Search Results (108)

High-resolution range profile (HRRP) recognition serves as a foundational task in radar automatic target recognition (RATR), enabling robust classification under all-day and all-weather conditions. However, existing approaches often struggle to simultaneously capture the multi-scale spatial dependencies and global spectral relationships inherent in HRRP signals, limiting their effectiveness in complex scenarios. To address these limitations, we propose a novel multi-scale domain perception network tailored for HRRP-based target recognition, called MSDP-Net. MSDP-Net introduces a hybrid spatial–spectral representation learning strategy through a multiple-domain perception HRRP (DP-HRRP) encoder, which integrates multi-head convolutions to extract spatial features across diverse receptive fields, and frequency-aware filtering to enhance critical spectral components. To further enhance feature fusion, we design a hierarchical scale fusion (HSF) branch that employs stacked semantically enhanced scale fusion (SESF) blocks to progressively aggregate information from fine to coarse scales in a bottom-up manner. This architecture enables MSDP-Net to effectively model complex scattering patterns and aspect-dependent variations. Extensive experiments on both simulated and measured datasets demonstrate the superiority of MSDP-Net, achieving 80.75% accuracy on the simulated dataset and 94.42% on the measured dataset, highlighting its robustness and practical applicability. Full article

The threshing drum, a core component in combine harvesters, experiences significant unbalanced vibrations during high-speed rotation, leading to severe mechanical wear, increased energy consumption, elevated noise levels, potential safety hazards, and higher maintenance costs. A primary challenge is that excessive interference signals often obscure the fundamental frequency characteristics of the vibration, hampering balancing effectiveness. This study introduces a signal conditioning model to suppress such interference and accurately extract the unbalanced quantities from the raw signal. Leveraging this extracted vibration force signal, an automatic optimization method for the balancing counterweights was developed, solving calculation issues inherent in traditional approaches. This formed the basis for an automatic balancing control strategy and an integrated system designed for online monitoring and real-time control. The system continuously adjusts the rotation angles, θ₁ and θ₂, of the balancing weight disks based on live signal characteristics, effectively reducing the drum’s imbalance under both internal and external excitation states. This enables a closed loop of online vibration testing, signal processing, and real-time balance control. Experimental trials demonstrated a significant 63.9% reduction in vibration amplitude, from 55.41 m/s² to 20.00 m/s². This research provides a vital theoretical reference for addressing structural instability in agricultural equipment. Full article

Hyperspectral imaging has been increasingly used in mining for detailed mineral characterization and enhanced ore–waste discrimination, which is essential for optimizing resource extraction. However, the full deployment of this technology still faces challenges due to the variability of field conditions and the spectral complexity inherent in real-world mining environments. In this study, we compare the performance of two approaches for ore–waste discrimination in both laboratory and actual mine site conditions: (i) a data-driven feature extraction (FE) method and (ii) a knowledge-based mineral mapping method. Rock samples, including ore and waste from an open-pit gold mine, were obtained and scanned using a hyperspectral imaging system under laboratory conditions. The FE method, which quantifies the frequency absorption peaks at different wavelengths for a given rock sample, was used to train three discriminative models using the random forest classifier (RFC), support vector classification (SVC), and K-nearest neighbor classifier (KNNC) algorithms, with RFC achieving the highest performance with an F1-score of 0.95 for the laboratory data. The mineral mapping method, which quantifies the presence of pyrite, calcite, and potassium feldspar based on prior geochemical analysis, yielded an F1-score of 0.78 for the ore class using the RFC algorithm. In the next step, the performance of the developed discriminative models was tested using hyperspectral data of two muck piles scanned in the open-pit gold mine. The results demonstrated the robustness of the mineral mapping method under field conditions compared to the FE method. These results highlight hyperspectral imaging as a valuable tool for improving ore-sorting efficiency in mining operations. Full article

The widespread integration of power electronic devices and renewable energy sources into power systems has significantly exacerbated voltage and current waveform distortion issues, where asymmetric loads—including single-phase nonlinear equipment and unbalanced three-phase power electronic installations—serve as critical harmonic sources whose inherent nonlinear and asymmetric characteristics increasingly compromise power quality. To enhance power quality management, this paper proposes a universal harmonic source modeling and operational state identification methodology integrating physical mechanisms with data-driven algorithms. The approach establishes an RL-series equivalent impedance model as its physical foundation, employing singular value decomposition and Z-score criteria to accurately characterize asymmetric load dynamics; subsequently applies Variational Mode Decomposition (VMD) to extract time-frequency features from equivalent impedance parameters while utilizing Density-Based Spatial Clustering (DBSCAN) for the high-precision identification of operational states in asymmetric loads; and ultimately constructs state-specific harmonic source models by partitioning historical datasets into subsets, substantially improving model generalizability. Simulation and experimental validations demonstrate that the synergistic integration of physical impedance modeling and machine learning methods precisely captures dynamic harmonic characteristics of asymmetric loads, significantly enhancing modeling accuracy, dynamic robustness, and engineering practicality to provide an effective assessment framework for power quality issues caused by harmonic source integration in distribution networks. Full article

This study focuses on the problem of identifying and extracting the magnetopause boundary of the Earth’s magnetosphere using the Soft X-ray Imager (SXI) onboard the Solar Wind Magnetosphere Ionosphere Link Explorer (SMILE) mission. The SXI employs lobster-eye optics to perform panoramic imaging of the magnetosphere based on the Solar Wind Charge Exchange (SWCX) mechanism. However, several factors are expected to hinder future in-orbit observations, including the intrinsically low signal-to-noise ratio (SNR) of soft-X-ray emission, pronounced vignetting, and the non-uniform effective-area distribution of lobster-eye optics. These limitations could severely constrain the accurate interpretation of magnetospheric structures—especially the magnetopause boundary. To address these challenges, a boundary detection approach is developed that combines image calibration with denoising based on deep image prior (DIP). The method begins with calibration procedures to correct for vignetting and effective area variations in the SXI images, thereby restoring the accurate brightness distribution and improving spatial uniformity. Subsequently, a DIP-based denoising technique is introduced, which leverages the structural prior inherent in convolutional neural networks to suppress high-frequency noise without pretraining. This enhances the continuity and recognizability of boundary structures within the image. Experiments use ideal magnetospheric images generated from magnetohydrodynamic (MHD) simulations as reference data. The results demonstrate that the proposed method significantly improves the accuracy of magnetopause boundary identification under medium and high solar wind number density conditions (N = 10–20 cm⁻³). The extracted boundary curves consistently achieve a normalized mean squared error (NMSE) below 0.05 compared to the reference models. Additionally, the DIP-processed images show notable improvements in peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), indicating enhanced image quality and structural fidelity. This method provides adequate technical support for the precise extraction of magnetopause boundary structures in soft X-ray observations and holds substantial scientific and practical value. Full article

Eddy current testing (ECT) has become a widely adopted technique for non-destructive testing (NDT) due to its effectiveness in detecting surface and near-surface defects in conductive materials. However, traditional methods mainly focus on defect detection and face significant challenges in extracting geometric information such as defect size and shape, which is crucial for structural health monitoring (SHM) and remaining useful life (RUL) assessment. To address these challenges, this study proposes a defect reconstruction approach based on a complex-valued convolutional neural network (CV-CNN), which directly leverages both amplitude and phase information inherent in complex-valued impedance signals. The proposed framework employs convolution, pooling, and activation operations specifically designed within the complex-valued domain to facilitate the high-fidelity reconstruction of defect morphology as well as precise multi-class defect classification. Notably, this approach processes the complete complex-valued signal without relying on prior structural parameters or baseline data, thereby achieving substantial improvements in both defect visualization and classification performance. Moreover, when compared to a complex-valued fully convolutional neural network (CV-FCNN), CV-CNN demonstrates a superior average classification accuracy of 85%, significantly outperforming the CV-FCNN model. Experimental results on carbon steel specimens with standard electrical discharge machining (EDM) notches under multi-frequency excitation confirm these advantages. This contribution provides a promising solution in the field of NDT for intelligent and precise defect detection. Full article

In high-mobility communication scenarios, leveraging reconfigurable intelligent surfaces (RISs) to assist orthogonal time frequency space (OTFS) systems proves advantageous. Nevertheless, the integration of RIS into OTFS systems increases the complexity of channel estimation (CE). Utilizing the benefits of machine learning (ML) to address such intricate issues holds the potential to reduce CE complexity. Despite this potential, there is a lack of investigations of ML-based CE in RIS-assisted OTFS systems, leaving significant gaps and posing challenges for intelligent applications. Moreover, ML-based CE methods encounter numerous difficulties, including intricate parameter tuning and long training time. Motivated by the inherent advantages of the single-hidden layer feed-forward network structure, we introduce extreme learning machine (ELM) into RIS-assisted OTFS systems to improve CE accuracy. In this method, we incorporate a threshold-based approach to extract initial features, aiming to remedy the inherent limitations of the ELM network, such as inadequate network parameters compared to the deep learning network. This initial feature extraction contributes to an enhanced ELM learning ability, leading to improved CE accuracy. Applying the classic message passing algorithm for data symbol detection, simulation results demonstrate the effectiveness of the proposed method in improving the symbol detection (SD) performance of RIS-assisted OTFS systems. Furthermore, the SD performance exhibits its robustness against variations in modulation order, maximum velocity, and the number of sub-surfaces. Full article

Accurate power load forecasting is crucial for ensuring grid stability, optimizing economic dispatch, and facilitating renewable energy integration in modern smart grids. However, real load forecasting is often disturbed by the inherent non-stationarity and multi-factor coupling effects. To address this problem, a novel hybrid forecasting framework based on adaptive mode decomposition (AMD) and improved least squares support vector machine (ILSSVM) is proposed for effective short-term power load forecasting. First, AMD is utilized to obtain multiple components of the power load signal. In AMD, the minimum energy loss is used to adjust the decomposition parameter adaptively, which can effectively decrease the risk of generating spurious modes and losing critical load components. Then, the ILSSVM is presented to predict different power load components, separately. Different frequency features are effectively extracted by using the proposed combination kernel structure, which can achieve the balance of learning capacity and generalization capacity for each unique load component. Further, an optimized genetic algorithm is deployed to optimize model parameters in ILSSVM by integrating the adaptive genetic algorithm and simulated annealing to improve load forecasting accuracy. The real short-term power load dataset is collected from Guangxi region in China to test the proposed forecasting framework. Extensive experiments are carried out and the results demonstrate that our framework achieves an MAPE of 1.78%, which outperforms some other advanced forecasting models. Full article

Acoustic data inherently contain a variety of information, including indicators of abnormal symptoms. In this study, we propose a method for detecting abnormal symptoms by converting acoustic data into spectrogram representations and applying a deep learning model. Spectrograms effectively capture the temporal and frequency characteristics of acoustic signals. In this work, we extract key features such as spectrograms, Mel-spectrograms, and MFCCs from raw acoustic data and use them as input for training a convolutional neural network. The proposed model is based on a custom ResNet architecture that incorporates Bottleneck Residual Blocks to improve training stability and computational efficiency. The experimental results show that the model trained with Mel-spectrogram data achieved the highest classification accuracy at 97.13%. The models trained with spectrogram and MFCC data achieved 95.22% and 93.78% accuracy, respectively. The superior performance of the Mel-spectrogram model is attributed to its ability to emphasize critical acoustic features through Mel-filter banks, which enhances learning performance. These findings demonstrate the effectiveness of spectrogram-based deep learning models in identifying latent patterns within acoustic data and detecting abnormal symptoms. Future research will focus on applying this approach to a wider range of acoustic domains and environments. The results of this study are expected to contribute to the development of disease surveillance systems by integrating acoustic data analysis with artificial intelligence techniques. Full article

Under cavitation conditions, hydraulic turbines can suffer from mechanical damage, which will shorten their useful life and reduce power generation efficiency. Timely detection of cavitation phenomena in hydraulic turbines is critical for ensuring operational reliability and maintaining energy conversion efficiency. However, extracting cavitation features is challenging due to strong environmental noise interference and the inherent non-linearity and non-stationarity of a cavitation hydroacoustic signal. A multi-index fusion adaptive cavitation feature extraction and cavitation detection method is proposed to solve the above problems. The number of decomposition layers in the multi-index fusion variational mode decomposition (VMD) algorithm is adaptively determined by fusing multiple indicators related to cavitation characteristics, thus retaining more cavitation information and improving the quality of cavitation feature extraction. Then, the cavitation features are selected based on the frequency characteristics of different degrees of cavitation. In this way, the detection of incipient cavitation and the secondary detection of supercavitation are realized. Finally, the cavitation detection effect was verified using the hydro-acoustic signal collected from a mixed-flow hydro turbine model test stand. The detection accuracy rate and false alarm rate were used as evaluation indicators, and the comparison results showed that the proposed method has high detection accuracy and a low false alarm rate. Full article

Accurate fault diagnosis in analog circuits faces significant challenges owing to the inherent complexity of fault data patterns and the limited feature representation capabilities of conventional methodologies. Addressing the limitations of current convolutional neural networks (CNN) in handling heterogeneous fault characteristics, this study presents an efficient channel attention-enhanced multi-input CNN framework (ECA-MI-CNN) with dual-domain feature fusion, demonstrating three key innovations. First, the proposed framework addresses multi-domain feature extraction through parallel CNN branches specifically designed for processing time-domain and frequency-domain features, effectively preserving their distinct characteristic information. Second, the incorporation of an efficient channel attention (ECA) module between convolutional layers enables adaptive feature response recalibration, significantly enhancing discriminative feature learning while maintaining computational efficiency. Third, a hierarchical fusion strategy systematically integrates time-frequency domain features through concatenation and fully connected layer transformations prior to classification. Comprehensive simulation experiments conducted on Butterworth low-pass filters and two-stage quad op-amp dual second-order low-pass filters demonstrate the framework’s superior diagnostic capabilities. Real-world validation on Butterworth low-pass filters further reveals substantial performance advantages over existing methods, establishing an effective solution for complex fault pattern recognition in electronic systems. Full article

Background: In deep learning-based epilepsy prediction and classification, enhancing the extraction of electroencephalogram (EEG) features is crucial for improving model accuracy. Traditional supervised learning methods rely on large, detailed annotated datasets, limiting the feasibility of large-scale training. Recently, self-supervised learning approaches using masking-and-reconstruction strategies have emerged, reducing dependence on labeled data. However, these methods are vulnerable to inherent noise and signal degradation in EEG data, which diminishes feature extraction robustness and overall model performance. Methods: In this study, we proposed a self-supervised learning Transformer network enhanced with Adaptive Frequency-Time Attention (AFTA) for learning robust EEG feature representations from unlabeled data, utilizing a masking-and-reconstruction framework. Specifically, we pretrained the Transformer network using a self-supervised learning approach, and subsequently fine-tuned the pretrained model for downstream tasks like seizure prediction and classification. To mitigate the impact of inherent noise in EEG signals and enhance feature extraction capabilities, we incorporated AFTA into the Transformer architecture. AFTA incorporates an Adaptive Frequency Filtering Module (AFFM) to perform adaptive global and local filtering in the frequency domain. This module was then integrated with temporal attention mechanisms, enhancing the model’s self-supervised learning capabilities. Result: Our method achieved exceptional performance in EEG analysis tasks. Our method consistently outperformed state-of-the-art approaches across TUSZ, TUAB, and TUEV datasets, achieving the highest AUROC ($0.891$), balanced accuracy ($0.8002$), weighted F1-score ($0.8038$), and Cohen’s kappa ($0.6089$). These results validate its robustness, generalization, and effectiveness in seizure detection and classification tasks on diverse EEG datasets. Full article

RGB-Thermal (RGBT) semantic segmentation is an emerging technology for identifying objects and materials in high dynamic range scenes. Thermal imaging particularly enhances feature extraction at close range for applications such as textile damage detection. In this paper, we present RGBT-Textile, a novel dataset specifically developed for close-range textile and damage segmentation. We meticulously designed the data collection protocol, software tools, and labeling process in collaboration with textile scientists. Additionally, we introduce ThermoFreq, a novel thermal frequency normalization method that reduces temperature noise effects in segmentation tasks. We evaluate our dataset alongside six existing RGBT datasets using state-of-the-art (SOTA) models. Experimental results demonstrate the superior performance of the SOTA models with ThermoFreq, highlighting its effectiveness in addressing noise challenges inherent in RGBT semantic segmentation across diverse environmental conditions. We make our dataset publicly accessible to foster further research and collaborations. Full article

Accurate interval forecasting of wind power is crucial for ensuring the safe, stable, and cost-effective operation of power grids. In this paper, we propose a hybrid deep learning model for day-ahead wind power interval forecasting. The model begins by utilizing a Gaussian mixture model (GMM) to cluster daily data with similar distribution patterns. To optimize input features, a feature selection (FS) method is applied to remove irrelevant data. The empirical wavelet transform (EWT) is then employed to decompose both numerical weather prediction (NWP) and wind power data into frequency components, effectively isolating the high-frequency components that capture the inherent randomness and volatility of the data. A convolutional neural network (CNN) is used to extract spatial correlations and meteorological features, while the bidirectional gated recurrent unit (BiGRU) model captures temporal dependencies within the data sequence. To further enhance forecasting accuracy, a multi-head self-attention mechanism (MHSAM) is incorporated to assign greater weight to the most influential elements. This leads to the development of a day-ahead wind power interval forecasting model based on GMM-FS-EWT-CNN-BiGRU-MHSAM. The proposed model is validated through comparison with a benchmark forecasting model and demonstrates superior performance. Furthermore, a comparison with the interval forecasts generated using the NPKDE method shows that the new model achieves higher accuracy. Full article

In the electric locomotive traction transmission system, a four-quadrant rectifier has a high fault rate owing to the complicated control and bad operating conditions, and the fault directly affects the system’s safety and stability. To address such an issue, a rectifier fault diagnosis approach regarding a local tangent space alignment (LTSA) dimensionality reduction to optimize the high-dimensional energy entropy feature is proposed. Firstly, the fault signal is analyzed by using different wavelet functions through wavelet packet multi-resolution decomposition technology so as to extract the frequency band information of the signal. Each wavelet function corresponds to a specific frequency band; the energy–information entropy ratio of each frequency band coefficient is calculated, and then, the wavelet function and optimal frequency band, which are appropriate for the fault signal, are determined. Secondly, the energy entropy of each coefficient in the optimal frequency band is calculated to form the high-dimensional energy entropy feature. The LTSA algorithm is adopted to optimize the high-dimensional feature, through the fault sample number and clustering results, solve the difficulty of selecting the inherent dimension and nearest neighbor number in high-dimensional data, and obtain the simple and effective low-dimensional feature vector to describe the fault features, which reduces the conflict and redundancy between features. Finally, the optimized fault features are used as an input to the classifier support vector machine (SVM), and the fault types are obtained through training and testing. To validate the efficacy of the presented approach, it is tested from the aspects of noise environment, sample proportion and algorithm complexity, and compared with advanced methods. The results indicate that the proposed technique attains an average accuracy of 99.0625% in four-quadrant rectifier fault diagnosis. Under a different signal-to-noise ratio (SNR) and different training and test ratios, the average value after 30 diagnoses is better. Compared with other methods, this method shows a high diagnostic rate and strong robustness in terms of output voltage, noise, training and test ratio. Full article