection, the visualization and digitization of station pipeline design are achieved, providing a basis for prefabrication and processing. They also improve welding quality and efficiency through automated welding technology and non-destructive testing technology. Through research on the planning and construction of prefabrication factories, construction organization and quality management, supply chain management, and information technology applications, real-time monitoring and information management of the construction process have been achieved. Case analysis shows that factory prefabrication can achieve a prefabrication rate of 70% for DN50–DN600 pipelines in the station, 80% for automated welding seams, a total construction period reduction of about 30%, a one-time welding qualification rate of over 96%, and a significant cost reduction, reflecting the significant advantages of factory prefabrication in terms of construction period, quality, and cost. Further research has clarified that factory prefabrication technology can effectively improve the efficiency, quality, and economic benefits of pipeline construction in oil and gas stations, promote the transformation of construction towards a high-efficiency, low-carbon, and sustainable direction, and provide support for the strategic goal of “One National Network”. Full article

Robotic tack welding poses challenges in path optimization due to local optimum entrapment, limited adaptability, and high-dimensional complexity. To overcome these challenges, a Lévy flight-enhanced improved whale optimization algorithm (LF-IWOA) was developed. The algorithm combines elite opposition-based learning (EOBL), differential evolution (DE), and Lévy flight (LF) to improve global exploration capability, increase population diversity, and improve convergence. Additionally, a dynamic trajectory optimization model is designed to consider joint-level constraints, including velocity, acceleration, and jerk. The performance of LF-IWOA was evaluated using two industrial workpieces with varying welding point distributions. Comparative experiments with metaheuristic algorithms, such as the genetic algorithm (GA), WOA and other recent nature-inspired methods, show that LF-IWOA consistently achieves shorter paths and faster convergence. For Workpiece 1, the algorithm reduces the welding path by up to 25.53% compared to the genetic algorithm, with an average reduction of 14.82% across benchmarks. For Workpiece 2, the optimized path is 18.41% shorter than the baseline. Moreover, the dynamic trajectory optimization strategy decreases execution time by 26.83% and reduces mechanical energy consumption by 15.40% while maintaining smooth and stable joint motion. Experimental results demonstrated the effectiveness and practical applicability of the LF-IWOA in robotic welding tasks. Full article

Almost 70 years after the surprise discovery of a cache of textile-wrapped relics inside an early 13th-century reliquary bust, the St Eustace head reliquary (accession number 1850,1127.1), four of the textile relic wrappings were analysed by combining multiband imaging and fibre-optic reflectance spectroscopy (FORS), as well as dye analysis by high-pressure liquid chromatography coupled to mass spectrometry (HPLC-MS) and fibre analysis by scanning electron microscopy—energy dispersive X-ray spectroscopy (SEM-EDX). In all cases, the use of silk was confirmed, in line with the idea that these precious textiles were purposefully chosen for reuse in a sacred setting. Additionally, dye analysis was able to point to the possible geographic origins of the textile fragments. For 1850,1127.1.a, a mixture of sappanwood (Biancaea sappan) and flavonoid yellow dyes was commensurate with a Chinese or Central Asian origin. Mediterranean origins were thought likely for 1850,1127.1.c and 1850,1127.1.f, from the mixture of kermes (Kermes vermilio) and cochineal (likely Porphyrophora sp.), found in the mauve band of the former, and the combination of weld (Reseda luteola), madder (Rubia tinctorum) and an indigoid dye found in the latter. Finally, the unusual combination of sappanwood, orchil and a yellow dye containing flavonoid glucuronides suggested a less straightforward origin for textile 1850,1127.1.g. The other textile fragments from the reliquary were only investigated using FORS without removing them from their Perspex glass mounts. Nonetheless, indications for the presence of insect-red anthraquinone dyes, safflower (Carthamus tinctorius) and an indigoid dye were obtained from some of these fragments. The study provides a window into the landscape of availability, use and re-use in sacred contexts of precious textiles in the 13th century and evidences the geographic reach of these silks, allowing a new perspective on the St Eustace head reliquary. Full article

To address the challenges of redundant point cloud processing and insufficient robustness under complex working conditions in existing teaching-free methods, this study proposes a dual-modal perception framework termed “2D image autonomous recognition and 3D point cloud precise planning”, which integrates stereo vision and deep learning. First, an improved U-Net deep learning model is developed, where VGG16 serves as the backbone network and a dual-channel attention module (DAM) is incorporated, achieving robust weld segmentation with a mean intersection over union (mIoU) of 0.887 and an F1-Score of 0.940. Next, the weld centerline is extracted using the Zhang–Suen skeleton refinement algorithm, and weld feature points are obtained through polynomial fitting optimization to establish cross-modal mapping between 2D pixels and 3D point clouds. Finally, a groove feature point extraction algorithm based on improved RANSAC combined with an equal-area weld bead filling strategy is designed to enable multi-layer and multi-bead robot trajectory planning, achieving a mean absolute error (MAE) of 0.238 mm in feature point positioning. Experimental results demonstrate that the method maintains high accuracy under complex working conditions such as noise interference and groove deformation, achieving a system accuracy of 0.208 mm and weld width fluctuation within ±0.15 mm, thereby significantly improving the autonomy and robustness of robot trajectory planning. Full article

Over the past decade, friction stir spot welding (FSSW) has gained increasing attention, making it a competitor to conventional welding methods such as resistance welding, rivets, and screws. This type of welding is environmentally friendly because it does not require welding tools and is solid-state welding. This study attempts to demonstrate the importance of pin geometry on temperature distribution and joint quality by using threaded and non-threaded pins for similar and dissimilar alloys. To this end, thermal analysis of the welded joints was conducted using real-time monitoring from a thermal camera and an infrared thermometer, in addition to finite element method (FEM) simulations. The thermal analysis showed that the generated temperatures were higher in dissimilar alloys (Al-Cu) than in similar ones (Al-Al), reaching about 350 °C. In addition, dissimilar alloys show more pronounced FSSW stages through extended periods for each plunging, dwelling, and drawing-out time. The FEM simulation results are consistent with those obtained from thermal imaging cameras and infrared thermometers. The dwelling time was influential, as the higher it was, the more heat was generated, which could be close to the melting point, especially in aluminum alloys. This study provides an in-depth experimental and numerical investigation of temperature distribution throughout the welding cycle, utilizing different pin geometries for both similar and dissimilar non-ferrous alloy joints, offering valuable insights for advanced industrial welding applications. Full article

The seaming of geomembranes (GMBs) is a critical aspect of their successful functioning as barriers to liquid, with bonding and welding being the commonly employed methods. Due to the limitations of conventional welding methods at the connection points between the geomembrane and the structure, extrusion welding often results in damage at the seams. The bonding method, which has lower requirements for construction conditions, has emerged as a currently viable alternative seaming technique. Bonding techniques are widely applied in small reservoirs and embankments. This study investigates the performance of high-density polyethylene (HDPE) GMB seams bonded using asphalt-based adhesive (ABA) and non-asphalt-based adhesive (NABA). Seam tensile tests were conducted under wetting and freeze-thaw cycles (FTCs) conditions to evaluate the mechanical properties of the seamed GMBs. The results indicated that the seam strength of specimens bonded with ABA increased as wetting time and FTCs increased (with a maximum increase of 113.8%). In contrast, specimens bonded with NABA exhibited decreased seam strength under similar conditions (with a maximum decrease of 93.4%). Both types of specimens exhibited enhanced seam strength with increasing seam width. Due to wetting and FTCs, the seam efficiency of NABA-bonded specimens decreased, while that of ABA-bonded specimens showed slight improvement. However, the improved seam efficiency remained below 1.2%, an extremely small value. The axial tensile strength of bonded specimens was significantly lower than that of seamless specimens, failing to fulfill long-term safety operation requirements. Therefore, bonding method should be used cautiously at non-critical structural components where the welding is impractical but repair and replacement are relatively simple. The findings provide insight for GMB installers and design engineers in order to improve the performance of HDPE GMB seams. Full article

The aim of this study was to compare the dimensional accuracy of vinyl polysiloxane impressions differing in terms of curing time (regular-setting (RS) or fast-setting (FS)) in combination with different tray materials (metal (M) and plastic (P)). A typodont reference model simulated a partially edentulous maxilla. Reference points were given by center points of either precision balls welded to specific teeth or finishing-line centers of prepared teeth. These reference points enabled the detection of dimensional deviations between the digitized reference and the scans of the models achieved from the study impressions. Twenty impressions were made for each of the following four test groups: RS-M, RS-P, FS-M and FS-P. Global scan data accuracy was measured by distance and tooth axis deviations from the reference, while local accuracy was determined based on the trueness and precision of the abutment tooth surfaces. Statistical analysis was conducted using ANOVA accompanied by pairwise Tukey post hoc tests (α = 0.05). Most of the distances tended to be underestimated. Global accuracy was favorable; even for long distances, the mean absolute distance deviations were < 100 µm. Local accuracy was excellent for all test groups, with trueness ≤ 11 µm and precision ≤ 9 µm. Within the limitations of this study, all impression and tray materials were suitable to fabricate models with clinically acceptable accuracy. Full article

To address the issue of the low precision in detecting defects in aluminum alloy weld seam digital radiography (DR) images using the current target detection algorithms, a modified algorithm named YOLOv8-ELA based on YOLOv8 is proposed. The model integrates a novel HS-FPN feature fusion module, which optimizes the parameter efficiency and enhances the detection performance. For better identification of small defect features, the CA attention mechanism within HS-FPN is substituted with the ELA attention mechanism. Additionally, the first output layer is enhanced with a SimAM attention mechanism to improve the small target recognition. The experimental findings indicate that, at a 0.5 threshold, the YOLOv8-ELA model achieves mean average precision (mAP@0.5) values of 93.3%, 96.4%, and 96.5% for detecting pores, inclusions, and incomplete welds, respectively. These values surpass those of the original YOLOv8 model by 1.4, 2.3, and 0.1 percentage points. Overall, the model attains an average mAP of 95.4%, marking a 1.3% improvement over its predecessor, confirming its superior defect detection capabilities. Full article