Search Results (3,289)

Overhead transmission line conductors are usually helically stranded. The current-carrying section is made of aluminum and/or aluminum alloys. Several factors affect their electrical resistance, such as the conductivity of the conductor material, the cross-sectional area, the lay length of the different layers of aluminum, and the presence of a steel core used to increase the mechanical strength of the conductor. The direct current (DC) and alternating current (AC) resistances per unit length of stranded conductors are different due to the effect of the eddy currents. In steel-reinforced conductors, there are other effects, such as the transformer effect due to the magnetization of the steel core, which make the AC resistance dependent on the current. Operating temperature also has an important effect on electrical resistance. Resistive losses are the main source of heating in transmission line conductors, so their temperature rise is highly dominated by such power losses, making it critical to know the value of the AC resistance per unit length when applying dynamic line rating (DLR) methods. They are of great interest especially in congested lines, as by applying DLR approaches it is possible to utilize the full line capacity of the line. This paper highlights the difficulty of accurately calculating the electrical resistance of helically stranded conductors, especially those with a magnetic core, and the importance of accurate measurements for the development of conductor models and DLR approaches. Full article

The low-Earth-orbit satellite internet supports the transmission of multiple business types. With increasing business volume and advancements in encryption technology, the quality of service faces challenges. Traditional models lack flexibility in optimizing network performance and ensuring service quality, particularly showing poor performance in identifying encrypted traffic. Therefore, designing a model that can accurately identify multiple business scenarios as well as encrypted traffic with strong generalization capabilities is a challenging issue to resolve. In this paper, addressing the characteristics of diverse low-Earth-orbit satellite traffic and encryption, the authors propose STC-BERT (satellite traffic classification-BERT). During the pretraining phase, this model learns contextual relationships of large-scale unlabeled traffic data, while in the fine-tuning phase, it utilizes a semantic-enhancement algorithm to highlight the significance of key tokens. Post semantic enhancement, a satellite traffic feature fusion module is introduced to integrate tokens into specific low-dimensional scales and achieve final classification in fully connected layers. The experimental results demonstrate our approach’s outstanding performance compared to other models: achieving 99.31% (0.2%↑) in the USTC-TFC task, 99.49% in the ISCX-VPN task, 98.44% (0.9%↑) in the Cross-Platform task, and 98.19% (0.8%↑) in the CSTNET-TLS1.3 task. Full article

This study proposes an improved few-shot learning model of the Siamese network residual Visual Geometry Group (VGG). This model combined with time–frequency domain transformation techniques effectively enhances the performance of across-load fault diagnosis for induction motors with limited data conditions. The proposed residual VGG-based Siamese network consists of two primary components: the feature extraction network, which is the residual VGG, and the merged similarity layer. First, the residual VGG architecture utilizes residual learning to boost learning efficiency and mitigate the degradation problem typically associated with deep neural networks. The employment of smaller convolutional kernels substantially reduces the number of model parameters, expedites model convergence, and curtails overfitting. Second, the merged similarity layer incorporates multiple distance metrics for similarity measurement to enhance classification performance. For cross-domain fault diagnosis in induction motors, we developed experimental models representing four common types of faults. We measured the vibration signals from both healthy and faulty models under varying loads. We then applied the proposed model to evaluate and compare its effectiveness in cross-domain fault diagnosis against conventional AI models. Experimental results indicate that when the imbalance ratio reached 20:1, the average accuracy of the proposed residual VGG-based Siamese network for fault diagnosis across different loads was 98%, closely matching the accuracy of balanced and sufficient datasets, and significantly surpassing the diagnostic performance of other models. Full article

Optimization of land management and agricultural practices require precise classification of soil properties. This study presents a method to fine-tune deep neural network (DNN) hyperparameters for multiclass classification of soil properties using genetic algorithms (GAs) with knowledge-based generation of hyperparameters. The focus is on classifying soil attributes, including nutrient availability (0.78 ± 0.11), nutrient retention capacity (0.86 ± 0.05), rooting conditions (0.85 ± 0.07), oxygen availability to roots (0.84 ± 0.05), excess salts (0.96 ± 0.02), toxicity (0.96 ± 0.01), and soil workability (0.84 ± 0.09), with these accuracies representing the results from classification with variations from cross-validation. A dataset from the USA, which includes land-use distribution, aspect distribution, slope distribution, and climate data for each plot, is utilized. A GA is applied to explore a wide range of hyperparameters, such as the number of layers, neurons per layer, activation functions, optimizers, learning rates, and loss functions. Additionally, ensemble methods such as random forest and gradient boosting machines were employed, demonstrating comparable accuracy to the DNN approach. This research contributes to the advancement of precision agriculture by providing a robust machine learning (ML) framework for accurate soil property classification. By enabling more informed and efficient land management decisions, it promotes sustainable agricultural practices that optimize resource use and enhance soil health for long-term ecological balance. Full article

The flow of water through a channel with a heterogeneous porous layer in its central core is simulated using the method of Smoothed-Particle Hydrodynamics (SPH). Three different porous substrates are considered that differ in the geometry of their grain arrays. The heterogeneity is modeled by dividing the porous substrate into four zones that each have a different porosity. The pressure loss and the flow across the channel are simulated at two different scales, the pore scale and the Representative Elementary Volume (REV) scale, based on use of the Ergun equation. Since the computational cost at the REV scale is much lower than at the pore scale, it is therefore important to assess how accurately the REV-scale calculation reproduces the pore-scale results. The REV-scale simulation predicts cross-sectional mainstream velocity profiles and head losses through the channel that differ from the pore-scale results by root-mean-square errors of about 0.01% and 0.3%, respectively. Full article

In saline soil areas, the concrete piers of concrete bridges experience long-term corrosion, mainly caused by chloride salts due to alternating temperature changes. Waterborne concrete coatings are prone to failure in this aggressive salt environment. Implementing coating protection measures can improve the durability of concrete and enhance the service life of bridges. However, the effectiveness and longevity of coatings need further research. In this paper, three types of waterborne concrete anti-corrosion coatings were applied to analyze the macro and micro surface morphology under wet–dry cycles and long-term immersion conditions. Various indicators such as glossiness, color difference, and adhesion of the coatings were tested during different cyclic periods. The chloride ion distribution characteristics of the buried concrete coatings in saline soil, the macro morphology analysis of chloride ion distribution regions, and the micro morphology changes of the coatings under different corrosion times were also investigated. The results showed that waterborne epoxy coatings (ES), waterborne fluorocarbon coatings (FS), and waterborne acrylic coatings (AS) all gradually failed under long-term salt exposure, with increasing coating porosity, loss of internal fillers, and delamination. The chloride ion content inside the concrete decreased with increasing depth at the same corrosion time, while the chloride ion content at the same depth increased with time. The chloride ion distribution boundary in the cross-section of concrete with coating protection was not significant, while the chloride ion distribution boundary in the cross-section of untreated concrete gradually contracted towards the concrete core with increasing corrosion time. During the corrosion process in saline soil, the coatings underwent three stages: adherence of small saline soil particles, continuous increase in adhered material area, and multiple layers of uneven coverage by saline soil. The failure process of the coatings still required erosive ions to infiltrate the surface through micropores. The predicted lifespans of FS, ES, and AS coatings, obtained through weighted methods, were 2.45 years, 2.48 years, and 2.74 years, respectively, which were close to the actual lifespans observed in salt environments. The developed formulas effectively reflect the corrosion patterns of different resin-based coatings under salt exposure, providing a basis for accurately assessing the corrosion behavior and protective effectiveness of concrete under actual environmental factors. Full article

In this paper, we propose a lightweight lithography machine learning-based hotspot detection model that integrates the Squeeze-and-Excitation (SE) attention mechanism and the Efficient Channel Attention (ECA) mechanism. These mechanisms can adaptively adjust channel weights, significantly enhancing the model’s ability to extract relevant features of hotspots and non-hotspots through cross-channel interaction without dimensionality reduction. Our model extracts feature vectors through seven convolutional layers and four pooling layers, followed by three fully connected layers that map to the output, thereby simplifying the CNN network structure. Experimental results on our collected layout dataset and the ICCAD 2012 layout dataset demonstrate that our model is more lightweight. By evaluating overall accuracy, recall, and runtime, the comprehensive performance of our model is shown to exceed that of ConvNeXt, Swin transformer, and ResNet 50. Full article

In the evolving field of artificial intelligence, fine-tuning diffusion models is crucial for generating contextually coherent digital characters across various media. This paper examines four advanced fine-tuning techniques: Low-Rank Adaptation (LoRA), DreamBooth, Hypernetworks, and Textual Inversion. Each technique enhances the specificity and consistency of character generation, expanding the applications of diffusion models in digital content creation. LoRA efficiently adapts models to new tasks with minimal adjustments, making it ideal for environments with limited computational resources. It excels in low VRAM contexts due to its targeted fine-tuning of low-rank matrices within cross-attention layers, enabling faster training and efficient parameter tweaking. DreamBooth generates highly detailed, subject-specific images but is computationally intensive and suited for robust hardware environments. Hypernetworks introduce auxiliary networks that dynamically adjust the model’s behavior, allowing for flexibility during inference and on-the-fly model switching. This adaptability, however, can result in slightly lower image quality. Textual Inversion embeds new concepts directly into the model’s embedding space, allowing for rapid adaptation to novel styles or concepts, but is less effective for precise character generation. This analysis shows that LoRA is the most efficient for producing high-quality outputs with minimal computational overhead. In contrast, DreamBooth excels in high-fidelity images at the cost of longer training. Hypernetworks provide adaptability with some tradeoffs in quality, while Textual Inversion serves as a lightweight option for style integration. These techniques collectively enhance the creative capabilities of diffusion models, delivering high-quality, contextually relevant outputs. Full article

Ancient paintings, as a vital component of cultural heritage, encapsulate a profound depth of cultural significance. Over time, they often suffer from different degradation conditions, leading to damage. Existing ancient painting inpainting methods struggle with semantic discontinuities, blurred textures, and details in missing areas. To address these issues, this paper proposes a generative adversarial network (GAN)-based ancient painting inpainting method named RG-GAN. Firstly, to address the inconsistency between the styles of missing and non-missing areas, this paper proposes a Regional Attention-Style Transfer Module (RASTM) to achieve complex style transfer while maintaining the authenticity of the content. Meanwhile, a multi-scale fusion generator (MFG) is proposed to use the multi-scale residual downsampling module to reduce the size of the feature map and effectively extract and integrate the features of different scales. Secondly, a multi-scale fusion mechanism leverages the Multi-scale Cross-layer Perception Module (MCPM) to enhance feature representation of filled areas to solve the semantic incoherence of the missing region of the image. Finally, the Global Context Perception Discriminator (GCPD) is proposed for the deficiencies in capturing detailed information, which enhances the information interaction across dimensions and improves the discriminator’s ability to identify specific spatial areas and extract critical detail information. Experiments on the ancient painting and ancient Huaniao++ datasets demonstrate that our method achieves the highest PSNR values of 34.62 and 23.46 and the lowest LPIPS values of 0.0507 and 0.0938, respectively. Full article

Spherical quantum wells (SQWs) have proven to be excellent materials for suppressing Auger recombination due to their expanded confinement volume. However, research on the factors and mechanisms of their high-intensity optical properties, such as multiexciton properties and third-order optical nonlinearities, remains incomplete, limiting further optimization of these properties. Here, a series of CdS/CdSe (xML)/CdS SQWs with varying CdSe layer thicknesses were prepared. The modulation effects of CdSe shell variations on the PL properties, defect distribution, biexciton binding energy, and third-order optical nonlinearities of the SQWs were investigated, and their impact on the material’s multiexciton properties was further analyzed. Results showed that the typical CdS/CdSe(3ML)/CdS sample exhibited a large volume-normalized two-photon absorption cross-section (18.17 × 10² GM/nm³) and favorable biexciton characteristics. Optical amplification was observed at 12.4 μJ/cm² and 1.02 mJ/cm² under one-photon (400 nm) and two-photon (800 nm) excitation, respectively. Furthermore, different amplified spontaneous emission spectra were observed for the first time under one/two-photon excitation. This phenomenon was attributed to thermal effects overcoming the biexciton binding energy. This study provides valuable insights for further optimizing multiexciton gain characteristics in SQWs and developing optical gain applications. Full article

China’s Yunnan Province, known for its tea plantations, faces significant challenges in smart pest management due to its ecologically intricate environment. To enable the intelligent monitoring of pests within tea plantations, this study introduces a novel image recognition algorithm, designated as YOLOv8n-WSE-pest. Taking into account the pest image data collected from organic tea gardens in Yunnan, this study utilizes the YOLOv8n network as a foundation and optimizes the original loss function using WIoU-v3 to achieve dynamic gradient allocation and improve the prediction accuracy. The addition of the Spatial and Channel Reconstruction Convolution structure in the Backbone layer reduces redundant spatial and channel features, thereby reducing the model’s complexity. The integration of the Efficient Multi-Scale Attention Module with Cross-Spatial Learning enables the model to have more flexible global attention. The research results demonstrate that compared to the original YOLOv8n model, the improved YOLOv8n-WSE-pest model shows increases in the precision, recall, mAP50, and F1 score by 3.12%, 5.65%, 2.18%, and 4.43%, respectively. In external validation, the mAP of the model outperforms other deep learning networks such as Faster-RCNN, SSD, and the original YOLOv8n, with improvements of 14.34%, 8.85%, and 2.18%, respectively. In summary, the intelligent tea garden pest identification model proposed in this study excels at precise the detection of key pests in tea plantations, enhancing the efficiency and accuracy of pest management through the application of advanced techniques in applied science. Full article

In recent years, new media have exacerbated the complexity of online public opinion scenarios through fragmentation of information, diversification of public opinion, rapid diffusion of public opinion, and concealment of information sources, which have posed several serious challenges to the benign development of online public opinion ecosystems. Therefore, based on diversified public opinion scenarios, we study the interaction between information dissemination and the evolution of group opinions and the dissemination laws to solve the problem of imprecise grasping of the dissemination laws in complex public opinion scenarios. Facing the two-way interaction between online platforms and real society, we constructed a coupled online–offline viewpoint evolution dynamics model, which considers factors such as the user subject level and the network environment level, and combines viewpoint dynamics theory with information dissemination dynamics theory. Based on the real case of dual interaction between online and offline, we carry out the construction of a two-layer coupling network and numerical fitting comparison experiments to study the synergistic and penetration mechanism of public opinion in both online and offline multi-spaces. Based on parametric analysis experiments, the influence of different factors on communication indicators is mined, and the driving effect of the viewpoint environment of offline communication on online public opinion is studied, which reveals the objective role of multi-factors on the law of intralayer communication, cross-network communication, and viewpoint evolution, and provides strategic suggestions for the comprehensive management of public opinion in online–offline large-scale mass incidents. Full article

The growing demand for stealth technology in military and aerospace applications has driven the development of advanced radar-absorbing structures. In particular, honeycomb absorbing structures (HASs) have shown promise due to their unique properties. In order to enhance the absorption characteristics of HASs and evaluate its application effect on aircraft, firstly, the mechanism of enhancing the electromagnetic (EM) absorption capacity of honeycomb structures by using a gradient design for the impregnation material is studied. Secondly, a multi-layer gradient honeycomb absorbing structure (MGHAS) with top skin and intermediate bonding layers is proposed. The influence of the type and arrangement of impregnation materials on reflectivity is analyzed to obtain design strategies that can enhance the absorption performance of the MGHAS. An improved particle swarm optimization (PSO) algorithm is proposed to optimize the EM absorption performance of the MGHAS. The optimized MGHAS achieves broadband absorption below −10 dB in a 2–18 GHz range, and the reflectivity even reaches −30 dB near 10 GHz. Finally, to solve the problem of electromagnetic scattering characteristics of periodic structures, such as HASs applied to electrically large targets, reflectivity is introduced into a shooting and bouncing ray method, which is a high-frequency algorithm used to analyze the electromagnetic scattering characteristics of the aircraft inlet. Based on this method, the reduction effect of the MGHAS on the radar cross section (RCS) of the aircraft inlet is explored. The results indicate that at the detection angle at 0° and detection frequency at 10 GHz, an aircraft inlet equipped with the MGHAS achieves a 26 dB reduction in the RCS compared with an aircraft inlet without stealth technologies and an 18 dB reduction compared with an inlet with coating-type absorbing material in TM mode. This study demonstrates that the proposed MGHAS effectively reduces the electromagnetic scattering intensity of the aircraft inlet and enhances the radar stealth performance of the aircraft. Full article

Two-dimensional human pose estimation aims to equip computers with the ability to accurately recognize human keypoints and comprehend their spatial contexts within media content. However, the accuracy of real-time human pose estimation diminishes when processing images with occluded body parts or overlapped individuals. To address these issues, we propose a method based on the YOLO framework. We integrate the convolutional concepts of Kolmogorov–Arnold Networks (KANs) through introducing non-linear activation functions to enhance the feature extraction capabilities of the convolutional kernels. Moreover, to improve the detection of small target keypoints, we integrate the cross-stage partial (CSP) approach and utilize the small object enhance pyramid (SOEP) module for feature integration. We also innovatively incorporate a layered shared convolution with batch normalization detection head (LSCB), consisting of multiple shared convolutional layers and batch normalization layers, to enable cross-stage feature fusion and address the low utilization of model parameters. Given the structure and purpose of the proposed model, we name it KSL-POSE. Compared to the baseline model YOLOv8l-POSE, KSL-POSE achieves significant improvements, increasing the average detection accuracy by 1.5% on the public MS COCO 2017 data set. Furthermore, the model also demonstrates competitive performance on the CrowdPOSE data set, thus validating its generalization ability. Full article

As a new type of pile, the bearing characteristics of stepped variable-section DX piles (multi-joint extruded and expanded piles) are quite complicated; thus, their design concepts and pile-forming processes are still in the exploration stage, and their application in actual engineering is not particularly mature. The settlement law and load transfer law of the variable section DX pile have not been studied deeply, and the values of the parameters of engineering design are not clear, which are the problems to be solved for the variable section DX pile. To solve the above problems, the present study on the bearing characteristics of stepped variable-section DX piles under vertical loading is of great scientific significance and engineering practical value. In this study, the bearing capacity of a DX pile with two variable steps was first analyzed experimentally. Then, the bearing capacity of variable cross-section DX piles and equal cross-section piles were simulated under the same soil conditions. Later, the numerical simulation results were compared with the experimental results to verify the validity and accuracy of the numerical models established in ABAQUS software. Finally, the bearing capacity of stepped variable-section DX piles in different soil layers was analyzed numerically to compare the effect of different soils on the compressive bearing capacity of piles. The results indicated that the load-bearing plates had a greater influence on the bearing capacity of the stepped variable-section DX piles. At the optimum variable section ratio, which was close to 0.9, DX piles had a good bearing capacity. The relative errors of the numerical simulation ultimate loads were below 10%, which verified the accuracy of the developed numerical model. The simulated ultimate load of the equal-section pile was the smallest. The vertical compressive bearing capacity and the effect of controlling settlement under the same level of load of the variable section DX pile in sandy soil were both better than those in silt soil. There was little difference between the bearing capacities of the piles with a load-bearing plate. The bearing capacity of the pile with two load-bearing plates was the best, which can be used in practical engineering. Full article