Search Results (358)

Sleeper voids, or hanging sleepers, in ballasted railway tracks threaten structural safety and serviceability. This study proposes a physics-guided quantitative ground-penetrating radar (GPR) framework for detecting hanging sleepers using high-frequency antennas ($f\ge 1.5$ GHz). The framework integrates signal post-processing, sleeper-region localization, time-domain peak searching with polarity consideration, and continuous wavelet transform (CWT) as auxiliary verification. By exploiting the physical geometric relationship between the sleeper and ballast interfaces, the method quantitatively estimates their elevation difference and identifies hanging sleepers according to engineering criteria. Spatial continuity constraints are further introduced to reduce false detections. Validation through gprMax simulations and field experiments demonstrates effective detection and severity assessments, providing a physically interpretable solution for automated railway inspection. Full article

This paper investigates the deployment of four electric vehicle (EV) fast-charging stations (FCSs) in a commercial facility’s parking area, where multiple service centers operate on varying schedules. The commercial load demand is modeled using Monte Carlo Simulation (MCS), introducing realistic stochastic variability and overlapping power patterns with FCS operations. A single-point sensing strategy at the point of common coupling (PCC) is adopted for load disaggregation. Continuous Wavelet Transform (CWT) is employed for feature extraction, and multiclass classification is performed using Error-Correcting Output Codes (ECOC). Under commercial load interference, conventional machine-learning classifiers achieve a macro classification accuracy of 89.53%, with the lowest class accuracy dropping to 76.74%. To address this limitation, a deep learning (DL)-based framework is implemented. Simulation results demonstrate that the proposed DL approach improves overall classification accuracy from 89.53% to 100%, corresponding to a 10.47 percentage-point absolute improvement, an 11.7% relative gain, and complete elimination of misclassification errors. Notably, the most affected charging station class (FCS₂) accuracy increases from 76.74% to 100%. These results demonstrate that the proposed deep learning framework reliably detects FCS activations even under overlapping, variable, and high-power commercial load conditions, enabling more efficient energy management and optimal utilization of electrical resources, reduced energy waste, and enhanced sustainability of EV charging infrastructure within commercial facilities. Full article

Background/Objectives: Predicting individual response to depression therapy prior to treatment initiation remains a critical clinical challenge, as the response rate to both selective serotonin reuptake inhibitors (SSRIs) and repetitive transcranial magnetic stimulation (rTMS) is approximately 50%, leaving treatment selection largely trial-based. This study presents a computer-aided decision (CAD) framework that predicts depression therapy outcomes from pre-treatment electroencephalogram (EEG) signals using advanced time-frequency representations and pretrained convolutional neural networks (CNNs). Methods: EEG signals from 30 SSRI patients and 46 rTMS patients are transformed into time-frequency images using Continuous Wavelet Transform (CWT), Variational Mode Decomposition (VMD), and their pixel-level fusion. Four pretrained CNN architectures, including ResNet-18, MobileNet-V3, EfficientNet-B0, and TinyViT-Hybrid, are fine-tuned and evaluated under both image-independent and subject-independent 6-fold cross-validation (CV). Results: Results reveal a clear therapy-specific pattern: CWT-based representations yield superior discrimination for SSRI outcome prediction, with ResNet-18 achieving 99.43% image-level accuracy, while VMD-based representations are statistically superior for rTMS outcome prediction, with ResNet-18 reaching 98.77%. Pixel-level fusion of CWT and VMD does not consistently improve performance over the best individual representation in either therapy context. Pairwise Wilcoxon signed-rank tests confirm a two-tier architectural hierarchy in which ResNet-18 and TinyViT-Hybrid significantly outperform MobileNet-V3 and EfficientNet-B0 across all conditions, while remaining statistically indistinguishable from each other. At the subject level, the framework achieves 82.50% and 83.53% accuracy for SSRI and rTMS, respectively, under strict subject-independent evaluation. Per-channel analysis reveals occipital dominance for SSRI under CWT and frontotemporal dominance for rTMS under VMD, consistent with known neurophysiological mechanisms. Conclusions: These findings demonstrate that the choice of time-frequency representation is therapy-specific and at least as important as architectural complexity, and that competitive performance can be achieved without recurrent or attention layers by combining well-designed spectral images with a simple pretrained residual network. Full article

Background: Parkinson’s disease is a progressive neurodegenerative disorder. Early PD detection plays a key role in effective therapy. Electroencephalography is a neuroimaging technique used to analyze brain abnormalities, such as those seen in patients with PD. However, the complex nature of EEG data requires advanced signal processing and classification methods. Methods: This study systematically evaluates three time-frequency (TF) representation techniques, namely discrete wavelet transform (DWT), continuous wavelet transform (CWT), and synchrosqueezing transform (SST), along with four pretrained convolutional neural network architectures for EEG-based PD detection. The experiments were performed using the San Diego dataset. Image-wise and subject-wise 5-fold cross-validation were employed to assess performance and generalization capability. Results: CWT and SST consistently outperform DWT across all evaluated architectures in image-wise CV evaluation. At the image-wise level, the CWT-EfficientNet-B0 model achieved 97.28% accuracy for HC vs. PD-OFF classification, while SST-EfficientNet-B0 reached 97.26% accuracy for HC vs. PD-ON classification. In subject-wise evaluation, acceptable accuracies of up to 84% were achieved, indicating the ability of the framework in learning PD patterns for unseen subjects. Conclusions: These findings demonstrate that the choice of TF representation has a strong impact on classification performance and that lightweight CNN architectures can achieve high image-wise accuracy with reduced computational cost. Full article

In modern industrial systems, the fault diagnosis of rotating machinery is crucial for ensuring safe equipment operation. However, practical fault data are often contaminated by noise, and the scarcity of samples across fault conditions makes effective feature extraction challenging. Moreover, single-sensor measurements provide limited and incomplete information, further degrading the accuracy and reliability of diagnostic models. To address these challenges, this paper proposes an explainable intelligent fault diagnosis for rotating machinery via multi-source information fusion under noisy environments and small sample conditions. Firstly, a multi-sensor data intelligent fusion module (MSDIFM) is developed. It converts multi-sensor vibration signals into time–frequency maps via continuous wavelet transform (CWT). Pixel-level cross-channel fusion is then performed using a variance-driven dynamic weighting strategy to generate a unified fusion map, adaptively highlighting high information channels. Secondly, a multi-dimensional adaptive asymmetric soft-threshold residual shrinkage block (MASRSB) is proposed to implement differentiated and dynamic threshold control for positive and negative features, enhancing representation and discrimination capabilities. Thirdly, the multi-scale Swin Transformer (MSSwin-T) is designed. This module significantly enhances the model’s feature extraction capability by expanding multi-level receptive fields, strengthening key channel representations, and reinforcing cross-window feature interactions. Finally, to validate the effectiveness of the proposed method, experiments are conducted on both the Case Western Reserve University (CWRU) dataset and the self-created PT890 dataset. Results demonstrate that the proposed method exhibits outstanding diagnostic performance and robustness under noisy conditions and with small sample sizes. Full article

Response latency and sensor noise are universal challenges in closed-loop control systems. In the context of semi-active suspensions, these issues also exist and manifest as critical bottlenecks. Due to the highly transient nature of road shocks, the inherent physical actuation delays of the hardware, combined with the phase lag introduced by traditional signal filtering, often cause the control response to significantly lag behind the physical excitation. To address this issue from a predictive perspective, this study proposes a Physics-Informed Gated Convolutional Neural Network (PI-GCNN) designed to predict future multi-modal energy evolution, thereby enabling feedforward control. Unlike traditional feedback mechanisms, the proposed framework employs the Continuous Wavelet Transform (CWT) to convert short-horizon inertial data into time–frequency scalograms, effectively isolating transient shock features from background vibrations. A novel physics-guided gating mechanism is embedded within the network architecture to regulate feature activation. This mechanism is trained using an asymmetric sparse physics loss, which combines L1 regularization with adaptive spectral consistency constraints to enforce noise suppression on flat roads while ensuring sensitivity to impacts. Extensive validation was conducted using high-fidelity heavy truck simulations and the public PVS 9 real-world dataset. The results confirm that the PI-GCNN achieves a predictive phase lead of approximately 100–200 ms over real-time baselines, creating a valuable actuation window for suspension dampers. Furthermore, the model demonstrates exceptional computational efficiency, with a parameter count of 0.10 M and a single-frame inference latency of 0.25 ms, making it highly suitable for deployment on resource-constrained automotive edge computing platforms. Full article

Time–frequency (TF) characterization of electromyographic (EMG) bursts is essential for accurately assessing muscle function, particularly when the signals exhibit a high degree of nonstationarity. In this exploratory study, we investigated the temporal dynamics of the spectral components associated with short-latency EMG bursts using several TF analysis techniques. Specifically, we compared the performance and interpretability of spectrograms obtained via the short-time Fourier transform (STFT), the continuous wavelet transform (CWT), and noise-assisted multivariate empirical mode decomposition (NA-MEMD), applied to EMG signals recorded from the biceps femoris muscle of freely moving rats in an animal model of Parkinson’s disease, acquired using chronically implanted bipolar electrodes during treadmill locomotion. For each method, we evaluated its effectiveness in capturing transient variations in frequency content, the stability of extracted features across bursts, and the extent to which these features reflect physiologically meaningful aspects of muscle activation. The results show that TF approaches reveal complementary information about burst structure; NA-MEMD provides greater adaptability to nonlinear and nonstationary components, whereas STFT- and CWT-based representations offer more controlled and comparable analyses. Overall, these findings highlight the value of TF analysis as a methodological tool for evaluating muscle function and provide a solid foundation for selecting analytical strategies in studies where EMG bursts exhibit complex and highly variable spectral profiles. Full article

The Hulukou-Xiangbiling section of the Jinsha River is located in a typical high-mountain gorge area characterized by a complex geological environment, rendering it highly susceptible to landslide disasters. To reveal the deformation mechanisms of typical landslides in this region under hydrological effects, this study employed the Small Baseline Subset InSAR (SBAS-InSAR) technique to process multi-track Sentinel-1 SAR images acquired between 2021 and 2024. Long-term deformation time series were extracted for the Xiaxiaomidi and Chenjiatian landslides. On this basis, a systematic multi-scale coupling analysis of the deformation characteristics was conducted using trend-cycle decomposition, Continuous Wavelet Transform (CWT), Cross Wavelet Transform (XWT), and Wavelet Coherence (WTC). The results indicate that although the two landslides are located in the same river section, their deformation mechanisms and hydrological response patterns differ significantly. The deformation of the Xiaomidi landslide is mainly concentrated in the lower part of the slope, exhibiting a characteristic of continuous acceleration. The analysis demonstrates that the evolution of this landslide is primarily controlled by hydrodynamic processes such as toe unloading, water body erosion, and water level fluctuations. In contrast, the Chenjiatian landslide displays a distinct dominant cycle of 365 days, manifesting as a composite mode of long-term creep superimposed with seasonal acceleration. Its deformation shows a high correlation with rainfall (correlation coefficient > 0.9), with a lag effect of approximately 1 to 2 months. This reflects the dominant role of rainfall infiltration and pore pressure transfer in the landslide dynamics. Full article

Background/Objectives: Dementia is a progressive neurodegenerative disorder for which accurate and timely diagnosis remains a major clinical challenge. Electroencephalography (EEG) offers a noninvasive and cost-effective means of capturing neurophysiological alterations, motivating the development of reliable EEG-based automated diagnostic frameworks. This study aims to systematically examine how different time–frequency representations (TFRs) affect dementia classification performance within a unified multi-channel EEG image fusion framework. Methods: Resting-state, eyes-closed EEG recordings from 88 subjects, including Alzheimer’s disease, frontotemporal dementia, and cognitively normal controls, were preprocessed and segmented. Channel-wise signals were converted into two-dimensional time–frequency images using Short-Time Fourier Transform (STFT), Continuous Wavelet Transform (CWT), Hilbert–Huang Transform (HHT), Wigner–Ville Distribution (WVD), or Constant-Q Transform (CQT). Images from 19 EEG channels were fused into a structured grid and classified using pretrained convolutional neural networks, including MobileNetV2, ResNet-50, and InceptionV3. Results: Results indicate that classification performance is highly dependent on the chosen TFR. The STFT-based representation combined with InceptionV3 achieved the highest accuracy, reaching 98.8% with random splitting and 84.3% with subject-wise splitting, outperforming previous studies. CQT also showed competitive performance, whereas HHT and WVD were less effective. Gradient-weighted class activation mapping provided interpretable visualization of physiologically relevant EEG channel contributions. Conclusions: The proposed framework demonstrates the importance of structured multi-channel fusion and systematic TFR evaluation for robust and interpretable EEG-based dementia classification and serves as a foundation for future cross-dataset validation. Full article

Early detection of fire-related risks in lithium-ion batteries (LIBs) remains a critical challenge, as conventional protection mechanisms typically activate only after irreversible degradation or macroscopic failure occurs. In this study, an innovative sensor-based diagnostic framework is proposed for proactive fire prediction in LIBs by simultaneously monitoring low-frequency and high-frequency electrical signatures generated during battery charge–discharge processes. An electromagnetic (EM) antenna sensor and a high-frequency current transformer (HFCT) sensor were employed to capture complementary voltage- and current-based transient signals associated with internal degradation phenomena. Cell-level experiments were conducted under various C-rates and temperature conditions, including high-stress environments, while module-level validation was performed on a 4-series, 1-parallel (4S1P) configuration at a 2C-rate under ambient temperature. Time–frequency characteristics of the measured signals were systematically evaluated using MATLAB-based continuous wavelet transform (CWT) and discrete wavelet transform (DWT) techniques. The results reveal that degradation-induced transient events exhibit non-stationary, impulsive voltage and current signatures with distinct frequency-band localization, which intensify with increasing C-rate, elevated temperature, and aging progression. At the module level, although signal amplitudes were partially attenuated due to current redistribution, characteristic wavelet energy patterns and time–frequency concentrations remained clearly distinguishable, demonstrating the scalability of the proposed approach. The combined EM antenna–HFCT sensing strategy, together with multi-resolution wavelet analysis, enables effective phenomenological differentiation between normal operational noise and incipient internal fault signatures well before conventional thermal or capacity-based indicators become evident. These findings demonstrate feasibility of the proposed method for early-stage fault diagnosis and highlight its potential applicability to advanced battery management systems for proactive fire prevention in large-scale energy storage and electric vehicle applications. Unlike conventional voltage-, temperature-, or gas-based diagnostics, the proposed approach enables the detection of incipient degradation phenomena at the microsecond scale by exploiting complementary low- and high-frequency electrical signatures. This study provides experimental evidence that wavelet-based EM and HFCT sensing can identify MISC-related precursors significantly earlier than conventional battery management indicators. Full article

Under practical operating conditions, intelligent fault diagnosis of permanent magnet synchronous motors (PMSMs) is often hindered by the shortage of effective fault samples. To address this issue, this paper proposes a twin-data-driven transfer learning-based diagnostic method for PMSM inter-turn short-circuit faults. First, a finite element model of the motor is established in Ansys to generate inter-turn short-circuit twin data, thereby enriching the source-domain samples. Second, continuous wavelet transform (CWT) is employed to convert stator current signals into multi-scale time–frequency feature maps, which are then fed into a feature extraction network constructed by integrating a residual network (ResNet) into an efficient channel attention mechanism (ECA) to achieve effective fusion of local and global time–frequency features. Finally, a joint loss function combining multi-kernel maximum mean discrepancy (MK-MMD) and a domain-adversarial neural network (DANN) is introduced to align feature distributions and perform adversarial optimization, enhancing cross-domain invariance and improving fault recognition capability. Experimental results demonstrate that the proposed REDM method achieves higher diagnostic accuracy and robustness than several existing intelligent fault diagnosis approaches. Full article

Broken rotor bar faults (BRBFs) in induction motors (IMs) present significant challenges in industrial applications, particularly due to the need for large labeled datasets and fast processing. This study addresses these issues by leveraging transfer learning with classical diagnostic techniques, using experimental 3-phase current and 3-axes vibration signals. The Gramian Angular Field (GAF) technique has been utilized to transform time series data into 2D images, enabling fine-tuning of an EfficientNetB3 model, which achieved 99.83% accuracy in classifying five BRBF severity levels. The proposed strategy also outperforms the state-of-the-art methods using the same experimental data. Similarly, validation with features extracted using Continuous Wavelet Transform (CWT) and Short-Time Fourier Transform (STFT) further confirmed its reliability and superiority. This study also offers enhanced interpretability through Grad-CAM visualizations of the best model, which highlights the critical regions contributing to fault classification. These visualizations enable deeper and simpler understanding of fault mechanisms and support subsequent risk analysis, making the developed model actionable and user-friendly for industrial applications. Full article

To address the limitations of traditional rolling bearing fault diagnosis methods—such as inadequate feature extraction, limited noise robustness, and weak generalization under variable working environments—this study proposes a fault diagnosis framework that integrates parallel axial attention into a ResNet architecture. First, continuous wavelet transform (CWT), known for its inherent noise immunity, is employed to convert vibration signals into time–frequency images, providing a noise-suppressed representation of fault characteristics. Convolutional layers are then applied to reduce image dimensionality and computational complexity. A parallel axial attention module is subsequently introduced to independently capture feature dependencies along the temporal and frequency axes, enhancing the model’s ability to focus on discriminative fault-related regions while filtering out irrelevant noise. ResNet serves as the backbone network for deep feature learning and classification. Experiments on the Case Western Reserve University bearing dataset show that the proposed method achieves an average diagnostic accuracy exceeding 99.67% under multiple operating regimes. Notably, it maintains an accuracy above 95% even in high-noise environments with signal-to-noise ratios (SNRs) ranging from −4 dB to 4 dB, significantly outperforming several existing convolutional neural network-based approaches. This demonstrates the strong anti-noise capability and robustness resulting from the synergistic combination of time–frequency analysis and attention mechanisms. Furthermore, cross-dataset validation using the Southeast University bearing dataset confirms the strong generalization ability of the method. These results indicate that the proposed approach exhibits excellent diagnostic performance and practical applicability in noisy and complex industrial environments. Full article

Tiles are commonly used as architectural finishing materials, but are prone to debonding defects due to construction and environmental factors in engineering applications. Therefore, effective detection of tile debonding holds significant engineering relevance. This study proposes a tile debonding detection method based on impact sound signal features and a dual-branch convolutional neural network. The sound signals collected through tapping are transformed into two types of two-dimensional feature maps using Mel-frequency cepstral coefficients (MFCCs) and continuous wavelet transform (CWT), which are then fed in parallel into the dual-branch convolutional neural network for feature extraction and fusion. Finally, tile debonding classification is performed in the classifier module. Experimental results show that the proposed model achieves a classification accuracy of 98.5% under laboratory conditions. Moreover, it demonstrates strong robustness under varying noise levels and sound pressure conditions, maintaining an accuracy of 82% in a 75 dB human voice noise environment. Field validation in real-world engineering environments yields an accuracy of 91.5%. These findings indicate that the proposed method, which combines MFCC and CWT features with a dual-branch convolutional neural network architecture, enables high-precision identification of tile debonding defects. Full article

Bearings, as core components of mechanical equipment, play a critical role in ensuring equipment safety and reliability. Early fault detection holds significant importance. Addressing the challenges of insufficient robustness in bearing fault diagnosis under industrial high-noise conditions and the difficulty of extracting fault features from a single modality, this study proposes a three-channel multimodal fault diagnosis method that integrates a Convolutional Auto-Encoder (CAE) with a dual attention mechanism (M-CNNBiAM). This approach provides an effective technical solution for the precise diagnosis of bearing faults in high-noise environments. To suppress substantial noise interference, a CAE denoising module was designed to filter out intense noise, providing high-quality input for subsequent diagnostic networks. To address the limitations of single-modal feature extraction and restricted generalization capabilities, a three-channel time–frequency signal joint diagnosis model combining the Continuous Wavelet Transform (CWT) with an attention mechanism was proposed. This approach enables deep mining and efficient fusion of multi-domain features, thereby enhancing fault diagnosis accuracy and generalization capabilities. Experimental results demonstrate that the designed CAE module maintains excellent noise reduction performance even under −10 dB strong noise conditions. When combined with the proposed diagnostic model, it achieves an average diagnostic accuracy of 98% across both the CWRU and self-test datasets, demonstrating outstanding diagnostic precision. Furthermore, under −4 dB noise conditions, it achieves a 94% diagnostic accuracy even without relying on the CAE denoising module. With a single training cycle taking only 6.8 s, it balances training efficiency and diagnostic performance, making it well-suited for real-time, reliable bearing fault diagnosis in industrial environments with high noise levels. Full article