Search Results (598)

Hot cracking in welding is a very complex phenomenon. It can happen in the weld metal zone during solidification but also in the heat-affected zone (HAZ). Hot cracking defects are material decohesion that occur at high temperatures along grain boundaries when the strain and strain rate exceed a certain level. The cracks can be internal or open to the surface in the weld bead. During a welding operation, different types of hot cracks can appear, such as hot cracking due to solidification, hot cracking due to liquation, hot cracking due to loss of ductility. The main factors favoring hot solidification cracking include the presence of residual elements and impurities, leading to the formation of a low-melting eutectic; the solidification mode; and mechanical restraints. This review paper gives an introduction to solidification cracking in stainless-steel welds, the weldability of the austenite grades, and the causes of solidification cracking occurrence. The main methods with which to detect and inspect cracks are investigated. Particular focus is placed on TIG (tungsten inert gas), also known as Gas Tungsten Arc Welding (GTAW). A review of the literature reveals that considerable progress has been made in terms of the improvement in the properties of the weld joint through the application of mitigation means and strategies. The effort made by researchers in understanding solidification cracking phenomena has been key to enhancing cracking resistance and ensuring the integrity of structures. Full article

Aero-engine blades operate under extreme conditions involving high temperature, pressure, rotational speed, and cyclic loads, making them susceptible to surface defects such as micro-cracks. Due to their small scale, weak edges, low contrast, and elongated morphology, micro-cracks are easily affected by metallic reflections, uneven illumination, and complex background textures in borescope images, resulting in high missed-detection rates for conventional detection methods. To address these challenges, this study proposes an improved YOLO11-based framework for aero-engine blade micro-crack detection. The proposed method introduces P1/P2 shallow high-resolution detection branches to enhance the perception of fine crack edges and textures, incorporates Focal Loss to alleviate foreground–background imbalance, applies object-level Tversky Loss to strengthen false-negative constraints, and adopts a hard mining strategy to improve learning for difficult crack samples. Experiments conducted on a real aero-engine borescope image dataset demonstrate that the proposed model achieves a Precision of 0.9981, Recall of 0.9606, F1-score of 0.9790, mAP50 of 0.9781, and mAP50-95 of 0.6938 on an independent test set. Compared with the YOLO11 baseline, the proposed method significantly improves crack detection accuracy, localization quality, and robustness in complex borescope inspection scenarios. Full article

Crack defects are prone to occur during MAG overlay remanufacturing of TBM cutter rings, thereby affecting the repair quality and service reliability of the remanufactured layer. In this study, longitudinal alternating magnetic field (LAMF) stirring was introduced into the MAG overlay remanufacturing process of H13 steel cutter rings to regulate molten-pool behavior and suppress crack defects. A molten-pool-scale sequentially coupled thermo-fluid-electromagnetic model was developed to compare the relative changes in the temperature and velocity fields with and without LAMF under identical MAG process parameters, heat-source input, material properties, and boundary conditions. In the model, the effect of LAMF was introduced through a Lorentz-force source term acting on the electrically conductive molten metal. The simulation results show that LAMF promoted heat redistribution within the molten pool, smoothed the thermal transition near the rear region of the molten pool, and reduced local heat accumulation. Meanwhile, LAMF modified the molten-pool flow pattern by weakening excessive flow along the welding direction and enhancing transverse circulation and vortex-induced mixing. Comparative overlay remanufacturing experiments were then conducted using a self-built magnetic-field stirring platform. Penetrant testing, X-ray inspection, metallographic observation, and industrial CT reconstruction were combined to characterize surface cracks, internal defects, and post-solidification microstructure. Compared with the non-LAMF condition, the maximum internal crack length decreased from 29.41 mm to 20.30 mm, corresponding to a reduction of 30.98%, and the crack-defect volume fraction decreased from 0.93% to 0.28%, corresponding to a decrease of 0.65 percentage points. The combined simulation and characterization results indicate that Lorentz-force-driven electromagnetic stirring improves the thermal-fluid conditions near the solidification front, thereby effectively reducing the formation tendency of solidification-related crack defects during MAG overlay remanufacturing. Full article

Steel surface defect inspection plays an essential role in maintaining product quality and production safety in industrial manufacturing. However, existing detection methods still encounter difficulties in accurately identifying tiny defects, suppressing interference from complex backgrounds, and balancing detection accuracy with computational cost. To address these challenges, this paper proposes CNS-YOLOv8, an improved defect detection model based on YOLOv8n. First, a C2f_SCConv module is introduced to enhance multi-scale feature extraction and spatial representation capability. Second, a Normalization-based Attention Module (NAM) is embedded after the high-level semantic feature layer to improve the model’s sensitivity to critical defect regions. Third, a SlimNeck structure is adopted to strengthen feature fusion while reducing computational overhead. Experimental results on the NEU-DET dataset demonstrate that CNS-YOLOv8 achieves 83.1% mAP@0.5 and 49.6% mAP@0.5:0.95, surpassing YOLOv8n by 3.9 and 1.2 percentage points, respectively. In addition, comparative experiments show that CNS-YOLOv8 outperforms Faster R-CNN and YOLOv7 in terms of mAP@0.5 while requiring substantially fewer GFLOPs. In general, the proposed method balances detection accuracy and computational efficiency effectively, highlighting its potential for real-time industrial surface defect detection. Full article

In the resistor images used in this study, many defective regions are weak coating-like marks rather than obvious scratches or pits. Their appearance is close to the epoxy background, and some visible defects were missing from the original annotation files. If these labels are used directly, the detector treats the missed defects as background samples during training. We therefore corrected the supervision before changing the feature constraint. An early YOLO26s model was first used to nominate low-overlap boxes, and these candidates were then checked manually. Only confirmed defects were merged into the labels. After this step, a scale-gated prototype consistency term was added during training to reduce the model’s bias toward the dominant tiny-defect group. On the fixed corrected benchmark, mAP50 improved from 28.14% to 63.20%, and Recall increased from 18.42% to 62.20%. In the end-to-end deployment view, where the raw and cleaned validation sets answer different practical questions, mAP50 changed from 43.66% to 63.15%, and Recall changed from 30.01% to 62.24%. For normal-size defects, Recall increased from 26.09% to 56.52%. A prototype-only transfer study on the public MVTec AD benchmark further evaluates whether the feature constraint generalizes when the label-repair stage is not applicable to clean public annotations. Since the prototype term is removed after training, the deployed detector remains the original YOLO26s model without an additional inference branch. Full article

Instance segmentation of surface defects is one of the research hotspots in the field of image segmentation. Due to limitations such as restricted receptive fields or the loss of fine-grained details, traditional neural network models still struggle to achieve sufficiently high-segmentation accuracy for surface defects. To meet the demand for high precision segmentation of surface defects on copper strips and plates in industrial quality inspection, this paper proposes a feature fusion segmentation network, termed DSFFNet. First, a dual-branch structure is designed in DSFFNet to fuse spatial-domain features with discrete cosine transform (DCT)-domain features, thereby obtaining richer feature information. Second, a 2D-DCT frequency feature extraction module is developed to more effectively capture the edge information of targets. Third, a triplet attention mechanism is introduced into the backbone network to form an attention-centric network. Finally, a bidirectional fusion module and a multi-scale fusion network are designed to capture finer-grained feature information. Comparative experiments conducted on the KUST-SEG-Dataset demonstrate that DSFFNet achieves 94.66% ± 1.07% (mask)mAP₅₀ and 95.38% ± 0.06% (box)mAP₅₀, outperforming several classic image segmentation methods. Furthermore, generalization experiments on the public NEU-Seg dataset yield a (mask)mAP₅₀ of 86.27% ± 0.01%. The generalization results indicate that DSFFNet is robust to datasets with similar defect types. Full article

Prompt specifications for multi-agent large language model (LLM) systems carry data contracts and integration logic across interdependent files but are rarely subjected to structured-inspection rigor. We report a single-system case study of iterative, agent-driven auditing applied to AEGIS (Autonomous Engineering Governance and Intelligence System), a seven-lane production pipeline whose 7152-line specification surface was audited across nine rounds, surfacing 51 consistency defects (per-round counts of 15, 8, 12, 2, 8, 1, 4, 1, 0). We present a seven-category post hoc taxonomy with explicit coding rules, non-monotonic convergence consistent with cascading edits and audit-scope expansion, and a locked audit protocol. We further report two partial replications on a public synthetic mini-specification: a cross-LLM panel of four frontier vendors (OpenAI, Anthropic, Google, xAI; 12 traces; multi-vendor union detects all five seeded defects) and an inter-rater reliability check on a stratified subsample (Cohen’s $\kappa$ = 0.80 on category, 0.46 on severity). The full reproducibility bundle accompanies the submission. Full article

Defect detection in manufacturing has evolved from manual inspection to deep learning-based Automated Visual Inspection (AVI) systems; however, acquiring sufficient defect samples in real industrial environments remains challenging, causing severe data sparsity and class imbalance. We propose CASDA (Context-Aware Steel Defect Augmentation), a five-stage framework that classifies defect morphology and background surface properties, constructs a compatibility matrix encoding their contextual relationship, and synthesizes defect images via a ControlNet pipeline conditioned on a three-channel hint image. Experiments on the Severstal steel dataset demonstrate that CASDA achieves an 83.0% quality validation pass rate. Under multi-seed evaluation (seeds 42 and 456), CASDA improved EB-YOLOv8’s overall mAP@0.5 by 2.60 pp over the raw baseline and achieved a Class 2 AP gain of 22.09 pp over Copy-Paste, suggesting that context-aware synthesis produces more discriminative minority-class training samples than simple patch reuse under the tested settings. Performance gains are architecture-dependent; YOLO-MFD did not show overall improvement, indicating that augmentation sensitivity varies with backbone feature representation. Full article

Digital tools in aluminum alloy processing are computational, sensing-based, and data-driven methods used to understand, predict, monitor, optimize, and control how aluminum alloys are transformed into components. They support decisions across casting, deformation processing, heat treatment, welding, surface engineering, and additive manufacturing by linking processing conditions with geometry, microstructure, defects, properties, and service performance. In technical use, the term includes finite element method (FEM), computational fluid dynamics (CFD), CALculation of PHAse Diagrams (CALPHAD), microstructure models, machine-learning regressors, surrogate models, nondestructive digital inspection, image-analysis tools, and digital twins. These tools are most effective when they establish links among controllable processing variables, underlying metallurgical mechanisms, measurable quality indicators, and service-relevant performance outcomes. Full article

The reliable inspection of aging oil and gas pipelines is essential for preventing accidents and ensuring operational safety, yet the accuracy of RFID-based detection systems is often limited by noise-sensitive peak detection algorithms, motivating the need for more robust signal processing approaches. In this study, an improved Discrete Wavelet Transform (DWT)-based method is proposed, employing db6/db8 wavelets for signal denoising and reconstruction, followed by peak localization using derivative zero-crossing to enhance detection precision. Experimental validation was conducted through both simulations and physical tests, where the proposed method achieved zero false and missed detections in simulation environments and reduced relative error by 30–50% compared to conventional algorithms in practical scenarios. These results demonstrate that the proposed approach significantly improves detection reliability and accuracy. Overall, the method provides an effective and cost-efficient solution for pipeline surface defect inspection, offering strong potential for application in real-world industrial monitoring systems. Full article

Aircraft skin defect recognition is a safety-critical visual inspection task in which lightweight models must maintain high diagnostic accuracy while suppressing false alarms caused by complex surface textures, illumination variations, and weak defect patterns. This study proposes HQCA-Net, a simulation-based hybrid quantum-classical channel attention network for reliable aircraft skin defect recognition. The core component, termed Residual Quantum Channel Attention (RQCA), embeds a 10-qubit variational quantum circuit into a classical ResNet-18 backbone to perform compact and structured nonlinear feature recalibration, introducing only 30 trainable quantum-gate parameters. The quantum circuit is evaluated using state-vector simulation, and this study focuses on model-level feature recalibration, reliability, and robustness within the evaluated dataset rather than implementation on physical quantum hardware. Experiments on a six-class aircraft skin defect dataset show that HQCA-Net achieves 97.93% classification accuracy and a global false positive rate of 0.49%, outperforming ResNet-18 and classical lightweight attention mechanisms including SE, ECA, and SimAM. Additional analyses using confidence calibration, Grad-CAM visualization, Gaussian noise perturbation, few-shot training, and circuit-depth ablation further indicate that the proposed RQCA module improves feature discrimination and false-alarm suppression under compact parameter constraints. These results suggest that the hybrid quantum-classical attention module can serve as a parameter-efficient nonlinear feature recalibration strategy for reliable visual defect inspection under the tested experimental conditions. Full article

Electroluminescence (EL) imaging is widely used for photovoltaic (PV) defect inspection, yet fair comparison of deep learning backbones remains difficult because datasets, labels, and protocols vary across studies. This work presents a controlled image-level benchmark of six architectures (ConvNeXt-T, ViT-B/16, DeiT-B/16, Swin-T, DenseNet121, and MobileNetV3-Large) across five hierarchical tasks for monocrystalline and polycrystalline cells with binary and multi-class labels. A balanced proprietary dataset of 20,000 single-cell EL images was evaluated with identical preprocessing, augmentation, training, and stratified five-fold cross-validation, yielding 150 runs. ConvNeXt-T achieved the highest mean macro-F1 (93.12%) while using about one-third of the parameters of base ViT/DeiT models. On the four-class polycrystalline task, it reached 84.94 ± 0.45% macro-F1, compared with 70.08 ± 1.19% for DenseNet121 and 59.43 ± 1.71% for MobileNetV3-Large. Error analysis revealed conservative missed-defect behavior in lightweight CNNs, especially for surface-level degradation and crack categories. The results provide image-level cross-validation evidence for controlled benchmarking and motivate future module-level grouped validation. Full article

From the perspective of applied surface science, heritage textiles from the Kashgar region can be regarded as fragile fibrous surface systems in which stains, abrasion, yarn breakage, yarn shedding, holes, and color fading represent measurable surface-degradation phenomena. However, manual inspection of these complex, woven, embroidered, and aged surfaces is time-consuming and difficult to standardize. To support non-contact surface-condition documentation, this study proposes an improved YOLOv8-based framework, YOLOv8-MABFT, for surface defect detection and condition-level assessment of Kashgar heritage textiles. The model integrates the C2f-Faster-EMA module and an RT-DETR-informed decoder head to improve the detection of weak-boundary and fine-grained surface defects. A dataset of 8247 high-resolution annotated images was constructed, covering six surface-degradation categories: stains, broken yarn, yarn shedding, holes, abrasion, and color fading. Experimental results show that YOLOv8-MABFT achieves an F1-score of 94.6%, a precision of 91.4%, a recall of 98.0%, and an mAP@0.5 of 94.0%, outperforming Faster R-CNN, SSD, YOLOv5n, YOLOv7n, and YOLOv8n while maintaining lightweight computational characteristics. CAM-based visualizations indicate that the improved model focuses more consistently on defect-related surface regions rather than surrounding decorative textures. Based on detected defects, seven surface-condition variables were constructed and input into a Random Forest classifier for four-level condition prediction. SHAP analysis shows that Distribution and Severity are the main contributors to condition classification. Overall, the proposed framework provides an applied surface-science tool for non-contact surface defect detection, surface-condition documentation, and preliminary condition-level assessment of fragile textile substrates. Full article

Accurate surface defect classification is a critical requirement in structural health monitoring and infrastructure inspection, where defects, including cracks, spalling, delamination and noncrack regions, often appear with low-contrast and complex background textures. Motivated by the need for a robust and discriminative framework that can enhance defect visibility and focus learning on damage-critical regions, this research proposes a novel damage-aware DenseNet-201 (DA-DenseNet-201) model for surface defect classification. As a critical novelty, a damage-aware adaptive contrast-limited adaptive histogram equalisation (DAC) filtering strategy is introduced as a preprocessing stage. The proposed DAC filter dynamically adjusts contrast enhancement parameters based on damage indicators, selectively amplifying crack edges and defect textures while preserving healthy surface regions and suppressing noise. Building on this method, enhanced images are processed using a pretrained DenseNet-201 backbone, retaining the benefits of dense feature propagation and efficient gradient flow. To strengthen the discriminative learning of DA-DenseNet-201 further, an attention refinement block is integrated into the network, combining channel attention to emphasise defect-relevant feature responses and spatial attention to localise damage regions accurately. In addition, a multiscale feature fusion mechanism aggregates feature maps from multiple dense blocks to capture fine-grained crack patterns, texture-level degradation and high-level semantic damage information. Extensive experiments conducted on surface defect datasets demonstrate its effectiveness, achieving a superior classification accuracy of 98.93%, along with notable improvements in sensitivity, specificity and the intersection over union compared with state-of-the-art models. These results confirm that the proposed DA-DenseNet-201 provides a reliable and high-performance solution for automated surface defect classification. Full article

Automated visual inspection of photovoltaic (PV) cells is an important component of solar-module quality assurance. However, adapting modern pre-trained vision backbones to PV defect classification remains challenging because full fine-tuning requires substantial memory, naturally imbalanced datasets can reduce sensitivity to rare defect classes, and edge-oriented inspection workflows impose computational constraints. Parameter-efficient fine-tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA) and Quantized LoRA (QLoRA), have been widely studied in natural language processing, but their use for PV defect classification remains underexplored. This study presents a controlled benchmark of LoRA and QLoRA against full fine-tuning for PV cell defect classification. Four adaptation strategies—full fine-tuning, LoRA with rank 8, LoRA with rank 16, and 4-bit QLoRA with rank 16—are evaluated using a ConvNeXt-Tiny backbone on a 17,377-image polycrystalline PV cell electroluminescence dataset referred to as POLY, covering five classes: intact, cracked, broken, surface-diffuse, and surface-point. The natural 6.7× class imbalance is preserved without synthetic resampling, and a group-aware StratifiedGroupKFold protocol based on available cell or panel-image identifiers is used to reduce identifiable leakage across folds. All PEFT variants slightly outperform full fine-tuning in macro-F1 while training 26–52× fewer parameters. QLoRA_r16 achieves the highest macro-F1 score of 79.92 ± 0.75%, compared with 78.26 ± 0.94% for full fine-tuning, while training the same number of parameters as LoRA_r16 (1.060 M; 3.67% of the adapted model). QLoRA_r16 also improves F1 on the intact (+4.75 points) and surface-diffuse (+2.62 points) classes relative to full fine-tuning. This class-wise pattern suggests that quantized low-rank adaptation may influence minority and visually ambiguous categories; however, the present experiments do not isolate the independent effect of NF4 quantization from adapter rank, batch size, or optimization dynamics. Under the training configuration used, QLoRA_r16 records the lowest observed peak training GPU memory, approximately 30% below full fine-tuning (1727 MB versus 2478 MB). Because QLoRA_r16 was trained with batch size 16 whereas the other methods used batch size 32, this reduction should be interpreted as an end-to-end configuration effect rather than as the isolated effect of 4-bit quantization. Overall, the results indicate that PEFT is a promising and resource-efficient alternative to full fine-tuning for PV defect classification, although batch-matched memory experiments, direct embedded-device profiling, and cross-dataset validation remain necessary before making deployment-level claims. Full article