Search Results (79)

To address the limited detection accuracy of casting defects—including pores, inclusions, and looseness—in digital radiography (DR) images, which stems from their small scale, high morphological variability, and interference from complex background textures, we propose MTS-YOLOv11: an edge–discrepancy collaborative defect detection framework tailored for casting DR imagery. Built upon YOLOv11, MTS-YOLOv11 incorporates three key innovations: (1) a Multi-Scale Edge Information Enhancement System (MSEES), integrated into the C3K2 module of the backbone network, to strengthen discriminative feature extraction for minute defects; (2) a TripletAttention mechanism embedded in high-level backbone stages to jointly calibrate channel–spatial dependencies and suppress texture-induced spurious responses under complex backgrounds; (3) a Scale-Discrepancy-Aware Gated Fusion (SDAGFusion) module positioned immediately before the detection head, enabling scale-discrepancy-aware gated fusion of multi-scale features, emphasizing defect regions while suppressing background interference. Experimental results show that on the casting DR dataset, MTS-YOLOv11 achieves mAP@0.5 = 96.5% and mAP@0.5:0.95 = 68.5%—improvements of 1.3 and 1.2 percentage points over the baseline YOLOv11—across all three defect categories. Moreover, on the same platform, MTS-YOLOv11 achieves an inference speed of 359.07 FPS, compared with 346.86 FPS for the baseline. Meanwhile, the model has 2.72M parameters and 7.8G FLOPs. These results indicate a consistent improvement in detection accuracy while maintaining a practical balance between precision and computational efficiency. Moreover, cross-dataset generalization tests on newly acquired industrial DR data show that MTS-YOLOv11 consistently outperforms the baseline across evaluation metrics, suggesting improved robustness to unseen imaging conditions and supporting its potential for real-world foundry inspection. Full article

Turbine blades serve as critical components in aircraft engines, yet casting defects inevitably arise during manufacturing. Therefore, accurate pre-service turbine blade defect detection is critical for aircraft engine safety. However, existing deep learning-based detection methods face several challenges: poor image quality, intraclass variance, interclass similarity, and irregular defect geometries. Moreover, most existing defect detection methods rely primarily on spatial-domain features, which are insufficient for capturing fine-grained texture information, limiting their ability to discriminate complex defect patterns. To address these challenges, we propose a novel Spatial-Frequency Complementary Fusion Network (SFCF-Net) that synergistically integrates spatial and frequency-domain features through complementary cross-modal fusion for accurate defect segmentation. First, a Selective Cross-modal Calibration (SCC) module is introduced that selectively calibrates spatial-frequency features through gated cross-modal interactions, effectively preserving fine-grained details under poor image conditions. Next, we propose a Cross-modal Refinement and Complementation (CRC) module that employs dual-stage attention mechanisms to model intra- and inter-modal feature dependencies, enabling robust discrimination between similar defect categories while maintaining consistency within the same defect class. Finally, we propose an Asymmetric Window Attention (AWA) module that employs bidirectional rectangular windows for accurate defect geometric characterization. Comprehensive experiments on the Aero-engine Turbine Blade Casting Defect Segmentation (ATBCD-Seg) dataset and a public benchmark demonstrate that SFCF-Net consistently outperforms state-of-the-art methods across multiple evaluation metrics, meeting practical requirements for automated quality control in blade manufacturing. Full article

Road defect detection is essential for traffic safety and infrastructure maintenance. Excising automated methods based on 2D image analysis lack spatial context and cannot provide accurate 3D localization required for maintenance planning. We propose a novel framework for road defect mapping from monocular video sequences by integrating differentiable Bird’s-Eye-View (BEV) mesh representation, semantic filtering, and multi-frame temporal fusion. Our differentiable mesh-based BEV representation enables efficient scene reconstruction from sparse observations through MLP-based optimization. The semantic filtering strategy leverages road surface segmentation to eliminate off-road false positives, reducing detection errors by 33.7%. Multi-frame fusion with ray-casting projection and exponential moving average update accumulates defect observations across frames while maintaining 3D geometric consistency. Experimental results demonstrate that our framework produces geometrically consistent BEV defect maps with superior accuracy compared to single-frame 2D methods, effectively handling occlusions, motion blur, and varying illumination conditions. Full article

Artificial intelligence (AI) is increasingly adopted in manufacturing for tasks such as automated inspection, predictive maintenance, and condition monitoring. However, the opaque, black-box nature of many AI models remains a major barrier to industrial trust, acceptance, and regulatory compliance. This study investigates how explainable artificial intelligence (XAI) techniques can be used to systematically open and interpret the internal reasoning of AI systems commonly deployed in manufacturing, rather than to optimise or compare model performance. A unified explainability-centred framework is proposed and applied across three representative manufacturing use cases encompassing heterogeneous data modalities and learning paradigms: vision-based classification of casting defects, vision-based localisation of metal surface defects, and unsupervised acoustic anomaly detection for machine condition monitoring. Diverse models are intentionally employed as representative black-box decision-makers to evaluate whether XAI methods can provide consistent, physically meaningful explanations independent of model architecture, task formulation, or supervision strategy. A range of established XAI techniques, including Grad-CAM, Integrated Gradients, Saliency Maps, Occlusion Sensitivity, and SHAP, are applied to expose model attention, feature relevance, and decision drivers across visual and acoustic domains. The results demonstrate that XAI enables alignment between model behaviour and physically interpretable defect and fault mechanisms, supporting transparent, auditable, and human-interpretable decision-making. By positioning explainability as a core operational requirement rather than a post hoc visual aid, this work contributes a cross-modal framework for trustworthy AI in manufacturing, aligned with Industry 5.0 principles, human-in-the-loop oversight, and emerging expectations for transparent and accountable industrial AI systems. Full article

The seeding technique is the only way to precisely control the crystal orientation of single-crystal superalloy castings. However, an inevitable assembly gap exists between the seed and the mold cavity in practice, whose role in defect formation remains insufficiently understood. To elucidate the mechanism and impact of this gap, superalloy seeds were machined to different extents, aiming to create varying gaps with the mold. After the seeding experiment, the chilled layers formed on the perimeter of the pre-processed seeds were detected, exhibiting two distinct microstructural zones: a eutectic aggregation region at the bottom and an equiaxed grain at the top. The thicker the layer, the more pronounced the differences in microstructure between these two regions. This can be explained by the fact that during preheating, the γ/γ′ eutectic-rich interdendritic region (enriched with Al + Ti + Ta) in the original seed melted first due to its lower melting point. The molten fluid flowed downward into the gap, solidifying rapidly into the chilled layer. The leading portion of the fluid, melting from the interdendritic zone, formed the eutectic zone in the lower part of the chilled layer. The subsequently poured charge alloy melt (non-enriched with Al + Ti + Ta) generated the upper equiaxed zone with only a little γ/γ′ eutectic. These equiaxed grains in the chilled layer subsequently grew upward and potentially developed into stray grains of the casting. Full article

In order to determine the causes of crack defects in Mn18Cr2 high-manganese wear-resistant steel plates, this paper conducted a systematic analysis of the steel plates’ microstructure, chemical composition, and hardness via metallographic microscopy, field-emission scanning electron microscopy, and Vickers hardness tester. The results indicated that there were folded cracks on the surface of the steel plate. The interior of the cracks was oxidized, and inclusions were observed in the crack gaps. A significant difference in the contents of Mn and Cr elements was detected at the defect locations, indicating that very obvious long-range diffusion of Mn and Cr elements had occurred during long-term high-temperature oxidation. The crack defects on the surface of the steel plate were related to the inheritance of the original cracks on the surface of the cast billet before rolling. There were cracks on the surface of the cast billet; the oxide scale and inclusions inside the cracks had not been completely removed. Multiple passes of rolling led to the cracks and oxide scale being pressed into the steel surface, thereby forming folding defects. The fine grain strengthening and deformation twinning generated by rolling deformation formed the hardened layer on the surface, resulting in higher surface hardness than core hardness. The austenite grain size inside the steel plate was in the range of 23–30 μm, and the hardness was around 275 HV. The grain size near the surface of the steel plate was around 10 μm. The surface hardness was 351 HV, which was higher than the core hardness of the steel plate. Full article

X-ray-based non-destructive testing technology plays a crucial role in the quality monitoring of aluminum alloy wheel hubs. Due to the characteristics of the casting process, wheel hub images often exhibit low contrast and a discrete distribution of defect edges. Existing methods often face problems such as poor feature extraction capability, low efficiency of cross-scale information fusion, and susceptibility to interference from complex backgrounds when detecting such defects. Therefore, this study proposes an innovative detection framework for defects in aluminum alloy wheel hubs. The model employs data preprocessing to enhance the quality of original images; integrates an asymmetric pinwheel-shaped convolution (PConv) with an efficient receptive field, enabling efficient focus on the edge feature information of discrete defects; innovatively constructs a Mamba-based two-stage feature pyramid network (MFDPN), which improves the network’s defect localization capability in complex scenarios via a secondary focusing-diffusion mechanism; and incorporates a channel and spatial attention block (CASAB), strengthening the model’s ability to resist interference from complex backgrounds. On our self-built wheel hub defect dataset, the proposed model outperforms the baseline by 7.2% in mAP50 and 5% in Recall at 39 FPS inference speed, thus validating its high practical utility for automated aluminum alloy wheel hub defect detection. Full article

Continuous casting is a key core link in steel production with characteristics of strong nonlinearity, multi-parameter coupling and dynamic fluctuations under working conditions. Traditional experience-dependent or mechanism-driven models are no longer suitable for the high-quality and high-efficiency production demands of modern steel industries. Machine learning provides an effective technical path for solving the complex control problems in the continuous casting process through its powerful data mining and pattern recognition capabilities. This paper systematically reviews the research progress of machine learning applications in the field of continuous casting, focusing on three core scenarios: abnormal prediction, quality defect detection and process parameter optimization. It sorts out the evolution from single models to feature optimization and integration, deep learning hybrid models, and mechanism-data dual-driven models. It summarizes the significant achievements of this technology in reducing production risks and improving the stability of cast billet quality, and it analyzes the prominent challenges currently faced such as data distortion and distribution imbalance, insufficient model interpretability and limited cross-scenario generalization ability. Finally, it looks forward to future technological innovation and application expansion directions, providing theoretical support and technical references for the digital and intelligent transformation of the steel industry. Full article

Central segregation, a typical internal defect in continuous casting slabs, significantly deteriorates the mechanical properties of steel products. However, traditional manual defect evaluation methods rely heavily on experience, are highly subjective and inefficient, making it difficult to meet the quality assessment requirements of today’s high-end steel materials. In this study, an approach which combines an unsupervised image enhancement algorithm and Otsu algorithm analysis was proposed to achieve automatic recognition and quantitative features extracting of central segregation in continuous casting slabs. The challenges posed by insufficient brightness and low contrast in central segregation images were addressed using unsupervised image enhancement algorithms. Following this enhancement, batch objective quantification of the segregation images was conducted through Otsu processing. Comparative experimental results showed that the enhanced images yielded an average Dice Similarity Coefficient of 0.965 for segregation recognition, representing a 38% improvement over unprocessed images, with consistent accuracy gains across complex segregation scenarios. This intelligent detection method eliminates the need for manually labeling a training set, substantially improves the consistency of segregation quantification and reduces the time cost significantly. Consequently, multiple parameters can be employed to quantify segregation characteristics, offering a more comprehensive and precise approach than current simplified rating methods. This advancement holds promise for enhancing quality control in steel processing and advancing Artificial Intelligence-driven technological progress within the metallurgical sector. Full article

Quality assurance in aluminum die casting is critical, as internal defects—such as porosity—can compromise structural integrity and significantly reduce component service life. In the cost-sensitive manufacturing environment of Germany, early and automated rejection of defective parts is essential to minimize scrap, rework, and energy waste. This study investigates the feasibility and performance of deep learning for automated defect detection in industrial X-ray images of two series-production aluminum die-cast components. A systematic methodology was employed: first, candidate object-detection frameworks (YOLOv5 vs. Faster R-CNN) were evaluated under real-time constraints (<2 s per image) on standard industrial hardware; subsequently, position-specific and single global models were trained on annotated datasets. A systematic hyperparameter study—focusing on input resolution, learning rate, and loss weights—was conducted to optimize accuracy and robustness. The best-performing models achieved F1-scores up to 0.87, with position-specific models outperforming the single global model on average. The approach was validated under real production conditions at Hengst SE (Nordwalde), demonstrating practical feasibility, strong acceptance among quality professionals, and significant potential to accelerate inspections and standardize decision-making. The results confirm that deep learning is a viable alternative to rule-based image processing and holds substantial promise for automating X-ray inspection workflows in aluminum die casting, contributing to both operational efficiency and sustainability goals. Full article

This study investigates the use of steel and cast iron for producing cast furnace rolls to replace welded rolls, which often fail from cracks and limited durability. Casting had not been previously considered by the manufacturer, but rising demands for durability and quality make it a promising alternative. Material selection focused on mechanical properties, wear resistance, and production costs. To ensure casting quality, Magmasoft 6.0 software was applied for detailed simulation of casting, solidification, and cooling. Results showed that steel alloys (GS-34CrMo4 and GS-20Mn5) are prone to shrinkage and porosity, which cannot be fully avoided even with feeders. In contrast, GJS-500-7 cast iron exhibited low shrinkage tendency and minimal defects, proving suitable for production while reducing costs. It also offers lower weight and efficient metal use, improving cost-effectiveness. Detected defects were concentrated in the central casting area, where they have little impact on functionality. Based on sixteen simulations, GJS-500-7 cast iron emerged as the most suitable material for furnace rolls thanks to its thermal resistance, castability, low porosity, and ability to meet required specifications. This process optimization represents an efficient, cost-effective choice, improving final product quality and creating new opportunities for the manufacturer. Full article

Automated quality control is critical in modern manufacturing, especially for metallic cast components, where fast and accurate surface defect detection is required. This study evaluates classical Machine Learning (ML) algorithms using extracted statistical parameters and deep learning (DL) architectures including ResNet50, Capsule Networks, and a 3D Convolutional Neural Network (CNN3D) using 3D image inputs. Using the Dataset Original, ML models with the selected parameters achieved high performance: RF reached 99.4 ± 0.2% precision and 99.4 ± 0.2% sensitivity, GB 96.0 ± 0.2% precision and 96.0 ± 0.2% sensitivity. ResNet50 trained with extracted parameters reached 98.0 ± 1.5% accuracy and 98.2 ± 1.7% F1-score. Capsule-based architectures achieved the best results, with ConvCapsuleLayer reaching 98.7 ± 0.2% accuracy and 100.0 ± 0.0% precision for the normal class, and 98.9 ± 0.2% F1-score for the affected class. CNN3D applied on 3D image inputs reached 88.61 ± 1.01% accuracy and 90.14 ± 0.95% F1-score. Using the Dataset Expanded with ML and PCA-selected features, Random Forest achieved 99.4 ± 0.2% precision and 99.4 ± 0.2% sensitivity, K-Nearest Neighbors 99.2 ± 0.0% precision and 99.2 ± 0.0% sensitivity, and SVM 99.2 ± 0.0% precision and 99.2 ± 0.0% sensitivity, demonstrating consistent high performance. All models were evaluated using repeated train-test splits to calculate averages of standard metrics (accuracy, precision, recall, F1-score), and processing times were measured, showing very low per-image execution times (as low as $3.69\times {10}^{-4}$ s/image), supporting potential real-time industrial application. These results indicate that combining statistical descriptors with ML and DL architectures provides a robust and scalable solution for automated, non-destructive surface defect detection, with high accuracy and reliability across both the original and expanded datasets. Full article

In this study, we report the fabrication and multi-technique characterization of pure and rare-earth (RE)-doped ZnO thin films using nanostructured microclusters synthesized via electrospinning followed by calcination. Lanthanum (La), erbium (Er), and samarium (Sm) were each incorporated at five concentrations (0.1–5 at.%) into ZnO, and the resulting powders were drop-cast as thin films on glass substrates. This approach enables the transfer of pre-engineered nanoscale morphologies into the final thin-film architecture. The morphological analysis by scanning electron microscopy (SEM) revealed a predominance of spherical nanoparticles and nanorods, with distinct variations in size and aspect ratio depending on dopant type and concentration. X-ray diffraction (XRD) and Rietveld analysis confirmed the wurtzite ZnO structure with increasing evidence of secondary phase formation at high dopant levels (e.g., Er₂O₃, Sm₂O₃, and La(OH)₃). Raman spectroscopy showed peak shifts, broadening, and defect-related vibrational modes induced by RE incorporation, in agreement with the lattice strain and crystallinity variations observed in XRD. Elemental mapping (EDX) confirmed uniform dopant distribution. Optical transmittance exceeded 70% for all films, with Tauc analysis revealing slight bandgap narrowing (Eg = 2.93–2.97 eV) compared to pure ZnO. This study demonstrates that rare-earth doping via electrospun nanocluster precursors is a viable route to engineer ZnO thin films with tunable structural and optical properties. Despite current limitations in film-substrate adhesion, the method offers a promising pathway for future transparent optoelectronic, sensing, or UV detection applications, where further interface engineering could unlock their full potential. Full article

As the demand for lightweight and high-performance conductive materials grows in power transmission systems, aluminum alloy rods have emerged as a cost-effective and scalable alternative to copper conductors. This review systematically examines the development status and technological progress in the purification and casting–rolling processes used in the production of Electrical Round Aluminum Rods (ERARs). It explores current challenges in improving electrical conductivity and mechanical strength while addressing issues such as hydrogen and oxide inclusion removal, grain refinement, and impurity segregation. Key purification techniques—including flux refining, gas treatment, filtration, and rotary injection—are compared in terms of performance, cost, and environmental impact. The paper also analyzes different casting–rolling methods, including continuous casting and rolling, twin-roll casting, and extrusion processes, with attention to process optimization and equipment design. Furthermore, emerging applications of artificial intelligence (AI) in predictive modeling, defect detection, and process parameter optimization are highlighted, offering a novel perspective on intelligent and sustainable ERAR production. This paper aims to provide insights for facilitating the industrial-scale production and performance enhancement of ERAR materials. Full article

In this paper, to address the issue of the unknown influence of activation functions on casting defect detection using convolutional neural networks (CNNs), we designed five sets of experiments to investigate how different activation functions affect the performance of casting defect detection. Specifically, the study employs five activation functions—Rectified Linear Unit (ReLU), Exponential Linear Units (ELU), Softplus, Sigmoid Linear Unit (SiLU), and Mish—each with distinct characteristics, based on the YOLOv8 algorithm. The results indicate that the Mish activation function yields the best performance in casting defect detection, achieving an mAP@0.5 value of 90.1%. In contrast, the Softplus activation function performs the worst, with an mAP@0.5 value of only 86.7%. The analysis of the feature maps shows that the Mish activation function enables the output of negative values, thereby enhancing the model’s ability to differentiate features and improving its overall expressive power, which enhances the model’s ability to identify various types of casting defects. Finally, gradient class activation maps (Grad-CAM) are used to visualize the important pixel regions in the casting digital radiography (DR) images processed by the neural network. The results demonstrate that the Mish activation function improves the model’s focus on grayscale-changing regions in the image, thereby enhancing detection accuracy. Full article