Search Results (13,956)

Aero-engine defects often exhibit micro-scale and high-frequency characteristics under complex metallic textures, which makes precise segmentation difficult. Most existing pixel-level methods rely on spatial-domain modeling and lack frequency-domain decoupling. As a result, high-frequency details are easily hidden by low-frequency background information. In addition, repeated downsampling weakens the representation of fine-grained structures, leading to inaccurate boundary localization and limited robustness. To address these issues, a spectrum-driven hierarchical learning network is proposed for aero-engine defect segmentation. First, a dual-band spectral module is constructed using the discrete cosine transform to separate high-frequency and low-frequency components, providing stable and physically meaningful frequency-domain priors for the network. Second, a detail-guided module is designed where high-frequency features adaptively guide skip connections, compensating information loss during encoding and improving boundary recovery. Furthermore, a low-frequency-driven region-aware modeling module is developed. The internal defect regions, boundary areas, and background regions are modeled hierarchically. A dynamic hyper-kernel generation mechanism performs region-sensitive convolutional modeling, improving adaptation to complex structural variations. Extensive experiments on the Turbo19 and NEU-Seg datasets demonstrate that the proposed method produces accurate defect boundaries and achieves mIoU scores of 89.82% and 91.44%, improving over the second-best method by 5.22% and 4.42%, respectively. Full article

The rapid deterioration of road infrastructure requires accurate and efficient methods for detecting pavement distresses. Unmanned Aerial Vehicles (UAVs) have emerged as a reliable alternative to conventional inspection techniques, enabling high-resolution data acquisition and improved operational safety. This study investigates the application of the Smart Oblique Capture (SOC) technique for pavement inspection through a systematic calibration of UAV flight parameters, including Ground Sample Distance (GSD), frontal and lateral overlap, camera tilt angle, and flight pattern. A structured experimental campaign was conducted, comprising 135 parameter combinations evaluated across three independent scenarios, resulting in a total of 405 UAV flights. The analysis focused on assessing the impact of these parameters on the visual quality of two-dimensional pavement reconstructions and processing efficiency. The results show that a configuration consisting of a 0.5 cm/pixel GSD, 70% frontal overlap, 80% lateral overlap, and a 70° camera tilt angle achieves the best balance between reconstruction quality and computational cost. Furthermore, the findings indicate that Smart Oblique Capture does not provide a statistically significant improvement in reconstruction quality for linear infrastructure compared to conventional oblique configurations, despite requiring a higher number of images and longer processing times. Overall, the results demonstrate that flight parameter calibration plays a more critical role than the adoption of advanced acquisition strategies such as Smart Oblique Capture. This study provides practical and reproducible guidelines for UAV-based pavement inspection, supporting efficient data acquisition while minimizing redundant information and unnecessary computational costs in infrastructure monitoring workflows. Full article

For power-grid applications such as transmission corridor inspection, substation asset inspection, and post-disaster emergency repair, reliable UAV self-localization under GNSS-degraded or GNSS-denied conditions is critical to ensuring operational safety and accurate defect geotagging. Due to substantial discrepancies in viewpoint, scale, and geometric structure between oblique UAV images and nadir satellite images, conventional RGB-based cross-view retrieval methods often suffer from unstable alignment and insufficient geometric modeling, particularly in scenarios with repetitive textures and partial overlap. To address these challenges, we propose a cross-view visual geo-localization model that integrates RGBD multimodal inputs with multi-scale attention enhancement. Specifically, MiDaS is used to estimate relative depth from UAV imagery, which is concatenated with RGB to form a four-channel input, while satellite images are padded with an additional zero channel to maintain dimensional consistency. A shared-weight ViTAdapter is adopted to learn joint semantic–geometric representations, and a lightweight Efficient Multi-scale Attention (EMA) module is adopted on spatial feature maps to strengthen multi-scale spatial consistency. In addition, an IoU-weighted InfoNCE loss is employed to accommodate partial matching during training, thereby improving the robustness of feature alignment. Experiments on the GTA-UAV dataset under the cross-area protocol show stable performance across both retrieval and localization metrics. Specifically, Recall@1, Recall@5, and Recall@10 reach 18.12%, 38.83%, and 49.47%, respectively; AP is 28.01 and SDM@3 is 0.53; meanwhile, the top-1 geodesic distance error Dis@1 is 1052.73 m. These results indicate that explicit geometric priors combined with multi-scale spatial enhancement can effectively improve cross-view feature alignment, leading to enhanced robustness and accuracy for localization in challenging power inspection scenarios. Full article

Quadrotor motion planning in cluttered environments presents significant challenges in achieving both computational efficiency and trajectory smoothness, particularly in low-altitude economy and intelligent energy system applications where autonomous aerial vehicles perform infrastructure inspection and power line monitoring. Many existing methods either rely on sampling-based algorithms that suffer from long computation times and suboptimal paths, or employ trajectory representations that produce high-order derivative discontinuities unsuitable for agile flight. In this work, we propose an efficient hierarchical motion planning framework that integrates a JPS–Bresenham-based path search with safe flight corridor construction and Bézier curve optimization. Our approach addresses trajectory generation through a two-stage process: a front-end path search that efficiently identifies collision-free paths with reduced waypoints, followed by a back-end optimization that leverages convex safe corridors with overlapping regions to expand the solution space. Through comprehensive benchmark experiments across six different map scenarios, we demonstrate that our method outperforms RRT* and PRM in both path quality and computational efficiency. Monte Carlo experiments across varying map sizes and obstacle densities confirm robustness and scalability advantages. Comparative studies with state-of-the-art planners demonstrate superior success rates and cost efficiency while maintaining strict kinodynamic feasibility. The Bézier-based optimization reduces snap integral by up to 55% compared to ordinary polynomial approaches, demonstrating its superiority for fast quadrotor trajectory planning in complex environments. Full article

Owing to the intricate mechanical coupling characteristics and the considerable difficulty in extracting synergistic spatio-temporal features from high-dimensional sensor data under fluctuating alternating loads, this study proposes a robust anomaly detection framework that combines Normalized Mutual Information (NMI) and Spatio-Temporal Graph Neural Networks (STGNN). First, NMI is utilized to quantify the nonlinear physical coupling intensity among multi-source sensors, thereby filtering out weakly correlated noise and reconstructing the spatial topological structure of the coupler system. Subsequently, a deep learning architecture incorporating Graph Convolutional Networks (GCN), Gated Recurrent Units (GRU), and one-dimensional convolutional residual connections is developed to capture the dynamic evolutionary characteristics of equipment states across both spatial interactions and temporal sequences. Finally, based on the model’s health-state predictions, a moving average algorithm is introduced to smooth the residual sequences, and an anomaly early-warning baseline is established in conjunction with the 3σ criterion. Experimental validation conducted using field service data from heavy-haul trains demonstrates that, compared to conventional serial CNN and Long Short-Term Memory (LSTM) models, the proposed method exhibits superior fitting performance and robustness against noise, effectively reducing the false alarm rate within normal working intervals. In a real-world case study, the method successfully identified variations in spatial linkage features induced by local damage and triggered timely alerts. Notably, the spatial alarm nodes were highly consistent with the fatigue crack initiation sites identified through on-site magnetic particle inspection. This study provides a viable data-driven analytical framework for the condition monitoring and anomaly identification of critical load-bearing components in heavy-haul trains. Full article

To address the challenges of multi-scale defect perception and complex background interference in railway insulator detection, this paper proposes LSD-YOLO, a lightweight multi-scale fusion network based on an improved YOLO11n. The model integrates three core modules: a Large-Small (LS) module for multi-scale receptive field fusion, a Token Statistics Self-Attention (TSSA) module for efficient global context modeling, and a Detail-Preserving Contextual Fusion (DPCF) module for adaptive multi-scale feature fusion. Experiments on a multi-defect insulator dataset constructed from 4C inspection system images and public datasets show LSD-YOLO achieves 86.2% mAP@50, 4.1 percentage points higher than the baseline model. Its precision and recall reach 91.8% and 80.6% respectively, with only 2.30 M parameters. Its comprehensive detection performance outperforms mainstream comparative models. The proposed method enhances the integrated detection ability for both physical defects and pollution-flashover faults of insulators, and provides a reference for intelligent inspection in complex railway scenarios. Full article

(1) Background: Advances in machine learning (ML)-based survival modeling enable the analysis of high-dimensional biomedical data. However, many approaches rely on the proportional hazards (PH) assumption, which is frequently violated in oncology and can limit the interpretability of hazard ratio-based results. Using Estrogen Receptor (ER) status in the METABRIC breast cancer cohort as a case study, we propose a framework that integrates machine learning survival models with Restricted Mean Survival Time (RMST) to provide a more robust and clinically interpretable approach for survival analysis under non-proportional hazards. (2) Methods: Overall survival was analyzed in 1104 patients. PH violations were confirmed using Schoenfeld residuals and Kaplan–Meier inspection. We compared four models: stratified Cox Elastic Net (Cox E-Net), Random Survival Forest (RSF), Gradient Boosting Survival Analysis (GBSA), and DeepHit. Performance was assessed using Harrell’s C-index, time-dependent IPCW C-index, and Integrated Brier Score (IBS). RMST at 180 months was utilized to quantify absolute survival differences between ER subgroups. To improve the stability of the estimates, 200 bootstrap resamples were performed, and 95% confidence intervals were derived from the bootstrap distribution. (3) ER status demonstrated significant PH violation (p < 0.005) with crossing survival curves. Discrimination (C-index 0.664–0.725) and calibration (IBS 0.149–0.169) were comparable across models, with RSF achieving the highest overall performance. Despite similar accuracy, survival curve structures differed substantially. Cox E-Net and RSF reproduced the observed crossing pattern, whereas GBSA generated smoother trajectories and DeepHit showed marked compression of subgroup separation. In the independent test cohort, the empirical RMST difference at 180 months was 16.6 months (ER-positive: 130.4; ER-negative: 113.8). Model-based RMST differences ranged from 1 month (DeepHit) to 27 months (Cox E-Net), with RSF and GBSA (12.8 and 13.8 months) most closely approximating the empirical benchmark. (4) Conclusions: We propose a novel, model-agnostic ML + RMST framework that addresses non-proportional hazards while providing quantifiable, time-specific clinical benefit. Moreover, models with similar discrimination and calibration produced markedly different survival curve behavior and absolute RMST estimates, demonstrating that accuracy metrics alone are insufficient for clinical interpretation. By linking prognostic modeling with absolute survival quantification, this framework advances survival evaluation beyond relative risk ranking toward individualized, clinically meaningful decision support. Full article

Remote sensing change detection (RSCD), a fundamental task in Earth observation, aims to automatically identify land-cover changes (e.g., building construction, vegetation degradation) by comparing multitemporal satellite or aerial images of the same region. With the explosive growth of high-resolution remote sensing data, achieving real-time accurate change detection on edge computing devices (e.g., drone-embedded chips, satellite on-board processors) has become an urgent challenge—existing deep learning methods, despite high accuracy, are hindered by massive parameters and computational costs that preclude deployment on resource-constrained embedded hardware. To address this, we focus on lightweight (i.e., low parameter count and low computational cost) RSCD network design, targeting three critical bottlenecks: blurred boundaries of changed regions, missed detection of small objects, and insufficient computational efficiency. We propose ATCFNet (Adjacent-Temporal Cross Fusion Network), featuring a three-step progressive feature optimization strategy: (1) the Adjacent Feature Aggregation Module (AFAM) enhances shallow geometric details via lateral three-stage fusion to compensate for lightweight backbones; (2) the Temporal Attention Cross Module (TACM) integrates cross-level feature propagation and Convolutional Block Attention Module (CBAM) for collaborative optimization of high-level semantics and low-level details; and (3) the Efficient Guidance Module (EGM) establishes long-range dependencies using shared change priors and lightweight self-attention to suppress internal voids in changed regions. Experiments on three public datasets (LEVIR-CD, HRCUS, SYSU-ChangeDet) demonstrate that ATCFNet achieves state-of-the-art accuracy with merely 3.71 million (M) parameters and 3.0 billion (G) floating-point operations (FLOPs)—F1-scores of 91.46%, 77.05%, and 83.53%, significantly outperforming 18 existing methods in most indicators. Notably, it excels in edge integrity (avoiding jagged blurring at change boundaries) and small-target detection in high-resolution urban scenes. This study provides an efficient and reliable lightweight solution for edge computing scenarios such as real-time drone inspection and satellite on-board intelligent processing. Full article

Industrial surface inspection is fundamental to advanced manufacturing, yet reliable robotic image acquisition in complex geometries remains challenging due to severe occlusions and the inherent trade-off between resolution and coverage. Inspired by human visual inspection behaviors and perception–action coordination mechanisms, this paper proposes a hierarchical trajectory optimization framework for robotic image acquisition based on measured point clouds. Specifically, a multi-constraint preprocessing model is developed to emulate human-like active perception strategies, enabling occlusion-aware viewpoint generation over complex concave and convex surfaces with adaptive camera orientation. Building upon this, a multi-objective trajectory optimization method is introduced to coordinate global coverage and local motion efficiency, jointly optimizing viewpoint sequencing, path length, and motion smoothness hierarchically. To further enhance flexibility in constrained environments, a Pose Reachability Augmented Generative Adversarial Network (PRAGAN) is proposed to learn feasible and adaptable imaging postures under kinematic constraints. Experimental results on an industrial robotic platform equipped with 2D and 3D vision systems demonstrate 100% coverage of key surface areas, a 47.0% reduction in path length, and a 37.5% decrease in solution time compared with the baseline in the physical experiments, while ensuring collision-free operation. Both simulation and real-world experiments validate that the proposed framework effectively captures human-inspired perception and motion coordination, providing a practical and scalable solution for complex industrial surface inspection. Full article

As global energy demand continues to grow, the inherent safety requirements for natural gas long-distance pipelines are becoming increasingly stringent. Therefore, accurately analyzing the trends in pipeline defects using multi-round internal inspection data is of great significance for enhancing pipeline inherent safety levels and reducing the risk of pipeline medium leakage. However, existing pipeline in-line inspection data alignment methods for long-distance multi-round pipeline data alignment suffer from cumbersome alignment procedures and low computational efficiency. This paper proposes an adaptive threshold dynamic time warping defect alignment method (Adaptive Dynamic Threshold-Dynamic Time Warping, ADTH-DTW) for rapidly matching multi-round in-line inspection data. A new multi-round in-line inspection data alignment framework based on valve-weld-defect is established. By integrating the DTW algorithm into each alignment stage, unnecessary manual effort is avoided, significantly improving data alignment efficiency. First, the ADTH method is used to clean redundant weld seam data in the in-line inspection data. By dynamically generating expected values and combining an intelligent point selection strategy, the method accurately identifies and removes interfering data. Additionally, valve chamber data is used to correct the overall mileage, providing a data foundation for subsequent defect alignment. Second, the dynamic time warping algorithm is used to align weld seam data and establish a data mapping table. Finally, relative displacement methods are employed to achieve defect matching. The validation results from three rounds of in-vehicle inspection data tested on-site indicate that the ADTH-DTW algorithm achieves an average 23.08% improvement in alignment accuracy compared to methods such as DTW, KL divergence, JS divergence, and linear interpolation, with computational efficiency nearly tripled. This effectively addresses the issue of incompatible computational efficiency and accuracy in existing data alignment algorithms, thereby enhancing the intrinsic safety level of natural gas long-distance pipelines. Full article

African swine fever (ASF) is a highly contagious and often fatal viral disease of pigs that poses serious economic consequences to the swine industry due to its high mortality rate and rapid spread. Currently, the identification of infectious ASF virus (ASFV) is the confirmatory test when clinical samples are positive for ASFV by any other diagnostic methods. Detection of infectious ASFV requires the availability of primary swine macrophage cultures as a cell substrate. We demonstrate here that cryopreserved swine primary macrophages are a suitable cell substrate for the detection, isolation and propagation of ASFV, showing similar results as when fresh swine macrophages are utilized. The possibility of using cryopreserved macrophages for detecting infectious ASFV would improve the efficacy of diagnostics in ensuring the availability of macrophage cell cultures during an emergency response. Full article

Planetary gear systems offer compact design and high-power density, but they are strongly influenced by transmission error (TE), which originates from geometric deviations and elastic deflections. This study presents a dynamic model that integrates elastic compliance, mesh stiffness, damping, and error excitation to evaluate coupled gear responses. Numerical results show that planet–ring contacts undergo larger forces and deflections than sun–planet meshes. Time–frequency analysis with continuous wavelet transform (CWT) reveals nonstationary vibration patterns, while gear tooth flank inspection confirms torque bias and micro-pitting. The findings connect modeling predictions with observed wear, offering insights for planetary gear diagnostics and design. Full article

To address challenges such as the sudden onset of urban fires, data synchronization delays in early warning systems, response lags, and insufficient routine monitoring, this paper proposes a Spatio-Temporal Collaborative Optimization for Joint Control and Scheduling (STCO-JCS) algorithm tailored for unmanned aerial vehicles (UAVs) and wireless sensor networks (WSNs). First, spatial autocorrelation analysis based on fire data classifies areas into ultra-high, high, medium, and low risk zones to assist in determining UAV access priorities. Second, we construct optimal inspection trajectories for the UAV by taking into account the inspection sequence and the city’s topography. By modeling the path deviations caused by wind interference and designing precision control algorithms, we improve the accuracy of the UAV’s flight path, ultimately achieving the goal of reducing UAV inspection time. Finally, by coordinating the spatiotemporal operations of drones and wireless sensor networks, we can achieve early detection and rapid response in high-risk fire zones, thereby reducing drone energy consumption while enhancing the efficiency of the UAV-WSN fire monitoring system. Simulation results demonstrate that under a 20-square-kilometer simulation area, STCO-JCS controls inspection paths within 14–17 km. In the multi-UAV scenario, the proposed method achieves approximately 3.17–9.66% improvement in energy efficiency, while in the single-UAV scenario, improvements of 10.83%, 50.54%, and 9.26% are observed in metrics. This provides effective decision support for the dynamic deployment of firefighting and rescue resources. Full article

Aircraft brake torque tubes are safety-critical components subject to combined torsional and thermal loading. As such, in aging aircraft, fatigue cracks frequently occur at the side walls of the grooves near the fillet transitions. This study presents a detailed analysis of the stress–strain state of the torque tube support section using a thermo-mechanically coupled finite element model (FEM) developed in ANSYS 2023 R2 Workbench. The model parameters are based on operational and design data provided by Röder Component Service Center Ltd. Unlike previous studies using idealized models, this approach integrates real-world non-destructive testing (NDT) evidence to identify critical areas with high stress concentrations. The model evaluates stress distributions under normal and emergency braking. Results show that the baseline 1 mm groove fillet exhibits pronounced stress peaks, correlating with observed crack initiation sites. Increasing the fillet radius to 3 mm reduces peak equivalent stress and improves the safety-factor distribution, significantly lowering crack-initiation propensity. These findings demonstrate that even minor local geometric refinements can enhance the structural robustness of torque-transmitting components. This FE–inspection integration framework offers a transferable method for reliability assessment and design improvement in aging aircraft fleets. Full article

Photovoltaic (PV) power stations are pivotal for the renewable energy transition, yet their operational efficiency is often compromised by defects such as surface dust accumulation and cracks. Traditional manual inspections are labor-intensive and subjective, while conventional monitoring methods struggle with environmental interference. This study proposes YOLO-MSG, a lightweight framework specifically designed for the automated detection of PV module defects during system operation, including normal panels as well as defective conditions such as dusty and cracked panels. The methodology integrates a Multi-Scale Grouped Convolution (MSGC) module for enhanced feature extraction and a Group-Stem Decoupled Head (GSD-Head) to reduce parameter redundancy. Furthermore, a joint optimization strategy involving LAMP and logits-based knowledge distillation is employed to facilitate edge deployment. Experimental results on a specialized PV defect dataset demonstrate that YOLO-MSG achieves a superior balance between detection accuracy and computational cost. Compared to state-of-the-art models like YOLO11 and YOLOv12, YOLO-MSG significantly reduces GFLOPs and parameter count while maintaining highly competitive mean Average Precision (mAP), with improvements of 1.35% in mAP and 2.37% in mAP50-95 over the baseline models. Specifically, the model achieves an average inference speed of 90.30 FPS on the NVIDIA Jetson AGX platform. These findings confirm the algorithm’s industrial viability, providing a robust and efficient solution for the real-time automated maintenance of photovoltaic infrastructures. Full article