Search Results (6,839)

As highway tunnel operations continue over time, structural defects, particularly cracks, have been observed to increase annually. Coupled with the rapid expansion of tunnel networks, traditional manual inspection methods have proven inadequate to meet current demands. In recent years, machine vision and deep learning technologies have gained significant attention in civil engineering for the detection and analysis of structural defects. However, rapid and accurate defect identification in highway tunnels presents challenges due to complex background conditions, numerous interfering factors, and the relatively low proportion of cracks within the structure. Additionally, the intensive labor requirements and limited efficiency in labeling training datasets for deep learning pose significant constraints on the deployment of intelligent crack segmentation algorithms. To address these limitations, this study proposes an automatic labeling and optimization algorithm for crack sample sets, utilizing crack features and the watershed algorithm to enable efficient automated segmentation with minimal human input. Furthermore, the deep learning-based crack segmentation network was optimized through comparative analysis of various network depths and residual structure configurations to achieve the best possible model performance. Enhanced accuracy was attained by incorporating axis extraction and watershed filling algorithms to refine segmentation outcomes. Under diverse lining surface conditions and multiple interference factors, the proposed approach achieved a crack segmentation accuracy of 98.78%, with an Intersection over Union (IoU) of 72.41%, providing a robust solution for crack segmentation in tunnels with complex backgrounds. Full article

High energy density technologies for welding processes provide opportune solutions to joint metal materials and repair components in several industrial applications. Their high-performance levels are related to the high penetration depth and welding speed achievable. Moreover, the localized thermal input helps in reducing distortion and residual stresses in the welds, minimizing the extension of the fusion zone and heat-affected zone. The use of these welding technologies can be decisive in the employment of sophisticated alloys such as Ni-based superalloys, which are notoriously excellent candidates for industrial components subjected to high temperatures and corrosive work conditions. Nonetheless, the peculiar crystallographic and chemical complexity of Ni-based superalloys (whether characterized by polycrystalline, directionally solidified, or single-crystal microstructure) leads to high susceptibility to welding processes and, in general, challenging issues related to the microstructural features of the welded joints. The present review highlights the advantages and drawbacks of high energy density (Laser Beam and Electron Beam) welding techniques applied to Ni-based superalloy. The effects of process parameters on cracking susceptibility have been analyzed to better understand the correlation between them and the microstructure-mechanical properties of the welds. The weldability of three different polycrystalline Ni superalloys, one solid solution-strengthened alloy, Inconel 625, and two precipitation-strengthen alloys, Nimonic 263 and Inconel 718, is reviewed in detail. In addition, a variant of the latter, the AF955 alloy, is also presented for its great potential in terms of weldability. Full article

Lane detection is a pivotal technology of the intelligent driving system. By identifying the position and shape of the lane, the vehicle can stay in the correct lane and avoid accidents. Image-based deep learning is currently the most advanced method for lane detection. Models using this method already have a very good recognition ability in general daytime scenes, and can almost achieve real-time detection. However, these models often fail to accurately identify lanes in challenging scenarios such as night, dazzle, or shadows. Furthermore, the lack of diversity in the training data restricts the capacity of the models to handle different environments. This paper proposes a novel method to train CycleGAN with existing daytime and nighttime datasets. This method can extract features of different styles and multi-scales, thereby increasing the richness of model input. We use CycleGAN as a domain adaptation model combined with an image segmentation model to boost the model’s performance in different styles of scenes. The proposed consistent loss function is employed to mitigate performance disparities of the model in different scenarios. Experimental results indicate that our method enhances the detection performance of original lane detection models in challenging scenarios. This research helps improve the dependability and robustness of intelligent driving systems, ultimately making roads safer and enhancing the driving experience. Full article

Due to the unique imaging mechanism of SAR, targets in SAR images present complex scattering characteristics. As a result, intelligent target detection in SAR images has been facing many challenges, which mainly lie in the insufficient exploitation of target characteristics, inefficient characterization of scattering features, and inadequate reliability of decision models. In this respect, we propose an intelligent target detection method based on multi-level fusion, where pixel-level, feature-level, and decision-level fusions are designed for enhancing scattering feature mining and improving the reliability of decision making. The pixel-level fusion method through the channel fusion of original images and their features after scattering feature enhancement represents an initial exploration of image fusion. Two feature-level fusion methods are conducted using respective migratable fusion blocks, namely DBAM and FDRM, presenting higher-level fusion. Decision-level fusion based on DST can not only consolidate complementary strengths in different models but also incorporate human or expert involvement in proposition for guiding effective decision making. This represents the highest-level fusion integrating results by proposition setting and statistical analysis. Experiments of different fusion methods integrating different features were conducted on typical target detection datasets. As shown in the results, the proposed method increases the mAP by 16.52%, 7.1%, and 3.19% in ship, aircraft, and vehicle target detection, demonstrating high effectiveness and robustness. Full article

This paper aims to address the challenges of significant data distribution differences and extreme data imbalances in the remaining useful life prediction modeling of rotating components of complex intelligent equipment under various working conditions. Grounded in deep learning modeling, it considers the multi-dimensional extraction method for degraded data features in the data feature extraction stage, proposes a network structure with multiple attention data extraction channels, and explores the extraction method for valuable data segments in the channel and time series dimensions. This paper also proposes a domain feature fusion network based on feature migration and examines methods that leverage abundant labeled data from the source domain to assist in target domain learning. Finally, in combination with a long short-term memory neural network (LSTM), this paper constructs an intelligent model to estimate the remaining lifespan of rotating components. Experiments demonstrate that, when integrating the foundational deep convolution network with the domain feature fusion network, the comprehensive loss error for life prediction on the target domain test set can be reduced by up to 6.63%. Furthermore, when adding the dual attention feature extraction network, the maximum reduction in the comprehensive loss error is 3.22%. This model can effectively enhance the precision of life prediction in various operating conditions; thus, it provides a certain theoretical basis and technical support for the operation and maintenance management of complex intelligent equipment. It has certain practical value and application prospects in the remaining life prediction of rotating components under multiple working conditions. Full article

To address the challenges associated with lightweight design and small object detection in infrared imaging for substation electrical equipment, this paper introduces an enhanced YOLOv8_Adv network model. This model builds on YOLOv8 through several strategic improvements. The backbone network incorporates PConv and FasterNet modules to substantially reduce the computational load and memory usage, thereby achieving model lightweighting. In the neck layer, GSConv and VoVGSCSP modules are utilized for multi-stage, multi-feature map fusion, complemented by the integration of the EMA attention mechanism to improve feature extraction. Additionally, a specialized detection layer for small objects is added to the head of the network, enhancing the model’s performance in detecting small infrared targets. Experimental results demonstrate that YOLOv8_Adv achieves a 4.1% increase in [email protected] compared to the baseline YOLOv8n. It also outperforms five existing baseline models, with the highest accuracy of 98.7%, and it reduces the computational complexity by 18.5%, thereby validating the effectiveness of the YOLOv8_Adv model. Furthermore, the effectiveness of the model in detecting small targets in infrared images makes it suitable for use in areas such as infrared surveillance, military target detection, and wildlife monitoring. Full article

Autonomous Underwater Vehicles (AUVs) operate independently using onboard batteries and data storage, necessitating periodic recovery for battery recharging and data transfer. Traditional surface-based launch and recovery (L&R) operations pose significant risks to personnel and equipment, particularly in adverse weather conditions. Subsurface docking stations provide a safer alternative but often involve complex fixed installations and costly acoustic positioning systems.This work introduces a comprehensive docking solution featuring the following two key innovations: (1) a novel deployable docking station (DDS) designed for rapid deployment from vessels of opportunity, operating without active acoustic transmitters; and (2) an innovative sensor fusion approach that combines the AUV’s onboard forward-looking sonar and camera data. The DDS comprises a semi-submersible protective frame and a subsurface, heave-compensated docking component equipped with backlit visual markers, an electromagnetic (EM) beacon, and an EM lifting device. This adaptable design is suitable for temporary installations and in acoustically sensitive or covert operations.The positioning and guidance system employs a multi-sensor approach, integrating range and azimuth data from the sonar with elevation data from the vision camera to achieve precise 3D positioning and robust navigation in varying underwater conditions. This paper details the design considerations and integration of the AUV system and the docking station, highlighting their innovative features.The proposed method was validated through software-in-the-loop simulations, controlled seawater pool experiments, and preliminary open-sea trials, including several docking attempts. While further sea trials are planned, current results demonstrate the potential of this solution to enhance AUV operational capabilities in challenging underwater environments while reducing deployment complexity and operational costs. Full article

Screen defect detection has become a crucial research domain, propelled by the growing necessity of precise and effective quality control in mobile device production. This study presents the FusionScratchNet (FS-Net), a novel algorithm developed to overcome the challenges of noise interference and to characterize indistinct defects and subtle scratches on mobile phone screens. By integrating the transformer and convolutional neural network (CNN) architectures, FS-Net effectively captures both global and local features, thereby enhancing feature representation. The global–local feature integrator (GLFI) module effectively fuses global and local information through unique channel splitting, feature dependency characterization, and attention mechanisms, thereby enhancing target features and suppressing noise. The bridge attention (BA) module calculates an attention feature map based on the multi-layer fused features, precisely focusing on scratch characteristics and recovering details lost during downsampling. Evaluations using the PKU-Market-Phone dataset demonstrated an overall accuracy of 98.04%, an extended intersection over union (EIoU) of 88.03%, and an F1-score of 65.13%. In comparison to established methods like you only look once (YOLO) and retina network (RetinaNet), FS-Net demonstrated enhanced detection accuracy, computational efficiency, and resilience against noise. The experimental results demonstrated that the proposed method effectively enhances the accuracy of scratch segmentation. Full article

The most effective way to solve urban traffic congestion in mega cities is to develop rail transit, which is also an important strategy for sustainable urban development. Improving the service performance of rail transit equipment is the key to ensuring the sustainable operation of urban rail transit. Automatic fare collection (AFC) is an indispensable system in urban rail transit. AFC directly serves passengers, and its condition directly affects the sustainability and safety of urban rail transit. This study proposes remaining useful life (RUL) prediction framework for AFC systems. Firstly, it proposes the quantification of AFC health state based on health degree, and proposes a health state assessment method based on digital analog fusion, which compensates for the shortcomings of single data-driven or model driven health methods. Secondly, it constructs a multi feature extraction method based on multi-layer LSTM, which can capture long-term temporal dependencies and multi-dimensional feature, overcoming the limitation of low model accuracy because of the weak data features. Then, the SSA-XGBoost model for AFC RUL prediction is proposed, which effectively performs global and local searches, reduces the possibility of overfitting, and improves the accuracy of the prediction model. Finally, we put it into practice of the AFC system of Shanghai Metro Line 10. The experiment shows that the proposed model has an MSE of 0.00111 and MAE of 0.02869 on the test set, while on the validation set, MSE is 0.00004 and MAE is 0.00659. These indicators are significantly better than other comparative models such as XGBoost, random forest regression, and linear regression. In addition, the SSA-XGBoost model also performs well on R-squared, further verifying its effectiveness in prediction accuracy and model fitting. Full article

Three-dimensional (3D) reconstruction of high-dynamic-range (HDR) surfaces plays an important role in the fields of computer vision and image processing. Traditional 3D measurement methods often face the risk of information loss when dealing with surfaces that have HDR characteristics. To address this issue, this paper proposes a simple 3D reconstruction method, which combines the features of non-overexposed regions in polarized and unpolarized images to improve the reconstruction quality of HDR surface objects. The optimum fringe regions are extracted from images with different polarization angles, and the non-overexposed regions in normally captured unpolarized images typically contain complete fringe information and are less affected by specular highlights. The optimal fringe information from different polarized image groups is gradually used to replace the incorrect fringe information in the unpolarized image, resulting in a complete set of fringe data. Experimental results show that the proposed method requires only 24~36 images and simple phase fusion to achieve successful 3D reconstruction. It can effectively mitigate the negative impact of overexposed regions on absolute phase calculation and 3D reconstruction when reconstructing objects with strongly reflective surfaces. Full article

Semantic segmentation of three-dimensional (3D) plant point clouds at the stem-leaf level is foundational and indispensable for high-throughput tomato phenotyping systems. However, existing semantic segmentation methods often suffer from issues such as low precision and slow inference speed. To address these challenges, we propose an innovative encoding-decoding structure, incorporating voxel sparse convolution (SpConv) and attention-based feature fusion (VSCAFF) to enhance semantic segmentation of the point clouds of high-resolution tomato seedling images. Tomato seedling point clouds from the Pheno4D dataset labeled into semantic classes of ‘leaf’, ‘stem’, and ‘soil’ are applied for the semantic segmentation. In order to reduce the number of parameters so as to further improve the inference speed, the SpConv module is designed to function through the residual concatenation of the skeleton convolution kernel and the regular convolution kernel. The feature fusion module based on the attention mechanism is designed by giving the corresponding attention weights to the voxel diffusion features and the point features in order to avoid the ambiguity of points with different semantics having the same characteristics caused by the diffusion module, in addition to suppressing noise. Finally, to solve model training class bias caused by the uneven distribution of point cloud classes, the composite loss function of Lovász-Softmax and weighted cross-entropy is introduced to supervise the model training and improve its performance. The results show that mIoU of VSCAFF is 86.96%, which outperformed the performance of PointNet, PointNet++, and DGCNN, respectively. IoU of VSCAFF achieves 99.63% in the soil class, 64.47% in the stem class, and 96.72% in the leaf class. The time delay of 35ms in inference speed is better than PointNet++ and DGCNN. The results demonstrate that VSCAFF has high performance and inference speed for semantic segmentation of high-resolution tomato point clouds, and can provide technical support for the high-throughput automatic phenotypic analysis of tomato plants. Full article

In the complex environment of fully mechanized mining faces, the current object detection algorithms face significant challenges in achieving optimal accuracy and real-time detection of mine personnel and safety helmets. This difficulty arises from factors such as uneven lighting conditions and equipment obstructions, which often lead to missed detections. Consequently, these limitations pose a considerable challenge to effective mine safety management. This article presents an enhanced algorithm based on YOLOv11n, referred to as GCB-YOLOv11. The proposed improvements are realized through three key aspects: Firstly, the traditional convolution is replaced with GSConv, which significantly enhances feature extraction capabilities while simultaneously reducing computational costs. Secondly, a novel C3K2_FE module was designed that integrates Faster_block and ECA attention mechanisms. This design aims to improve detection accuracy while also accelerating detection speed. Finally, the introduction of the Bi FPN mechanism in the Neck section optimizes the efficiency of multi-scale feature fusion and addresses issues related to feature loss and redundancy. The experimental results demonstrate that GCB-YOLOv11 exhibits strong performance on the dataset concerning mine personnel and safety helmets, achieving a mean average precision of 93.6%. Additionally, the frames per second reached 90.3 f·s⁻¹, representing increases of 3.3% and 9.4%, respectively, compared to the baseline model. In addition, when compared to models such as YOLOv5s, YOLOv8s, YOLOv3 Tiny, Fast R-CNN, and RT-DETR, GCB-YOLOv11 demonstrates superior performance in both detection accuracy and model complexity. This highlights its advantages in mining environments and offers a viable technical solution for enhancing the safety of mine personnel. Full article

Amidst the dual challenges of energy shortages and global warming, photovoltaic (PV) power generation has emerged as a critical technology due to its efficient utilization of solar energy. Rooftops, as underutilized spaces, are ideal locations for installing solar panels, avoiding the need for additional land. However, the accurate and generalized segmentation of large-scale PV panel images remains a technical challenge, primarily due to varying image resolutions, large image scales, and the significant imbalance between foreground and background categories. To address these challenges, this paper proposes a novel model based on the Res2Net architecture, an enhanced version of the classic ResNet optimized for multi-scale feature extraction. The model integrates Spatial Feature Reconstruction and multi-scale feature aggregation modules, enabling effective extraction of multi-scale data features and precise reconstruction of spatial features. These improvements are particularly designed to handle the small proportion of PV panels in images, effectively distinguishing target features from redundant ones and improving recognition accuracy. Comparative experiments conducted on a publicly available rooftop PV dataset demonstrate that the proposed method achieves superior performance compared to mainstream techniques, showcasing its effectiveness in precise PV panel segmentation. Full article

In seismic exploration, establishing a reliable parameter model (such as velocity, density, impedance) is crucial for seismic migration imaging and reservoir characterization. The interpolation of well data to obtain a complete spatial model is an important aspect of parameter modeling. However, in practical applications, well data are often sparse and irregularly distributed, which complicates the accurate construction of subsurface parameter models. The Kriging method is an effective interpolation method based on discrete well data, but its theoretical assumptions do not meet the practical requirements in seismic exploration, resulting in low modeling accuracy. This article introduces seismic facies information into the Kriging method and proposes a novel parameter modeling method named the facies-constrained Kriging (FC-Kriging) method. The FC-Kriging method modifies the Euclidean distance metric used in Kriging so that the distance between two points depends not only on their spatial coordinates but also on their associated facies categories. The proposed method is a multi-information fusion method that integrates facies information based on well data, enabling good interpolation results even with a limited number of wells. The parameter modeling results based on the FC-Kriging method are more consistent with geological logic, exhibiting clearer boundary features and higher resolution. Furthermore, the FC-Kriging method does not introduce additional computational complexity, making it convenient to implement in a 3D situation. The FC-Kriging method is applied to the 2D Sigsbee model, the 3D Standford V reservoir model and F3 block field data. The results demonstrate its accuracy and effectiveness. Full article

The prediction of ocean ambient noise is crucial for protecting the marine ecosystem and ensuring communication and navigation safety, especially under extreme weather conditions such as typhoons and strong winds. Ocean ambient noise is primarily caused by ship activities, wind waves, and other factors, and its complexity makes it a significant challenge to effectively utilize limited data to observe future changes in noise energy. To address this issue, we have designed a multi-modal linear model based on a “decomposition-prediction-modal trend fusion-total fusion” framework. This model simultaneously decomposes wind speed data and ocean ambient noise data into trend and residual components, enabling the wind speed information to effectively extract key trend features of ocean ambient noise. Compared to polynomial fitting methods, single-modal models, and LSTM multi-modal models, the average error of the relative sound pressure level was reduced by 1.3 dB, 0.5 dB, and 0.3 dB, respectively. Our approach demonstrates significant improvements in predicting future trends and detailed fittings of the data. Full article