Search Results (1,403)

Automatic component recognition plays a crucial role in intelligent ship manufacturing, but existing methods suffer from low recognition accuracy and high computational cost in industrial scenarios involving small samples, component stacking, and diverse categories. To address the requirements of shipbuilding industrial applications, a Triplet Spatial Reconstruction Attention (TSA) mechanism that combines threshold-based feature separation with triplet parallel processing is proposed, and a lightweight You Only Look Once Ship (YOLO-Ship) detection network is constructed. Unlike existing attention mechanisms that focus on either spatial reconstruction or channel attention independently, the proposed TSA integrates triplet parallel processing with spatial feature separation–reconstruction techniques to achieve enhanced target feature representation while significantly reducing parameter count and computational overhead. Experimental validation on a small-scale actual ship component dataset demonstrates that the improved network achieves 88.7% mean Average Precision (mAP), 84.2% precision, and 87.1% recall, representing improvements of 3.5%, 2.2%, and 3.8%, respectively, compared to the original YOLOv8n algorithm, requiring only 2.6 M parameters and 7.5 Giga Floating-point Operations per Second (GFLOPs) computational cost, achieving a good balance between detection accuracy and lightweight model design. Future research directions include developing adaptive threshold learning mechanisms for varying industrial conditions and integration with surface defect detection capabilities to enhance comprehensive quality control in intelligent manufacturing systems. Full article

Internal crack defects in high-strength low-alloy (HSLA) steels during continuous casting pose significant challenges to downstream processing and product reliability. However, due to the inherent class imbalance in industrial defect datasets, conventional machine learning models often suffer from poor sensitivity to minority class instances. This study proposes a predictive framework that integrates conditional tabular generative adversarial network (CTGAN) for synthetic minority sample generation and CatBoost for classification. A dataset of 733 process records was collected from a continuous caster, and 25 informative features were selected using mutual information. CTGAN was employed to augment the minority class (crack) samples, achieving a balanced training set. Feature distribution analysis and principal component visualization indicated that the synthetic data effectively preserved the statistical structure of the original minority class. Compared with the other machine learning methods, including KNN, SVM, and MLP, CatBoost achieved the highest metrics, with an accuracy of 0.9239, precision of 0.9041, recall of 0.9018, and F1-score of 0.9022. Results show that CTGAN-based augmentation improves classification performance across all models. These findings highlight the effectiveness of GAN-based augmentation for imbalanced industrial data and validate the CTGAN–CatBoost model as a robust solution for online defect prediction in steel manufacturing. Full article

The constitutive model is widely employed to characterize the rheological properties of metallic materials under high-temperature conditions. It is typically derived from a series of high-temperature tests conducted at varying deformation temperatures, strain rates, and strains, including hot stretching, hot compression, separated Hopkinson pressure bar testing, and hot torsion. The original experimental data used for establishing the constitutive model serves as the foundation for developing phenomenological models such as Arrhenius and Johnson–Cook models, as well as physical-based models like Zerilli–Armstrong or machine learning-based constitutive models. The resulting constitutive equations are integrated into finite element analysis software such as Abaqus, Ansys, and Deform to create custom programs that predict the distributions of stress, strain rate, and temperature in materials during processes such as cutting, stamping, forging, and others. By adhering to these methodologies, we can optimize parameters related to metal processing technology; this helps to prevent forming defects while minimizing the waste of consumables and reducing costs. This study provides a comprehensive overview of commonly utilized experimental equipment and methods for developing constitutive models. It discusses various types of constitutive models along with their modifications and applications. Additionally, it reviews recent research advancements in this field while anticipating future trends concerning the development of constitutive models for high-temperature deformation processes involving metallic materials. Full article

Surface defects of photovoltaic (PV) cells can seriously affect power generation efficiency. Accurately detecting such defects and handling them in a timely manner can effectively improve power generation efficiency. Aiming at the high-precision and real-time requirements for surface defect detection during the use of PV cells, this paper proposes a PV cell surface defect detection algorithm based on SEC-YOLOv8. The algorithm first replaces the Spatial Pyramid Pooling Fast module with the SPPELAN pooling module to reduce channel calculations between convolutions. Second, an ECA attention mechanism is added to enable the model to pay more attention to feature extraction in defect areas and avoid target detection interference from complex environments. Finally, the upsampling operator CARAFE is introduced in the Neck part to solve the problem of scale mismatch and enhance detection performance. Experimental results show that the improved model achieves a mean average precision (mAP@0.5) of 69.2% on the PV cell dataset, which is 2.6% higher than the original network, which is designed to achieve a superior balance between the competing demands of accuracy and computational efficiency for PV defect detection. Full article

The accurate detection of surface defects in bamboo is critical to maintaining product quality. Traditional inspection methods rely heavily on manual labor, making the manufacturing process labor-intensive and error-prone. To overcome these limitations, TEB-YOLO is introduced in this paper, a lightweight and efficient defect detection model based on YOLOv5s. Firstly, EfficientViT replaces the original YOLOv5s backbone, reducing the computational cost while improving feature extraction. Secondly, BiFPN is adopted in place of PANet to enhance multi-scale feature fusion and preserve detailed information. Thirdly, an Efficient Local Attention (ELA) mechanism is embedded in the backbone to strengthen local feature representation. Lastly, the original CIoU loss is replaced with EIoU loss to enhance localization precision. The proposed model achieves a precision of 91.7% with only 10.5 million parameters, marking a 5.4% accuracy improvement and a 22.9% reduction in parameters compared to YOLOv5s. Compared with other mainstream models including YOLOv5n, YOLOv7, YOLOv8n, YOLOv9t, and YOLOv9s, TEB-YOLO achieves precision improvements of 11.8%, 1.66%, 2.0%, 2.8%, and 1.1%, respectively. The experiment results show that TEB-YOLO significantly improves detection precision and model lightweighting, offering a practical and effective solution for real-time bamboo surface defect detection. Full article

Selective laser melting (SLM) offers a novel approach for manufacturing intricate structures, broadening the application of titanium alloy parts in the aerospace industry. After the build period, heat treatments of annealing (AT) and hot isostatic pressing (HIP) are often implemented, but a comparison of their mechanical performances based on the specimen orientation is still lacking. In this study, horizontally and vertically built Ti6Al4V SLM specimens that underwent the aforementioned treatments, together with their microstructural and defect characteristics, were, respectively, investigated using metallography and X-ray imaging. The mechanical properties and failure mechanism, via fracture analysis, were obtained. The critical factors influencing the mechanical properties and the correlation of the fatigue lives and failure origins were also estimated. The results demonstrate that the mechanical performances were determined by the α-phase morphology and defects, which included micropores and fewer large lack-of-fusion defects. Following the coarsening of the α phase, the strength decreased while the plasticity remained stable. With the discrepancy in the defect occurrence, anisotropy and scatter of the mechanical performances were introduced, which was significantly alleviated with HIP treatment. The fatigue failure origins were governed by defects and the α colony, which was composed of parallel α phases. Approximately linear relationships correlating fatigue lives with the X-parameter and maximum stress amplitude were, respectively, established in the AT and HIP states. The results provide an understanding of the technological significance of the evaluation of mechanical properties. Full article

This paper takes a look at training a generator model based on a limited dataset that can fit the distribution of the original dataset, improving the reconstruction ability of wafer datasets. High-fidelity wafer defect image generation remains challenging due to limited real data and poor physical authenticity of existing methods. We propose an enhanced StyleGANv3 framework with two key innovations: (1) a Heterogeneous Kernel Fusion Unit (HKFU) enabling multi-scale defect feature refinement via spatiotemporal attention and dynamic gating; (2) a Dynamic Adaptive Attention Module (DAAM) adaptively boosting discriminator sensitivity. Experiments on Mixtype-WM38 and MIR-WM811K datasets demonstrate state-of-the-art performance, achieving FID scores of 25.20 and 28.70 alongside SDS values of 36.00 and 35.45. The proposed method in this article helps alleviate the problem of limited datasets and makes an important contribution to data preparation for downstream classification and detection tasks. Full article

We provide an approach to detect a nitrogen-vacancy (NV) center, which might be a defect in a diamond nanomembrane, using a dual-coupling optomechanical system. The NV center modifies the energy-level structure of a dual-coupling optomechanical system through dressed states arising from its interaction with the mechanical membrane. Thus, we study the photon blockade in the cavity of a dual-coupling optomechanical system in which an NV center is embedded in a single-crystal diamond nanomembrane. The NV center significantly influences the statistical properties of the cavity field. We systematically investigate how three key NV center parameters affect photon blockade: (i) its coupling strength to the mechanical membrane, (ii) transition frequency, and (iii) decay rate. We find that the NV center can shift, give rise to a new dip, and even suppress the original dip in a bare quadratic optomechanical system. In addition, we can amplify the effect of the NV center on photon statistics by adding a gravitational potential when the NV center has little effect on photon blockade. Therefore, our study provides a method to detect diamond nanomembrane defects in a dual-coupling optomechanical system. Full article

The formation mechanism of black streak defects in hot-rolled steel sheets was investigated to address the influence of the process parameters on the surface quality during the production of 304 stainless steels. Macro-/microstructural characterization revealed that the defect regions contained necessary mold slag components (Ca, Si, Al, Mg, Na, K) which originated from the initial stage of solidification in the mold region of the continuous casting process, indicating obvious slag entrapment during continuous casting. On this basis, a three-dimensional coupled finite-element model for the molten steel flow–thermal characteristics was established to evaluate the effects of typical casting parameters using the determination of the critical slag entrapment velocity as the criterion. Numerical simulations demonstrated that the maximum surface velocity improved from 0.29 m/s to 0.37 m/s with a casting speed increasing from 1.0 m/min to 1.2 m/min, which intensified the meniscus turbulence. However, the increase in the port angle and the depth of the submerged entry nozzle (SEN) effectively reduced the maximum surface velocity to 0.238 m/s and 0.243 m/s, respectively, with a simultaneous improvement in the slag–steel interface temperature. Through MATLAB (version 2023b)-based reverse optimization combined with critical velocity analysis, the optimal mold slag properties were determined to be 2800 kg/m³ for the density, 4.756 × 10⁻⁶ m²/s for the kinematic viscosity, and 0.01 N/m for the interfacial tension. This systematic approach provides theoretical guidance for process optimization and slag design enhancement in industrial production. Full article

Aluminium alloy 6082 is widely used in the automotive and aerospace industries due to its high strength-to-weight ratio. However, its structural integrity can sometimes be affected by an early fatigue failure. This study investigates the fatigue performance of extruded 6082-T6 samples through a series of fatigue tests conducted at varying stress levels. The material showed significant variability under identical fatigue conditions, suggesting the presence of microstructural defects. Scanning electron microscopy with energy-dispersive spectroscopy (SEM/EDS) and scanning transmission electron microscopy (S/TEM) were used to identify the nature and location of the defects and evaluate the underlying mechanisms influencing the fatigue performance. Computer tomography (CT) also confirmed the presence of oxide inclusions on the fracture surface and near the edges of the samples. These oxide inclusions are distributed throughout the material heterogeneously and in the form of broken oxide films, suggesting that they might have originated during the material’s early processing stages. These oxides acted as stress concentrators, initiating microcracks that led to catastrophic and unpredictable early failure, ultimately reducing the fatigue life of micro-oxide-containing samples. These results highlight the need for better casting control and improved post-processing techniques to minimise the effect of oxide presence in the final components, thus enhancing their fatigue life. Full article

Detecting defects in transmission line insulators is crucial to prevent power grid failures as power systems continue to expand. This study introduces YOL011n-SSA, an enhanced insulator defect detection technique method that addresses the challenges of effectively identifying flaws in complex environments. First, this study incorporates the StarNet network into the backbone of the model. By stacking multiple layers of star operations, the model reduces both parameter count and model size, improving its adaptability to real-time object detection tasks. Secondly, the SOPN feature pyramid network is introduced into the neck part of the model. By optimizing the multi-scale feature fusion of the richer information obtained after expanding the channel dimension, the detection efficiency for low-resolution images and small objects is improved. Then, the ADown module was adopted to improve the backbone and neck parts of the model. It effectively reduces parameter count and significantly lowers the computational cost by implementing downsampling operations between different layers of the feature map, thereby enhancing the practicality of the model. Meanwhile, by introducing the NWD to improve the evaluation index of the loss function, the detection model’s capability in assessing the similarities among various small-object defects is enhanced. Experimental results were obtained using an expanded dataset based on a public dataset, incorporating three types of insulator defects under complex environmental conditions. The results demonstrate that the YOLO11n-SSA algorithm achieved an mAP@0.5 of 0.919, an mAP@0.5:0.95 of 70.7%, a precision of 0.95, and a recall of 0.875, representing improvements of 3.9%, 5.5%, 2%, and 5.7%, respectively, when compared to the original YOLO1ln method. The detection time per image is 0.0134 s. Compared to other mainstream algorithms, the YOLO11n-SSA algorithm demonstrates superior detection accuracy and real-time performance. Full article

Nero Siciliano (NS) is an autochthonous pig breed reared in northeastern Sicily; despite its high-quality meat products, NS is currently endangered. This study aimed to evaluate the genetic variability at nine loci within candidate genes for meat traits—Melanocortin 4 Receptor (MC4R), Ryanodine Receptor 1 (RYR1), Class 3 Phosphoinositide 3-Kinase (PIK3C3) and Leptin (LEP)—to provide useful information for preservation and exploitation of the NS pig breed. Distribution of the genetic variants was assessed in a representative sample of 87 pigs (18 boars and 69 sows) collected in nine farms located in the original breeding area. Genotypes have been determined using PCR-RFLP and Sanger sequencing. Alleles linked to different growth rates and back fat deposition showed high frequencies (MC4R c.175C—0.93; LEP g.3469T—0.91) in the whole sample. Deviations from Hardy–Weinberg equilibrium and different allele distribution in boars and sows were observed. The RYR1 g.1843T allele, associated with Malignant Hyperthermia and Pale Soft Exudative meat defect, was reported in seven heterozygote pigs (q = 0.04) with one farm exhibiting a frequency of 0.29. Our results suggest the need for continuous monitoring of the genetic variants in NS both to maintain high meat quality and eradicate the RYR1 g.1843T allele. Full article

With the advancement of automation in modern agriculture, the demand for intelligence in the post-picking sorting of fruits and vegetables is increasing. As a significant global agricultural product, the defect detection and sorting of tomato is essential to ensure quality and improve economic value. However, the traditional detection method (manual screening) is inefficient and involves high labor intensity. Therefore, a defect detection model named YOLO-RGDD is proposed based on YOLOv12s to identify five types of tomato surface defects (scars, gaps, white spots, spoilage, and dents). Firstly, the original C3k2 module and A2C2f module of YOLOv12 were replaced with RFEM in the backbone network to enhance feature extraction for small targets without increasing computational complexity. Secondly, the Dysample–Slim-Neck of the YOLO-RGDD was developed to reduce the computational complexity and enhance the detection of minor defects. Finally, dynamic convolution was used to replace the conventional convolution in the detection head in order to reduce the model parameter count. The experimental results show that the average precision, recall, and F1-score of the proposed YOLO-RGDD model for tomato defect detection reach 88.5%, 85.7%, and 87.0%, respectively, surpassing advanced object recognition detection algorithms. Additionally, the computational complexity of the YOLO-RGDD is 16.1 GFLOPs, which is 24.8% lower than that of the original YOLOv12s model (21.4 GFLOPs), facilitating the model’s deployment in automated agricultural production. Full article

The realization of high-precision target positioning requires the systematic suppression of nonlinear perturbations in the UAV optoelectronic system and the optimization of the cumulative deviation of coordinate transformations through error transfer modeling. This study proposes an error allocation method based on the improved raccoon optimization algorithm (KYCOA) to resolve the problem of degradation of positioning accuracy due to multi-source error coupling during UAV target positioning. Firstly, a multi-coordinate system transformation model is established to analyze the nonlinear transfer characteristics of the error, and the Taylor expansion is used to linearize the error transfer process and derive the synthetic error model under the geocentric coordinate system. Secondly, the KYCOA is proposed to optimize the error allocation by combining the good point set initialization strategy to enhance the population diversity, and the golden sine algorithm to improve the position updating mechanism in response to the defect of the traditional optimization algorithm, which easily falls into the local optimum. Simulation experiments show that the positioning error distance of the KYCOA is reduced by 66.75%, 41.89%, and 62.06% when compared with that of the original Coati Optimization Algorithm (COA), Grey Wolf Optimizer (GWO), and Whale Optimization Algorithm (WOA), respectively. In the real flight test, the target point localization error of the KYCOA is reduced by more than 40% on average when compared with that of other algorithms, which verifies the effectiveness of the proposed method in improving the target localization accuracy and robustness of UAVs. Full article

Hydrogen embrittlement (HE) can significantly degrade the mechanical properties of steels. This phenomenon is particularly relevant for high-strength steels where large elastic stresses lead to detrimental localized concentrations of hydrogen at defects. In this study, unnotched rotating bending specimens of the bearing steel SAE 52100 (100Cr6) quenched and tempered at 180 °C and 400 °C were electrochemically charged with hydrogen. Charged and non-charged specimens then underwent rotating bending fatigue testing, either immediately after charging or after aging at room temperature up to 72 h. The hydrogen-charged specimens annealed at 180 °C showed a sizeable drop in fatigue limit and fatigue lifetime compared to the non-charged specimens with cracks mainly originating from near-surface non-metallic inclusions. In comparison, the specimens annealed at 400 °C exhibited a moderate drop in fatigue limit and lifetime due to hydrogen charging with cracks originating mostly from the surface. Aging had only insignificant effects on the fatigue lifetime. Notably, annealing of charged samples for 2 h at 180 °C restored their lifetime to that of non-charged specimens. Full article