Search Results (812)

High-precision automated detection of metal welding defects is critical to ensuring structural safety and reliability in modern manufacturing. However, existing methods often struggle with insufficient fine-grained feature retention, low efficiency in multi-scale information fusion, and vulnerability to complex background interference, resulting in low detection accuracy. This work addresses the limitations by introducing the DEIM-SFA, a novel detection framework designed for automated visual inspection in industrial machine vision sensors. The model introduces a novel structure-aware dynamic convolution (SPD-Conv), effectively focusing on the fine-grained structure of defects while suppressing background noise interference; an innovative multi-scale dynamic fusion pyramid (FTPN) architecture is designed to achieve efficient and adaptive aggregation of feature information from different receptive fields, ensuring consistent detection of multi-scale targets; combined with a lightweight and efficient multi-scale attention module (EMA), this further enhances the model’s ability to locate salient regions in complex scenarios. The network is evaluated on a self-built welding defect dataset. Experimental results show that DEIM-SFA achieves a 3.9% improvement in mAP50 compared to the baseline model, mAP75 by 4.3%, mAP50–95 by 3.7%, and Recall by 1.4%. The model exhibits consistently significant superiority in detection accuracy across targets of various sizes, while maintaining well-balanced model complexity and inference efficiency, comprehensively surpassing existing state-of-the-art (SOTA) methods. Full article

Visual inspection remains a cornerstone of quality control in welded structures, yet manual evaluations are inherently constrained by subjectivity, inconsistency, and limited scalability. This study presents WeldVGG, a deep learning-based visual inspection model designed to automate weld defect classification using radiographic imagery. The proposed model is trained on the RIAWELC dataset, a publicly available collection of X-ray weld images acquired in real manufacturing environments and annotated across four defect conditions: cracking, porosity, lack of penetration, and no defect. RIAWELC offers high-resolution imagery and standardized class labels, making it a valuable benchmark for defect classification under realistic conditions. To improve trust and explainability, Grad-CAM++ is employed to generate class-discriminative saliency maps, enabling visual validation of predictions. The model is rigorously evaluated through stratified cross-validation and benchmarked against traditional machine learning baselines, including SVC, Random Forest, and a state-of-the-art architecture, MobileNetV3. The proposed model achieves high classification accuracy and interpretability, offering a practical and scalable solution for intelligent weld inspection. Furthermore, to prove the model’s ability to generalize, a test on the GDXray was performed, yielding positive results. Additionally, a Wilcoxon signed-rank test was conducted separately to assess statistical significance between model performances. Full article

This paper presents a comprehensive study on automated defect detection in complex structures using phased array ultrasonic testing data, focusing on both traditional signal processing and advanced deep learning methods. As a non-AI baseline, the well-known signal-to-noise ratio algorithm was improved by introducing automatic depth gate calculation using derivative analysis and eliminated the need for manual parameter tuning. Even though this method demonstrates robust flaw indication, it faces difficulties for automatic defect detection in highly noisy data or in cases with large pore zones. Considering this, multiple DL architectures—including fully connected networks, convolutional neural networks, and a novel Convolutional Attention Temporal Transformer for Sequences—are developed and trained on diverse datasets comprising simulated CIVA data and real-world data files from welded and composite specimens. Experimental results show that while the FCN architecture is limited in its ability to model dependencies, the CNN achieves a strong performance with a test accuracy of 94.9%, effectively capturing local features from PAUT signals. The CATT-S model, which integrates a convolutional feature extractor with a self-attention mechanism, consistently outperforms the other baselines by effectively modeling both fine-grained signal morphology and long-range inter-beam dependencies. Achieving a remarkable accuracy of 99.4% and a strong F1-score of 0.905 on experimental data, this integrated approach demonstrates significant practical potential for improving the reliability and efficiency of NDT in complex, heterogeneous materials. Full article

This study systematically investigates the effects of welding current on the macro-morphology, microstructure, mechanical properties, and corrosion resistance of Cu-Mn-Al alloy coatings deposited on 27SiMn steel substrates using Cold Metal Transfer (CMT) technology. The 27SiMn steel is widely applied in coal mining, geology, and engineering equipment due to its high strength and toughness, but its poor corrosion and wear resistance significantly limits service life. To address this issue, a Cu-Mn-Al alloy (high-manganese aluminum bronze) was selected as a cladding material because of its superior combination of mechanical strength, toughness, and excellent corrosion resistance in saline and marine environments. Compared with conventional cladding processes, CMT technology enables low-heat-input deposition, reduces dilution from the substrate, and promotes defect-free coating formation. To the best of our knowledge, this is the first report on the fabrication of Cu-Mn-Al coatings on 27SiMn steel using CMT, aiming to optimize process parameters and establish the relationship between welding current, phase evolution, and coating performance. The experimental results demonstrate that the cladding layer width increases progressively with welding current, whereas the layer height remains relatively stable at approximately 3 mm. At welding currents of 120 A and 150 A, the cladding layer primarily consists of α-Cu, κII, β-Cu₃Al, and α-Cu + κIII phases. At higher welding currents (180 A and 210 A), the α-Cu + κIII phase disappears, accompanied by the formation of petal-shaped κI phase. The peak shear strength (509.49 MPa) is achieved at 120 A, while the maximum average hardness (253 HV) is obtained at 150 A. The 120 A cladding layer demonstrates optimal corrosion resistance. These findings provide new insights into the application of CMT in fabricating Cu-Mn-Al protective coatings on steel and offer theoretical guidance for extending the service life of 27SiMn steel components in aggressive environments. Full article

The widespread application of WE43 (Mg-4Y-2Nd-1Gd-0.5Zr) alloy castings in aerospace components is hindered by the frequent formation of defects such as cracks, pores, and especially yttria inclusions. These defects necessitate subsequent welding. However, using homologous WE43 filler wires often exacerbates these issues, leading to high crack susceptibility and reintroduction of inclusions. Herein, we propose a novel strategy of tailoring Y content in filler wires to achieve high-quality welded joint of WE43 sand castings. Systematic investigations reveal that reducing Y content to 2 wt.% (WE23) effectively suppresses oxide inclusion formation and significantly enhances the integrity of the joint. The fusion zone microstructure evolves distinctly with varying Y levels: grain size initially increases, peaking at 24 μm with WE43 wire, then decreases with further Y addition. Moreover, eutectic compounds transition from a semi-continuous to a continuous network structure with increasing Y content, deteriorating mechanical performance. Notably, joints welded with WE23 filler exhibit minimal performance loss, with ultimate tensile strength, yield strength, and elongation reaching 93.0%, 98.0%, and 97.4% of the sand-cast base metal, respectively. The underlying strengthening mechanisms and solute-second phase relationships are elucidated, highlighting the efficacy of optimizing Y content in welding wire design. This study provides valuable insights toward defect-free welding of high-performance Mg-RE alloy castings. Full article

With the widespread use of high-density polyethylene (HDPE) pipes in various industrial and municipal applications, ensuring the structural integrity of their joints is crucial. This paper presents a novel defect detection method based on a microwave resonant probe, designed to perform efficient and non-destructive evaluation of butt fusion joints in HDPE pipes. The experimental setup integrates a microwave antenna and resonant cavity to record real-time variations in resonance frequency and S₂₁ magnitude while scanning the pipe surface. This method effectively detects common defects, including cracks, holes, and inclusions, within the butt fusion joints. The results show that the microwave resonant probe exhibits high sensitivity in detecting HDPE pipe defects. It can identify different sizes of cracks and holes, and can distinguish between talc powder and sand particles. This technique offers a promising solution for pipeline health monitoring, particularly for evaluating the quality of welded joints in non-metallic materials. Full article

Defect detection in lithium-ion battery (LIB) welding presents unique challenges, including scale heterogeneity, subtle texture variations, and severe class imbalance. We propose a multi-scale convolutional framework that integrates EfficientNet-B0 for lightweight representation learning, PANet for cross-scale feature aggregation, and a YOLOv8 detection head augmented with multi-head attention. Parallel dilated convolutions are employed to approximate self-similar receptive fields, enabling simultaneous sensitivity to fine-grained microstructural anomalies and large-scale geometric irregularities. The approach is validated on three datasets including RIAWELC, GC10-DET, and an industrial LIB defects dataset, where it consistently outperforms competitive baselines, achieving 8–10% improvements in recall and F1-score while preserving real-time inference on GPU. Ablation experiments and statistical significance tests isolate the contributions of attention and multi-scale design, confirming their role in reducing false negatives. Attention-based visualizations further enhance interpretability by exposing spatial regions driving predictions. Limitations remain regarding fixed imaging conditions and partial reliance on synthetic augmentation, but the framework establishes a principled direction toward efficient, interpretable, and scalable defect inspection in industrial manufacturing. Full article

Traditional natural gas transportation pipeline steels, such as API 5L X42 grade and the higher grades, are currently receiving a lot of attention in terms of their potential implementation in hydrogen transmission infrastructure. However, the microstructural constitution of steels with a ferrite phase and the presence of welds, with their non-polyhedral “sharp” microstructures acting as structural notches, make these steels prone to hydrogen embrittlement (HE). In this work, the notch tensile properties of copper- or nickel–phosphorus-coated API 5L X42 grade pipeline steel were studied in both the non-hydrogenated and electrochemically hydrogen-charged conditions in order to estimate anticipated protective effects of the coatings against HE. Both the Cu and Ni–P coatings were produced using conventional coating solutions for electroless plating. To study the material systems’ HE sensitivity, electrochemical hydrogenation of cylindrical, circumferentially V-notched tensile specimens was performed in a solution of hydrochloric acid with the addition of hydrazine sulfate. Notch tensile tests were carried out for the uncoated steel, Cu-coated steel, and Ni–P-coated steel at room temperature. The HE resistance was evaluated by determination of the hydrogen embrittlement index (HEI) in terms of relative changes in notch tensile properties related to the non-hydrogenated and hydrogen-charged material conditions. The results showed that pure electroless deposition of both coatings induced some degree of HE, likely due to the presence of hydrogen ions in the coating solutions used and the lower surface quality of the coatings. However, after the electrochemical hydrogen charging, the coated systems showed improved HE resistance (lower HEI_RA values) compared with the uncoated material. This behavior was accompanied by the hydrogen-induced coatings’ deterioration, including the occurrence of superficial defects, such as bubbling, flocks, and spallation. Thus, further continuing research is needed to improve the coatings’ surface quality and long-term durability, including examination of their performance under pressurized hydrogen gas charging conditions. Full article

The keyhole defect located at the termination of the friction stir welding (FSW) seam of 6082 aluminum alloys was repaired utilizing the refilling friction stir spot technique. This study examined the impact of the plunge depths on the microstructure of the welding spot. The results show that under the action of shear stress introduced by the pin, the (111)[1$\overline{1}$0] shear texture and (112)[11$\overline{1}$] Copper texture were formed. The formation of (001)[100] Cube and (001)[310] Cube_ND textures was due to the occurrence of discontinuous dynamic recrystallization. When the plunge depth of the sleeve was 1.0 mm, the volume fraction of deformed grains in the welding spot reached 45%, and the tensile strength of the welding spots was 184 MPa. When the plunge depth of the sleeve was 1.5 mm, the tensile strength of the repaired spot welding was 210 MPa, which was basically equal to the strength of the FSW seam. Full article

This paper investigates the influence of the internal concave surface structure of the stirring tool and welding parameters on the microstructure and mechanical properties of the T-joint. The analysis reveals that compared to the inner concave surface without spirals, T-joints welded by inner concave surfaces with spirals exhibit fewer welding defects. Meanwhile, the microscopic results showed that there is a welding juncture zone between the thermomechanical affected zone and the nugget zone, and a large number of θ’, T₁, and η’ phases precipitate in the nugget zone of the joint, which improves its strength and hardness. When welding speed v, rotational speed w and insertion depth h are 60 mm/min, 350 rpm, and 0.21 mm, respectively, the yield strength, the tensile strength, and the elongation of the T-joint reach their maximum values (352 MPa, 408 MPa and 5%), and the tensile strength represents 68.0% and 71.6% of the base materials, respectively. The fracture mechanism of the joint is a mode of ductile fracture. Furthermore, the T-joint exhibits a “W” and “Z” distribution pattern on both sides of the weld centerline B and A, respectively. Full article

Ultrasonic-assisted friction stir lap welding (FSLW) was employed to join dissimilar aluminum alloys, namely Al-7075 and Al-5052. The effect of ultrasonic power on the weld performance was systematically investigated. Increasing the ultrasonic power enhanced the material flow, resulting in a significant reduction in the cavity area in the nugget zone, from 0.37 mm² to 0.01 mm², as the ultrasonic power was increased from 0 W to 600 W. Simultaneously, increasing the ultrasonic power accelerated the dynamic recrystallization in the nugget zone, refining the grain size by 46%. This grain refinement consequently enhanced the hardness of the nugget zone, yielding an increase of approximately 10 HV. However, the excessive ultrasonic power level of 600 W also amplified the ultrasonic punch effect, inducing interfacial crack formation between Al-7075 and Al-5052 on the advancing side. These defects (cavity and interfacial crack) significantly influenced the joint failure behavior: the non-ultrasonic-assisted FSLW joints failed at the cavity, while the 600 W-ultrasonic-assisted FSLW joints failed along the interfacial crack. Comparatively, an ultrasonic power of 300 W suppressed both the cavity and interfacial crack, producing FSLW joints with the highest shear strength among all tested ultrasonic power levels (0 W, 300 W, and 600 W). Full article

As part of recent measures to combat global warming, automobiles are required to be electrified and their weight reduced, leading to the advancement of multi-material structures that include aluminum alloys and aluminum die castings. Conventional fusion welding methods for joining aluminum alloys and steel materials have poor joining performance due to differences in thermal conductivity between the materials and the presence of oxide films. Friction stir welding (FSW) has been attracting attention in recent years because it is a solid-phase joining method and can also be used to join dissimilar materials. In this study, FSW overlay joints were fabricated: Aluminum alloy AA6111 was used for the upper plate, AA6061 was used for the lower plate. Non-destructive testing was performed on each joint to instantly inspect and visualize joint defects. In the case of FSW joints, no difference was observed in the heat transfer process when the joints were heated directly, but the location of the hooking could be identified by heating from a distance from the joints. The results of the analysis of the temperature change at the defect location showed a difference in heat propagation. Full article

In order to meet the harsh working environment and complex and changeable stress conditions, the low-temperature and high-pressure liquid carbon dioxide conveying system used in oil extraction will choose metal bellows for transportation. In this paper, the bellows in an accident section are investigated and observed by the working environment and characterization methods such as macroscopic analysis, metallographic analysis, EDS component analysis, fracture scanning electron microscopy analysis, and related mechanical performance test methods. The failure mechanism of the accident is preliminarily judged, and the unidirectional fluid–structure coupling model and the standard k-ω turbulence model are used as the calculation models for subsequent simulation. Combined with Fluent finite element simulation analysis, it is verified that the failure is caused by a welding defect, the maximum stress of the metal bellows under normal conditions is less than its own yield strength, and the material can work normally. When the welding crack is greater than 2 mm, the strength of the workpiece weld will be reduced, and the stress concentration has exceeded the yield strength that the workpiece can bear, causing failure fracture at the welding defect part. Combined with ANSYS simulation of accident defects, compared with bellows without defects, the stress at the crack will increase with the increase in the inlet flow velocity and decrease with the increase in temperature, and the flow rate will have a greater influence on it. Therefore, in actual working conditions, the stiffness and fatigue life of the conveying system can be improved by appropriately reducing the liquid flow rate and increasing the temperature. It provides a reference for the future application research of bellows and the research on bellows fracture failure. Full article

Anomaly detection is a pressing issue, particularly in industrial images. Detecting weld defects in radiographic images is a challenge due to the small signal-to-noise ratio (SNR) and the limited availability of data. In this paper, we propose an automated weld defect detection method using Normalizing Flows (NFs). We employed various state-of-the-art NF architectures with different feature extractors to detect defects in radiographic images of welds, comprehensively comparing the results with radiographic images of welded steel pipes collected from industrial sites. The results show that the combination of CFlow-AD with a wide residual network-50-2 (WRN-50-2) outperformed the other methods, indicating its effectiveness in anomaly detection. Full article

This study presents a comprehensive multi-criteria decision-making (MCDM) framework for evaluating and selecting optimal non-destructive testing (NDT) techniques for oil and gas facility maintenance operations. This research used a Fuzzy Analytic Hierarchy Process (FAHP) integrated with multiple MCDM methods to assess eight NDT techniques including radiographic testing, ultrasonic testing, and thermographic testing. The evaluation framework incorporated seven technical criteria and seven economic criteria. The FAHP results revealed spatial resolution (0.175) as the most critical technical criterion, followed by depth penetration (0.155) and defect characterization (0.143). For economic criteria, downtime costs (0.210) and operational costs (0.190) emerged as the most significant factors. This study used TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), PROMETHEE (Preference Ranking Organization Method for Enrichment of Evaluations), and VIKOR (VIseKriterijumska Optimizacija I Kompromisno Resenje) methods to rank NDT techniques, with results consolidated using the CRITIC (CRiteria Importance Through Intercriteria Correlation) method. The final techno-economic analysis identified radiographic testing as the most suitable NDT method with a score of 0.665, followed by acoustic emission testing at 0.537. Visual testing ranked lowest with a score of 0.214. This research demonstrates the effectiveness of combining fuzzy logic with multiple MCDM approaches for NDT method selection in offshore welding operations. Full article