Search Results (47)

To address the computational redundancy, inadequate multi-scale feature capture, and poor noise robustness of traditional deep networks used for bearing vibration and acoustic signal feature extraction, this paper proposes a fault diagnosis method based on Depthwise Separable Atrous Convolution (DSAC) and Acoustic Spatial Pyramid Pooling (ASPP). First, the Continuous Wavelet Transform (CWT) is applied to the vibration and acoustic signals to convert them into time–frequency representations. The vibration CWT is then fed into a multi-scale feature extraction module to obtain preliminary vibration features, whereas the acoustic CWT is processed by a Deep Residual Shrinkage Network (DRSN). The two feature streams are concatenated in a feature fusion module and subsequently fed into the DSAC and ASPP modules, which together expand the effective receptive field and aggregate multi-scale contextual information. Finally, global pooling followed by a classifier outputs the bearing fault category, enabling high-precision bearing fault identification. Experimental results show that, under both clean data and multiple low signal-to-noise ratio (SNR) noise conditions, the proposed DSAC-ASPP method achieves higher accuracy and lower variance than baselines such as ResNet, VGG, and MobileNet, while requiring fewer parameters and FLOPs and exhibiting superior robustness and deployability. Full article

Hunan Province from 2000 to 2023 is the study area. Based on NOAA precipitation data and county-level rice yield statistics in Hunan Province, the Mann–Kendall test, extreme precipitation indices, and wavelet analysis examine the spatial and temporal evolution characteristics of extreme precipitation and its multi-scale impact on rice yield. The results show that the extreme precipitation in Hunan Province showed a stable pattern of fluctuation, and the main extreme precipitation indexes had no significant change trend. The spatial distribution showed a pattern of “high value in central-northern Hunan and stable in southern Hunan”, and the precipitation was concentrated in June–August. The rice yield showed the characteristics of “stable increase in the core area, intensified fluctuation in the transition area, and continuous shrinkage in the marginal area”, and the Dongting Lake Plain was a high-yield and stable area. Multi-scale analysis shows significant coupling between extreme precipitation and yield: in the 4–8-year cycle, the peak value of precipitation lags behind the response of 1–2 years, and changes synchronously in a short period. The response of rice to extreme precipitation showed a threshold-type nonlinear characteristic. Moderate wetting was beneficial to stable yield, while the yield decreased significantly when the intensity or continuous precipitation exceeded the threshold. Hunan’s rice system has strong climate resilience but requires a multi-scale climate-adaptive agricultural system via engineering, technology, and policy for long-term stability and sustainable grain production. Full article

Accurate forecasting of photovoltaic (PV) power is crucial for real-time grid balancing and storage optimization. However, the intermittent, noisy, and nonstationary nature of PV generation, together with cross-site interactions, makes multi-site intra-hour forecasting challenging. In this paper, we propose a unified approach for multi-site PV power forecasting named WGL (Wavelet–Graph Learning). Unlike prior studies that treat denoising and spatio-temporal modeling separately or predict each station independently, WGL forecasts all PV stations jointly while explicitly capturing their inherent spatio-temporal correlations. Within WGL, Learnable Wavelet Shrinkage (LWS) performs end-to-end noise suppression; a Temporal Multi-Scale Fine-grained Fusion (T-MSFF) module extracts complementary temporal patterns; and an attention fusion gate adaptively balances TCN and LSTM branches. For spatial coupling, graph self-attention (GSA) learns a sparse undirected graph among stations, and a Factorized Spatio-Temporal Attention (FSTA) efficiently models long-range interactions. Experiments on real-world multi-site PV datasets show that WGL consistently outperforms representative deep and graph-based baselines across intra-hour horizons, highlighting its effectiveness and deployment potential. Furthermore, a comprehensive analysis of influencing factors for scheme implementation—encompassing safety, reliability, economic rationality, management scientificity, and humanistic care—is conducted, providing a holistic assessment of the framework’s feasibility and potential impact in real-world power systems. Full article

The method addresses the challenges of non-steady conditions at an early age by combining wavelet filtering and empirical mode decomposition (EMD) to separate strain components arising from shrinkage, expansive agent compensation, temperature variations, construction disturbances, and live loads. The approach incorporates construction logs as external constraints to ensure accurate correspondence between signal features and physical events. Scientifically, this study addresses the fundamental problem of identifying and quantifying multi-source strain components under transient and non-steady construction conditions, which remains a major challenge in the field of structural monitoring. Field monitoring was conducted on typical cast-in-place concrete components: a full-width bridge deck in the negative moment region. The results show that both structural types exhibit a distinct shrinkage–recovery process at an early age but differ in amplitude distribution, recovery rate, and restraint characteristics. During the construction procedure stage, the cast-in-place segment in the negative moment region was sensitive to prestressing and adjacent segment construction. Under variable loads, the former showed higher live load sensitivity, while the latter exhibited more pronounced temperature-driven responses. Total strain decomposition revealed that temperature and dead load were the primary long-term components in the structure, with differing proportional contributions. Representative strain variations observed in the field ranged from 10 to 50 µε during early-age shrinkage–expansion cycles to 80–100 µε reductions during prestressing operations, quantitatively illustrating the evolution characteristics captured by the proposed method. This approach demonstrates the method’s capability to reveal transient stress mechanisms that conventional steady-state analyses cannot capture, providing a reliable basis for strain monitoring, disturbance identification, and performance evaluation during construction, as well as for long-term prediction and optimization of operation–maintenance strategies. Full article

Efficient power grid operations and effective business strategies require accurate prediction of power outages. However, predicting outages is a difficult task due to the large amount of heterogeneous, random, intermittent, and non-linear power grid data characterised by highly complex variable relationships. Attempting to simultaneously quantify these characteristics using a conventional single (linear or nonlinear) model may lead to inaccurate and costly results. To address this, we propose a hybrid RVM-WT-AdaBoostRT-RF framework using power grid data from the Electricity Supply Commission (Eskom) of South Africa. To achieve model interpretability, the least absolute shrinkage and selection operator (LASSO) is first applied to remedy the adverse effects of multicollinearity through regularisation and variable selection. Secondly, a random forest (RF) is used to select the top 10 most influential variables for each season for further analysis. A relevance vector machine (RVM) captures complex nonlinear relationships separately for each season, while the wavelet transform (WT) decomposes residuals generated from RVM into different frequency subseries (with reduced noise). These subseries are predicted with minimal bias using AdaBoost with regression and threshold (AdaBoostRT). Finally, we stack RVM, AdaBoostRT, RF, and residual individual predictions using RF as a meta-model to produce the final forecast with minimal error accumulation and efficiency. The comparative study, based on point forecast metrics, the Diebold-Mariano test, and prediction interval widths, shows that the proposed model outperforms vector autoregressive (VAR), RF, AdaBoostRT, RVM, and Naïve models. The study results can be utilised for optimising resource allocation, effective power grid management, and customer alerts. Full article

Rolling bearing vibration signals are often severely affected by strong external noise, which can obscure fault-related features and hinder accurate diagnosis. To address this challenge, this paper proposes an enhanced Deep Residual Shrinkage Network with Dynamic Convolution and Selective Kernel Attention (DDRSN-SKA). First, one-dimensional vibration signals are converted into two-dimensional time frequency images using the Continuous Wavelet Transform (CWT), providing richer input representations. Then, a dynamic convolution module is introduced to adaptively adjust kernel weights based on the input, enabling the network to better extract salient features. To improve feature discrimination, an Selective Kernel Attention (SKAttention) module is incorporated into the intermediate layers of the network. By applying a multi-receptive field channel attention mechanism, the network can emphasize critical information and suppress irrelevant features. The final classification layer determines the fault types. Experiments conducted on both the Case Western Reserve University (CWRU) dataset and a laboratory-collected bearing dataset demonstrate that DDRSN-SKA achieves diagnostic accuracies of 98.44% and 94.44% under −8 dB Gaussian and Laplace noise, respectively. These results confirm the model’s strong noise robustness and its suitability for fault diagnosis in noisy industrial environments. Full article

This research provides a new systematic solution to the essential issue of self-noise interference in underwater acoustic sensing signals induced by unmanned surface vehicles (USVs) operating at sea. The self-noise pertains to the near-field interference noise generated by the growing diversity and volume of acoustic equipment utilized by USVs. The generating mechanism of self-noise is clarified, and a self-noise propagation model is developed to examine its three-dimensional coupling properties within spatiotemporal fluctuation environments in the time-frequency-space domain. On this premise, the YOLOv11 object identification framework is innovatively applied to the delay-Doppler (DD) feature maps of self-noise, thereby overcoming the constraints of traditional time-frequency spectral approaches in recognizing noise with delay spread and overlapping characteristics. A comprehensive comparison with traditional models like YOLOv8 and SSD reveals that the suggested delay-Doppler YOLO (DD-YOLO) algorithm attains an average accuracy of 87.0% in noise source identification. An enhanced denoising method, termed optimized time-frequency regularized overlapping group shrinkage (OTFROGS), is introduced, using structural sparsity alongside non-convex regularization techniques. Comparative experiments with traditional denoising methods, such as the normalized least mean square (NLMS) algorithm, wavelet threshold denoising (WTD), and the original time-frequency regularized overlapping group shrinkage (TFROGS), reveal that OTFROGS outperforms them in mitigating USV self-noise. This study offers a dependable technological approach for optimizing the performance of USV acoustic systems and proposes a theoretical framework and methodology applicable to different underwater acoustic sensing contexts. Full article

Accurate nitrogen (N) content estimation in grassland vegetation is essential for ecosystem health and optimizing pasture quality, as N supports plant photosynthesis and water uptake. Traditional lab methods are slow and unsuitable for large-scale monitoring, while remote sensing models often face accuracy challenges due to hyperspectral data complexity. This study improves N content estimation in the typical steppe of Inner Mongolia by integrating hyperspectral remote sensing with advanced machine learning. Hyperspectral reflectance from Leymus chinensis and Cleistogenes squarrosa was measured using an ASD FieldSpec-4 spectrometer, and leaf N content was measured with an elemental analyzer. To address high-dimensional data, four spectral transformations—band combination, first-order derivative transformation (FDT), continuous wavelet transformation (CWT), and continuum removal transformation (CRT)—were applied, with Least Absolute Shrinkage and Selection Operator (LASSO) used for feature selection. Four machine learning models—Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Artificial Neural Network (ANN), and K-Nearest Neighbors (KNN)—were evaluated via five-fold cross-validation. Wavelet transformation provided the most informative parameters. The SVM model achieved the highest accuracy for L. chinensis (R² = 0.92), and the ANN model performed best for C. squarrosa (R² = 0.72). This study demonstrates that integrating wavelet transform with machine learning offers a reliable, scalable approach for grassland N monitoring and management. Full article

The prediction of reservoir and caprock thickness is important in geological evaluations for site selection for aquifer underground gas storage. Therefore, high-resolution seismic identification of reservoirs and caprocks is crucial. High-resolution time–frequency decomposition is one of the key methods for identifying sedimentary layers. Based on this, we propose a least squares constrained spectral analysis method using a greedy fast shrinkage algorithm. This method replaces the traditional Tikhonov regularization objective function with an L1-norm regularized objective function and employs a greedy fast shrinkage algorithm. By utilizing shorter window lengths to segment the data into more precise series, the method significantly improves the computational efficiency of spectral analysis while also enhancing its accuracy to a certain extent. Numerical models demonstrate that compared to the time–frequency spectra obtained using traditional methods such as wavelet transform, short-time Fourier transform, and generalized S-transform, the proposed method can achieve high-resolution extraction of the dominant frequencies of seismic waves, with superior noise resistance. Furthermore, its application in a research area in southern China shows that the method can effectively predict thicker sedimentary layers in low-frequency ranges and accurately identify thinner sedimentary layers in high-frequency ranges. Full article

The traditional detection method of transformer oil acid value has limitations, such as long detection period and toxicity of reagents; while, with the traditional spectral analysis, it is difficult to realize the efficient extraction of key features related to the acid value content. Early detection of rising acid levels is critical to prevent transformer insulation degradation, corrosion, and failure. Conversely, delayed detection accelerates aging and can cause costly repairs or unplanned outages. To address this need, this paper proposes a new method for predicting the acid value content of the transformer oil based on the infrared spectra in the transformer oil and a deep neural network (DNN). The infrared spectral data of the transformer oil is acquired by ALPHA II FT-IR spectrometer, the high frequency noise effect of the spectrum is reduced by wavelet packet decomposition (WPD), and the bootstrapping soft shrinkage (BOSS) algorithm is used to extract the spectra with the highest correlation with the acid value content. The BOSS algorithm is used to extract the feature parameters with the highest correlation with the acid value content in the spectrum, and the DNN prediction model is established to realize the fast prediction of the acid value content of the transformer oil. In comparison with the traditional infrared spectral preprocessing method and regression model, the proposed prediction model has a coefficient of determination (R²) of 97.12% and 95.99% for the prediction set and validation set, respectively, which is 4.96% higher than that of the traditional model. In addition, the accuracy is 5.45% higher than the traditional model, and the R² of the proposed prediction model is 95.04% after complete external data validation, indicating that it has good accuracy. The results show that the infrared spectral analysis method combining WPD noise reduction, BOSS feature extraction, and DNN modeling can realize the rapid prediction of the acid value content of the transformer oil based on infrared spectroscopy technology, and the prediction model can be used to realize the analytical study of transformer oils. The model can be further applied to the monitoring field of the transformer oil characteristic parameter to realize the rapid monitoring of the transformer oil parameters based on a portable infrared spectrometer. Full article

Noises on the field can affect the electromechanical system characteristics in the bearing fault diagnostic process. This paper presents a deep learning-based fault-diagnosis model DRSN–GCE (Deep Relative Shrinkage Network with Gated Convolutions and Enhancements), which is designed to deal with noise and improve noise resistance. In the first step, the data are preprocessed by adding different noises with different ratios of signal to noise and different frequencies to the vibration signals. This simulates the field noise environments. The continuous wavelet transformation (CWT), which converts the time-series signal from one dimension to a time-frequency two-dimensional image, provides rich data input for the deep learning model. Secondly, a convolutional gated layer is added to the deep residual network (DRSN), which suppresses the noise interference. The residual connection structure has also been improved in order to improve the transfer of features. In complex signals, the Gated Convolutional Shrinkage Module is used to improve feature extraction and suppress noise. The experiments on the Case Western Reserve University bearing dataset show that the DRSN–GCE exhibits high diagnostic accuracy and strong noise immunity in various noise environments such as Gauss, Laplace, Salt-and-Pepper, and Poisson. DRSN–GCE is superior to other deep learning models in terms of noise suppression, fault detection accuracy, and rolling bearing fault diagnoses in noisy environments. Full article

In the operation process of modern industrial equipment, as the core transmission component, the operation state of the gearbox directly affects the overall performance and service life of the equipment. However, the current gear operation is still faced with problems such as poor monitoring, a single detection index, and low data utilization, which lead to incomplete evaluation results. In view of these challenges, this paper proposes a shape and property integrated gearbox monitoring system based on digital twin technology and artificial intelligence, which aims to realize real-time fault diagnosis, performance prediction, and the dynamic visualization of gear through virtual real mapping and data interaction, and lays the foundation for the follow-up predictive maintenance application. Taking the QPZZ-ii gearbox test bed as the physical entity, the research establishes a five-layer architecture: functional service layer, software support layer, model integration layer, data-driven layer, and digital twin layer, forming a closed-loop feedback mechanism. In terms of technical implementation, combined with HyperMesh 2023 refinement mesh generation, ABAQUS 2023 simulates the stress distribution of gear under thermal fluid solid coupling conditions, the Gaussian process regression (GPR) stress prediction model, and a fault diagnosis algorithm based on wavelet transform and the depth residual shrinkage network (DRSN), and analyzes the vibration signal and stress distribution of gear under normal, broken tooth, wear and pitting fault types. The experimental verification shows that the fault diagnosis accuracy of the system is more than 99%, the average value of the determination coefficient (R²) of the stress prediction model is 0.9339 (driving wheel) and 0.9497 (driven wheel), and supports the real-time display of three-dimensional cloud images. The advantage of the research lies in the interaction and visualization of fusion of multi-source data, but it is limited to the accuracy of finite element simulation and the difficulty of obtaining actual stress data. This achievement provides a new method for intelligent monitoring of industrial equipment and effectively promotes the application of digital twin technology in the field of predictive maintenance. Full article

Background: Primary and secondary salivary gland malignancies differ significantly in treatment and prognosis. However, conventional ultrasonography often struggles to differentiate between these malignancies due to overlapping imaging features. We aimed to develop and evaluate noninvasive diagnostic models based on traditional ultrasound features, radiomics, and deep learning—independently or in combination—for distinguishing between primary and secondary salivary gland malignancies. Methods: This retrospective study included a total of 140 patients, comprising 68 with primary and 72 with secondary salivary gland malignancies, all pathologically confirmed, from four medical centers. Ultrasound features of salivary gland tumors were analyzed, and a radiomics model was established. Transfer learning with multiple pre-trained models was used to create deep learning (DL) models from which features were extracted and combined with radiomics features to construct a radiomics-deep learning (RadiomicsDL) model. A combined model was further developed by integrating ultrasound features. Least absolute shrinkage and selection operator (LASSO) regression and various machine learning algorithms were employed for feature selection and modeling. The optimal model was determined based on the area under the receiver operating characteristic curve (AUC), and interpretability was assessed using SHapley Additive exPlanations (SHAP). Results: The RadiomicsDL model, which combines radiomics and deep learning features using the Multi-Layer Perceptron (MLP), demonstrated the best performance on the test set with an AUC of 0.807. This surpassed the performances of the ultrasound (US), radiomics, DL, and combined models, which achieved AUCs of 0.421, 0.636, 0.763, and 0.711, respectively. SHAP analysis revealed that the radiomic feature Wavelet_LHH_glcm_SumEntropy contributed most significantly to the mode. Conclusions: The RadiomicsDL model based on ultrasound images provides an efficient and non-invasive method to differentiate between primary and secondary salivary gland malignancies. Full article

(1) Background: Predicting hospitalization length for COVID-19 patients is crucial for optimizing resource allocation and patient management. Radiomics, combined with machine learning (ML), offers a promising approach by extracting quantitative imaging features from CT scans. The aim of the present study is to use and adapt machine learning (ML) architectures, exploiting CT radiomics information, and analyze algorithms’ capability to predict hospitalization at the time of patient admission. (2) Methods: The original CT lung images of 168 COVID-19 patients underwent two segmentations, isolating the ground glass area of the lung parenchyma. After an isotropic voxel resampling and wavelet and Laplacian of Gaussian filtering, 92 intensity and texture radiomics features were extracted. Feature reduction was conducted by applying a last absolute shrinkage and selection operator (LASSO) to the radiomic features set. Three ML classification algorithms, linear support vector machine (LSVM), medium neural network (MNN), and ensemble subspace discriminant (ESD), were trained and validated through a 5-fold cross-validation technique. Model performance was assessed using accuracy, sensitivity, specificity, precision, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). (3) Results: The LSVM classifier achieved the highest predictive performance, with an accuracy of 86.0% and an AUC of 0.93. However, reliable outcomes are also registered when MNN and ESD architecture are used. (4) Conclusions: The study shows that radiomic features can be used to build a machine learning framework for predicting patient hospitalization duration. The findings suggest that radiomics-based ML models can accurately predict COVID-19 hospitalization length. Full article

Rolling bearing vibration signals contain rich fault feature information. However, their periodic pulse feature is often interfered with by strong background noise, which reduces the feature recognition ability of fault diagnosis strategies. Therefore, accurately extracting periodic pulse information under strong background noise is a key challenge in rolling bearing fault diagnosis. To address this, a fault feature extraction strategy combining wavelet overlapping group shrinkage (WOGS) and extended enveloped hierarchical multiscale-weighted permutation entropy (EEHMWPE) is proposed. First, wavelet decomposition is applied to decompose original vibration signals into wavelet coefficients, with WOGS adaptively adjusting the shrinkage level based on energy relationships to effectively suppress noise. Next, for the denoised signal, EEHMWPE extracts periodic pulse features by integrating envelope analysis, weighting, and extended statistical features. Envelope processing enhances fault-induced impulses, the weighting scheme highlights dominant fault patterns, and extended statistical features further improve the class separability between normal and fault signals. Finally, the strategy was validated on the bearing test bench, CWRU, and HUST datasets, all of which achieved over 99% accuracy with superior feature recognition. Full article