Search Results (983)

This data descriptor provides a standardized and reproducible subsystem-level representation of the NREL wind turbine gearbox condition monitoring benchmarking dataset. The released records are derived from Healthy (H1–H10) and Damaged (D1–D10) measurement files and include subsystem-level standardized indices (KHI_HS, KHI_IMS, KHI_PL) together with a calibrated 0–1 Gearbox Health Index (GHI). The indices are generated using a fully specified and deterministic feature extraction and aggregation workflow based on established vibration indicators and healthy-referenced normalization. The Zenodo deposit contains machine-readable CSV tables intended to support transparent benchmarking across supervised classification and anomaly detection studies. The proposed GHI is introduced as an interpretable and reproducible reference baseline rather than an optimized diagnostic model. Technical validation demonstrates condition-level separability within the analyzed dataset while emphasizing the descriptive nature of the index. By releasing structured derived records and a documented regeneration procedure, this work enables an implementation-independent comparison of gearbox condition monitoring approaches and supports reproducible evaluation of alternative health index formulations. Full article

Fault diagnosis of rolling bearings in wind turbines is significantly challenged by strong noise, non-stationary signals, and multi-source interference. To address these issues, a Multi-Scale Attention Residual Graph Convolutional Network (MSAR-GCN) is proposed. First, a fully connected graph is constructed in the frequency domain using a temporal segmentation strategy, which preserves full spectral resolution and captures cross-frequency coupling features via node embeddings. Second, a multi-scale residual module with a cross-layer pyramid structure is designed to extract features at varying granularities, integrated with a dynamic multi-head attention mechanism to adaptively emphasize damage-sensitive frequency bands. Additionally, a hierarchical feature distillation mechanism is employed to compress high-dimensional features, ensuring model lightweighting while retaining critical fault information. Experimental validations on CWRU and JNU datasets demonstrate that MSAR-GCN achieves 97.02% and 92.5% accuracy under −10 dB Gaussian noise, respectively, outperforming existing methods by over 4%. Specifically, the model exhibits exceptional robustness, maintaining 93.09% accuracy under severe non-Gaussian impulsive noise. With verified feature separability and high computational efficiency, the proposed method offers a promising solution for high-precision, real-time industrial fault diagnosis. Full article

The digital reconstruction of damaged archeological wall paintings is a challenging task due to severe material degradation, high fragmentation, and the lack of reference images. A crucial preliminary step is the separation and grouping of fragments originating from different wall paintings, which are often found mixed together at archeological sites. To address this issue, we explored the potential of multispectral imaging (MSI) for unsupervised fragment clustering, aiming to assess whether integrating multiple spectral bands can enhance fragment discrimination compared to using the visible band alone. As a test set, we examined five groups of wall painting fragments from a Roman domus (1st c. BC–1st c. AD) provided by the Archaeological Museum of Cremona (Italy). Images were acquired using the Hypercolorimetric Multispectral Imaging (HMI) system developed by Profilocolore^® Srl (Rome, Italy). Specifically, we considered visible reflectance (VIS), infrared reflectance (IR), infrared false color (IRFC), and Ultraviolet-induced Fluorescence (UVF) images. Through a systematic benchmarking study, we compared several state-of-the-art feature extraction and clustering methods across single- and multi-band configurations. Results show that combining MSI data can substantially enhance the system’s ability to correctly separate and group fragments, indicating a promising direction for future research. Full article

The application of ultra-supercritical power plant boilers is becoming increasingly widespread. P92 steel, as a typical material used for boiler main steam pipes, plays a critical role in unit safety, making the detection of its creep damage highly significant. However, existing conventional non-destructive testing methods are difficult to effectively detect creep damage. To address this issue, a magnetoacoustic emission (MAE)–magnetic Barkhausen noise (MBN) composite measurement system is developed, which is adapted to 20 Hz and 0.3 A sine wave excitation to trigger the synchronous pickup of MBN and MAE signals of P92 steel. After collecting signals with different creep life ratios (0%~100%) under working conditions of 650 °C and 100 MPa, time-domain (absolute mean, peak value, etc.) and frequency-domain (bandwidth) features are extracted. In response to the non-monotonicity between the magnetoacoustic features and the creep damage grade, principal component analysis (PCA) is introduced to reduce dimensionality. Different creep levels of samples in the two-dimensional principal component space are presented as clear gradient clustering, achieving the accurate differentiation of creep stages. Research has shown that the MAE-MBN composite system combined with PCA can effectively characterize the creep damage of P92 steel, providing a novel non-destructive detection path for the in-service life assessment of power plant components. Full article

In the field of forensic document examination, accurately determining the chronological sequence of intersecting lines between seal ink and handwriting is a crucial technical step for verifying document authenticity, identifying contract tampering, and detecting forged signatures. This technique analyzes the physical superimposition relationship formed by the deposition of the two media on the paper substrate to provide objective scientific evidence for judicial practice. Although traditional methods such as microscopic imaging and mass spectrometry analysis have achieved some progress, they still suffer from common limitations including high equipment costs, complex operation, and potential damage to samples. This study proposes and validates an innovative non-destructive determination method that integrates structured light 3D reconstruction technology with deep learning algorithms. The research captures the microscopic 3D morphological features of the ink intersection area using a high-precision structured light scanning system and effectively eliminates noise interference caused by paper substrate undulation through Gaussian flattening technology. Subsequently, a multimodal fusion strategy combines 2D texture images with 3D depth information to construct a dataset rich in features. On this basis, a deep learning model based on an improved Residual Neural Network (ResNet) is designed, incorporating the ELU activation function and an EMA mechanism to enhance the model’s feature extraction capability and convergence stability. Experimental results demonstrate that the proposed method achieves a recognition accuracy of 94.39% on the test set, fully validating its effectiveness and application potential in the non-destructive determination of ink stroke sequencing. Full article

Slow-moving landslides can trigger severe disasters when activated by earthquakes, torrential rains, or typhoons. Early detection is crucial for mitigating loss of life and property damage. Interferometric Synthetic Aperture Radar (InSAR) technology is among the most effective techniques for detecting slow-moving landslides, though its accuracy can be further improved through integration with optical imagery and Digital Elevation Models (DEM). Current machine learning approaches that combine InSAR and optical data suffer from limited efficiency, poor transferability, and challenges in regional-scale application. To address these limitations, this study proposes a multimodal dual-path network that integrates InSAR products with textural information from optical imagery to detect slow-moving landslides. One path processes InSAR deformation rates and topographic factors, while the other incorporates texture information and auxiliary data. Together, these paths extract semantic information from high-dimensional spatial features and condense it into low-dimensional representations. A pyramid pooling module is employed to capture multi-scale features during low-level semantic extraction. For feature fusion, a rate-constrained adaptive module is introduced to enhance the contribution of deformation rates to slow-moving landslides. According to the results, the proposed method improves the F1-score for landslide detection by 6% compared to using InSAR products alone. These results provide reliable technical support for regional landslide inventory compilation and disaster management, as well as new insights for regional-scale surveys in slow-moving landslide-prone areas. Full article

With the rapid development of the aviation industry, engines operate under extreme conditions of high temperature, high pressure, and high vibration, making them prone to surface damage such as ablation. Ablation not only affects the structural integrity of engine components but also threatens flight safety, making efficient and accurate detection of paramount importance. Traditional detection methods rely on manual visual inspection and non-destructive testing, which suffer from high subjectivity and low efficiency. In recent years, deep learning has achieved significant progress in industrial defect detection. However, conventional CNN-and Transformer-based architectures still suffer from substantial computational overhead and inadequate boundary segmentation accuracy in aero-engine ablation detection. This paper proposes a novel dual-pathway network Visual State-Space Residual Neural Network (VSS-ResNet) based on Mamba that combines Visual State Space (VSS) modules with ResNet50. This architecture leverages the global modeling capability of VSS modules and the local feature extraction capability of CNNs, effectively enhancing the accuracy and robustness of ablation boundary detection with the support of multi-scale feature fusion modules. Experimental results demonstrate that the proposed method achieves superior performance in mIoU, mPA, and Acc compared to mainstream segmentation models such as U-Net, Pyramid Scene Parsing Network (PSPNet), and DeepLab V3+ on a self-constructed engine endoscopic ablation dataset, validating its potential in intelligent aero-engine inspection. Full article

Floods are among the most devastating natural hazards, intensified by climate change and rapid urbanization. This study introduces a novel deep learning framework, Transfer Learning-Enhanced FEDformer (TLE-FEDformer), designed for accurate and temporally consistent flood inundation mapping. The framework integrates pre-trained Xception backbones for robust multi-sensor feature extraction from Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical imagery, a cross-modal fusion module to align heterogeneous modalities, and the Frequency Enhanced Decomposed Transformer (FEDformer) for efficient frequency-domain temporal modeling. This architecture effectively captures long-range dependencies and flood dynamics including onset, peak, duration, and recession, while addressing challenges such as cloud contamination, speckle noise, and limited labeled data. Comprehensive experiments demonstrate superior performance, achieving an overall accuracy of 98.12%, an F1-score of 98.55%, and an Intersection over Union (IoU) of 97.38%, outperforming baselines including Convolutional Neural Networks, Capsule Networks, and transfer learning alone. Ablation studies validate the contributions of each component, while sensitivity analyses confirm robustness across hyperparameters. Uncertainty quantification via Monte Carlo dropout highlights high confidence in core flooded regions. Preliminary generalization tests on independent events yield IoU > 94%, indicating strong transferability. TLE-FEDformer advances operational flood monitoring by providing reliable, scalable, and temporally consistent mapping from multi-sensor remote sensing data. This approach offers significant potential for real-time disaster response, early warning systems, and damage assessment in flood-prone regions worldwide. Full article

Hurricanes have intensified and become more persistent under a changing climate, increasing the risk of infrastructure damage and property loss in coastal regions, threatening their sustainability. This study examines how hurricane intensity and persistence influence infrastructure loss, contributing to a more comprehensive understanding of climate-related risks. Using data from the National Oceanic and Atmospheric Administration (NOAA) Storm Events Database from 1996 to 2024, we develop a series of machine learning models to predict property losses based on storm characteristics and contextual vulnerability factors. Narrative-based text analysis and time-series feature engineering were applied to extract meteorological and temporal attributes, while regression and ensemble models were used for predictive evaluation. Results show that storm intensity alone explains only a small portion of loss variance, with persistence influencing damage primarily through rainfall and hydrological effects. The findings highlight that vulnerability, exposure, and cumulative risk dynamics are essential for accurate long-term prediction and for assessing infrastructure sustainability. Overall, the study demonstrates that combining machine learning techniques with climate and vulnerability data can inform future research on infrastructure sustainability. The quantified vulnerability-versus-intensity breakdown presented here can support post-disaster resource allocation, insurance risk modeling, and the prioritization of infrastructure maintenance in hurricane-prone regions. Full article

The early detection and monitoring of stress-induced damage in concrete is a key goal for nondestructive evaluation and structural health monitoring of civil structures. Both linear and nonlinear ultrasonic testing methods have been developed for this purpose. The Ultrasonic Pulse Velocity (UPV) test is the standard linear technique and is reliable and easy to use, but it typically detects defects only after micro-cracks coalesce or grow beyond a threshold size. To enable earlier detection, features extracted from the nonlinear ultrasonic response—especially harmonics generation—have been proposed. However, these approaches often require complex measurement protocols, and their signal-to-noise ratio (SNR) can be limited. In this study, we leverage an exponential swept-sine pulse-compression (ESS–PuC) procedure to characterize both linear and nonlinear responses from a single measurement. We define and extract several features from both responses, and use them to monitor micro-crack initiation and growth in concrete specimens under gradually increasing compressive load. This enables a qualitative comparison of their characteristics and performance in detecting crack formation. Full article

Background: Disability progression in multiple sclerosis (MS) is increasingly recognized as a consequence of large-scale brain network disruption rather than isolated regional damage. Although diffusion tensor imaging (DTI) is the reference method for assessing structural connectivity, its limited availability restricts widespread clinical application. There is therefore a critical need for alternative approaches capable of capturing network-level alterations using routinely acquired MRI data. Objective: This study aimed to determine whether synthetic structural connectivity matrices derived from standard regional volumetric MRI can capture clinically meaningful network alterations in MS and predict subsequent functional progression, particularly upper limb decline. Methods: Regional brain volumetry was obtained from routine T1-weighted MRI using an automated, clinically approved volumetric pipeline. Synthetic structural connectivity matrices were generated by integrating principles of structural covariance, distance-dependent connectivity, and disease-specific vulnerability patterns. Graph-theoretical network metrics were extracted to characterize global and regional topology. Machine learning models including logistic regression, support vector machines, random forests, and gradient boosting were trained to predict clinical progression defined by worsening on the 9-Hole Peg Test. Dimensionality reduction was performed using principal component analysis, and model performance was evaluated using balanced accuracy, AUC-ROC, and resampling-based validation. Feature importance analyses were conducted to identify network vulnerability patterns. Results: Synthetic connectivity networks exhibited biologically plausible properties, including preserved but attenuated small-world organization. Global efficiency showed a strong inverse correlation with disability severity (EDSS). Patients with clinical progression demonstrated marked reductions in network integration and segregation, alongside increased characteristic path length. Machine learning models achieved robust prediction of upper limb functional decline, with ensemble-based methods performing best (balanced accuracy > 80%, AUC-ROC up to 0.85). A limited subset of connections accounted for a disproportionate share of predictive power, predominantly involving frontoparietal associative networks, thalamocortical pathways, and inter-hemispheric connections. In a longitudinal subset, network-level alterations preceded measurable clinical deterioration by several months. Conclusions: Synthetic structural connectivity derived from routine volumetric MRI captures clinically relevant network-level disruption in multiple sclerosis and enables accurate prediction of functional progression. By bridging network neuroscience with widely accessible imaging data, this framework provides a pragmatic alternative for connectomic analysis when diffusion imaging is unavailable and supports a network-based understanding of disease evolution in MS. Full article

Background and Objective: Axial spondyloarthritis (axSpA) is a group of chronic inflammatory diseases that primarily affect the sacroiliac joints. Early diagnosis is crucial for preventing irreversible structural damage. Magnetic Resonance Imaging (MRI) is the gold standard for detecting early inflammatory changes such as sacroiliitis. However, conventional MRI interpretation is inherently subjective and susceptible to both intra- and inter-observer variability. Therefore, artificial intelligence (AI)-driven diagnostic solutions are increasingly being explored. Among them, the Gated Attention Multiple Instance Learning (MIL) framework holds strong potential in modeling heterogeneous inflammatory distributions, thanks to its slice-level attention mechanism. This study aims to evaluate the diagnostic performance of a deep learning model based on Gated Attention MIL for automated sacroiliitis detection. Furthermore, its results are compared with a baseline deep learning architecture (standard ResNet-18), and its consistency with radiologist annotations is analyzed. Materials and Methods: The dataset included 554 subjects, comprising 276 patients diagnosed with axSpA and 278 healthy controls. All MRI data were derived from axial T2-weighted fat-suppressed (T2_TSE_TRA_FS) sequences. Patient-wise data splitting was employed to construct training, validation, and independent test sets. The proposed model architecture integrates ResNet-18-based feature extraction, a gated attention mechanism for instance-level weighting, and bag-level classification. Additionally, Test-Time Augmentation (TTA) was implemented to enhance robustness during inference. Results: On the independent test set, the model achieved an accuracy of 85.88%, sensitivity of 92.86%, specificity of 79.07%, and an F1-score of 86.67%. Attention heatmaps generated by the MIL module showed strong spatial overlap with bone marrow edema regions annotated by expert radiologists. Implementation of TTA led to an approximate 10% improvement in overall classification accuracy. Conclusions: The Gated Attention MIL framework demonstrated high diagnostic performance for sacroiliitis detection, indicating its value as a reliable decision support tool for early axSpA diagnosis. Validation on larger, multi-center datasets is warranted to ensure generalizability and to support clinical integration in routine radiology workflows. Full article

To address challenges such as complex backgrounds, partial occlusion, and high similarity of details in Terracotta Warrior image recognition, this paper proposes a lightweight detection method, YOLOv10-TWD, based on an improved YOLOv10n. Specifically, a lightweight Convolution-Attention Fusion Module (CAFMAttention) and a dual-branch feature extraction structure (DualConv) are integrated into the detection head to enhance the model’s focus on fine-grained features and its discriminative robustness under partial damage conditions. In the Neck network, Ghost-Shuffle Convolution (GSConv) is introduced to compress the computational cost of multi-scale feature fusion while strengthening context-aware capabilities. Experimental results on a self-built Terracotta Warrior dataset demonstrate that the proposed method achieves a 7.63% improvement in mAP@0.5 compared to the baseline YOLOv10n, while simultaneously achieving a 6.66% increase in inference speed. The model achieves high precision alongside significant optimization in inference efficiency, making it well-suited for rapid recognition tasks in cultural heritage and museum scenarios. Full article

Rolling bearings are critical and vulnerable components in mechanical equipment and are prone to various types of damage during operation. Consequently, rolling bearing fault diagnosis is of significant engineering importance. In recent years, deep learning-based approaches have achieved considerable progress in intelligent bearing fault diagnosis. However, existing models still suffer from several limitations, including insufficient feature extraction under noisy conditions, limited diagnostic accuracy, high computational cost, and low operational efficiency. To address these challenges, an intelligent rolling bearing fault diagnosis method based on an ascending-dimensional convolutional neural network (ADCNN) is proposed. Compared with conventional neural networks, the proposed ADCNN features a more compact model size, improved noise robustness, and higher diagnostic accuracy. A large convolutional kernel is introduced in the first layer to enhance noise immunity, while an ascending-dimensional module is employed to reduce the number of network parameters and improve feature extraction capability. In addition, a reduced linear transformation layer (RLTL) is incorporated to further achieve a lightweight architecture. Experimental results on the Case Western Reserve University (CWRU) dataset and a self-designed test dataset demonstrate that the proposed ADCNN achieves superior fault diagnosis performance under different noise environments while maintaining computational efficiency and model compactness. Full article

Cracks in planetary gearbox casings generate additional vibration responses, which may be used for monitoring structural degradations. This paper provides a signal processing framework to effectively track casing crack-related features in planetary gearboxes using the carrier synchronous signal average (C-SSA). The proposed algorithm is based on processing the hunting-tooth synchronous signal average (H-SSA) to extract the C-SSA which contains the cyclic interaction between the gear loadings and the corresponding casing response. The root mean square (RMS) of the C-SSA signal can then serve as a health condition indicator (CI) to track crack propagation. Further enhancement can be achieved by applying the Hilbert transform (HT) on the C-SSA using the full bandwidth to derive squared envelope signal, which enhances the trending capability. To remove cyclic temperature influences observed in the trends, singular spectrum analysis technique (SSAT) has been used to ensure that the trend reflects the changes purely due to the damage progression. Experiments using three casing-mounted sensors show good capability to track crack progression. Tests under 100%, 125%, and 150% load levels show consistent performance across these operating conditions, with better results seen at higher loads. The results demonstrate that C-SSA and its squared envelope signal effectively enhance the sensitivity and reliability of vibration-based casing crack detection, providing a practical tool for long-term structural health monitoring of planetary gearboxes. Full article