Search Results (766)

This study assesses the possibility of identifying non-through defects in dielectric coatings, specifically interfacial defects located at the metal–coating boundary, by means of high-voltage non-destructive testing. It is demonstrated that partial discharges causing characteristic distortions of the applied test-voltage pulse can be used as a reliable diagnostic feature of such defects. Using an equivalent capacitive representation of a defective coating, a relationship is established between the apparent charge and the geometry of the air-filled gap. The proposed approach is supported by COMSOL simulations of the electric-field distribution and by experiments performed on Plexiglas specimens containing blind holes of different depths. In addition, a method is developed for isolating the partial-discharge signal based on a weighted sum of increments in the root-mean-square deviations of the second derivative of the voltage waveform. The resulting relationships enable estimation of the residual coating thickness in the defect region. Full article

Low-strain reflection testing is widely used for the rapid screening of pile integrity, but its interpretation still relies heavily on manual judgment. This study proposes a dual representation learning framework for classifying the integrity of building foundation piles from low-strain testing records. A dataset containing 1139 piles from engineering projects was established and divided into four integrity classes. Each record was represented in two complementary forms: structured features extracted from engineering parameters and waveform characteristics, and a redrawn waveform image generated from coordinate point data. Support vector machine (SVM), random forest (RF), and convolutional neural network (CNN) models were used as single modality baselines, and their performance was compared with that of a multimodal neural network (MNN) trained on paired structured and image inputs. The multimodal model achieved the highest overall accuracy on the main evaluation subset, reaching 84.65%, whereas the random forest achieved the best Macro-Recall and Macro-F1. This result suggests that multimodal fusion mainly improved overall robustness rather than consistently enhancing performance across all classes. Clearly intact piles and severely defective piles were easier to identify, whereas Class II remained the most difficult category because of its borderline signal characteristics. In the supplementary external validation set, the same ranking of model performance was observed, and the multimodal model achieved an accuracy of 85%. These results indicate that the proposed framework has strong potential for computer-assisted screening of building foundation piles. Full article

This editorial synthesizes the key findings from 17 original research articles featured in the Special Issue on “Intelligent and Integrated Approaches for Efficient Oil and Gas Development.” The collection demonstrates a paradigm shift from purely data-driven methods toward physics-informed, interpretable, and operationally deployable intelligent systems across the upstream lifecycle. Advances span intelligent drilling with real-time model predictive control frameworks achieving sub-20 ms execution times and bottomhole pressure fluctuations below 0.30 MPa; AI-assisted reservoir characterization using multiscale convolutional neural networks, seismic waveform-constrained inversion, and geology-informed transformers that improve sandstone thickness prediction (R² = 0.895) and stratigraphic correlation (F1 = 0.886); production optimization through hybrid decomposition-ensemble models (R² = 0.954) and improved XGBoost (R² = 0.989); and enhanced oil recovery via self-assembled foam systems and polymer injector designs. Fundamental geochemical studies on the Qiongzhusi Formation shale and tight sandstone gas in the Ordos Basin provide critical geological constraints. The editorial identifies persistent challenges, including real-time performance versus physical fidelity, interpretability and uncertainty quantification, multi-scale integration, and generalizability across diverse geological settings. Future directions highlight reinforcement learning for autonomous operations, physics-informed digital twins, generative AI for subsurface scenario modelling, and integration with carbon capture, utilization, and storage. This Special Issue advances the convergence of petroleum engineering, artificial intelligence, and Earth sciences toward intelligent, secure, and sustainable hydrocarbon development. Full article

Background/Objectives: Although deep learning methods have achieved promising performance in recent years, comparatively less attention has been given to explicitly modeling periodic and multi-scale temporal dynamics for ECG-specific representation learning within TimesNet-based frameworks. In this work, we propose an ECG-specific TimesNet-based framework for multi-label classification of multi-lead ECG recordings that incorporates periodicity-aware temporal modeling. Methods: The proposed framework utilizes Fast Fourier Transform (FFT)-guided temporal decomposition to identify dominant frequency components and reshapes ECG sequences into period-aligned representations to better capture intra-period morphological patterns and inter-period rhythm dependencies. Multi-scale convolutional TimesBlocks are further employed to learn rhythm-aware and morphology-aware temporal representations. Results: The proposed framework was evaluated on the PTB-XL dataset using two experimental settings: Three-Class classification (NORM, AFIB, PVC) and Five-Class classification (NORM, AFIB, MI, PVC, STTC). Experiments were conducted using a one-vs-rest multi-label learning strategy with independent class probability estimation. The framework achieved mean one-vs-rest test AUC values of 0.956 and 0.913 for the Three-Class and Five-Class settings, respectively. Experimental results indicated that the reduced classification complexity in the Three-Class setting was associated with improved feature separability, more stable decision boundaries, and enhanced discriminative representation learning. Latent-space visualization using UMAP and PCA demonstrated clearer clustering in the Three-Class configuration, while gradient-based interpretability analysis highlighted physiologically relevant ECG waveform regions contributing to model predictions. In addition, computational profiling demonstrated practical feasibility with approximately 1.957 million trainable parameters, 13.14 GFLOPs computational complexity, 5.230 ms average inference latency per ECG recording, and a throughput of approximately 191 ECG recordings per second on GPU hardware. Conclusions: These findings suggest that periodicity-aware temporal modeling can improve ECGF representation learning while demonstrating practical potential for computationally efficient and interpretable automated ECG analysis applications. Full article

This paper aims to explore non-traveling fractal solutions to an extended Hirota–Satsuma–Ito equation (gHSI) that contains several well-known equations arising in fluid dynamics. Our approach is based on the application of a new variable-separation technique that transfers the governing equation into several solvable forms. Some of these equations can also be solved with standard analytical methods. We employ the modified generalized exponential rational function method (mGERFM), resulting in a varied set of exact analytical solutions. These solutions exhibit a wide range of structural types, such as periodic, rational, hyperbolic, and hybrid configurations. A notable feature of our solutions is that the obtained solutions include several free functions, which provide a systematic way to modify the structure of the waveforms in the solutions. By appropriately selecting these free functions, several categories of dromion-type solutions are introduced. These non-traveling fractal solutions appear to be the first of their kind derived for this equation. The analytical findings are supported by illustrations that demonstrate the complex temporal and spatial dynamics that are characteristic of these solutions. The proposed approach opens a systematic path to non-traveling waves in higher-dimensional systems, where functional flexibility gives rise to self-similar fractal structures, and could be adapted to other equations in physics and engineering. Full article

Controlling deposition parameters is fundamental to obtaining the desired properties of cathodic arc physical vapor deposition (PVD) coatings. Achieving uniform coatings on tools with complex, sharp geometries remains a significant challenge due to localized ion flux concentration. Pulsing the substrate bias is an effective way of controlling deposition energy. However, while widely used in cathodic arc PVD, the relationship between the actual bias waveform, coating integrity on sharp tool geometries, and resulting machining performance has not been systematically established. This study investigates the effect of pulsed bias duty cycle (20% to 90%) and frequency (1 to 20 kHz) on the microstructural evolution, residual stress state, and machining performance of AlTiN coated tools. Real-time oscilloscope measurements demonstrated that system inductance and capacitance significantly distort the ideal bias waveform. Microstructural analysis via Focused Ion Beam/Scanning Electron Microscopy (FIB/SEM) cross-sectioning confirmed that all bias parameters generated a dense microstructure. While pulse frequency had no significant influence on micromechanical properties or residual stress states, the duty cycle was the dominant variable. High-energy deposition (90% duty cycle) increased hardness to 33.9 GPa but generated severe compressive residual stresses (−5.2 GPa). This extreme compressive stress led to catastrophic edge delamination on sharp solid carbide endmills. Conversely, a low-energy 20% duty cycle generated a coating with lower hardness (29.4 GPa) and a near-neutral stress state (0.5 GPa), effectively preserving the edge integrity. Unlike the endmills, the turning inserts maintained their edge integrity across all deposition conditions. During the high-speed (350 m/min) dry turning of AISI 304 stainless steel, all evaluated coatings exhibited comparable tool life and cutting forces. Wear progression was characterized by rake cratering, combined with abrasion and adhesion-induced attrition on the flank. The results indicate that tool life in this extreme environment is governed primarily by high-temperature thermo-chemical stability rather than initial room-temperature hardness. Lower-energy pulsed bias deposition therefore represents a robust strategy for coating a wide range of tool geometries, delivering equivalent high-speed machining performance while preventing stress-induced delamination on sharp features. Full article

Given the complex operating conditions and latent faults exhibited by electric vehicle charging infrastructure amid massive order volumes, traditional monitoring methods based on thresholds or single statistical metrics struggle to detect dynamic, time-varying anomalies. This paper proposes a method for identifying and tracing the operational status of charging facilities based on the k-shape time-series clustering algorithm. This method directly uses charging current time series as the research object, eliminating the cumbersome manual feature extraction process. By utilizing a shape-based distance (SBD) metric strategy, it overcomes common time-series data issues such as phase shifts and amplitude scaling while preserving the integrity of the time dimension. Through iterative calculation of cluster centroids, the algorithm successfully and adaptively classifies massive amounts of data into typical clusters such as “standard charging,” “deep oscillation,” and “power-limited.” Based on the clustering results, this paper further constructs a “shape-operating condition” mapping mechanism. Combined with a Bayesian posterior probability model, this enables the localization of high-risk “vehicle-charger” combinations statistically associated with abnormal waveforms. Empirical studies demonstrate that this method can effectively identify equipment performance degradation at the micro-level of waveforms and provide prioritized inspection clues for the intelligent operation and maintenance of charging networks. Full article

With the increasing application of microseismic monitoring technology in mines, it is still difficult to automatically distinguish effective signals from noise signals, which limits its popularization and practical performance to a certain extent. This paper systematically analyzes six major identifiable signal patterns in high-noise mine environments, including rock drilling, trackless equipment operation, ore pass dumping, electromagnetic interference, blasting, and effective signals. The effective signals are further subdivided into low-energy and high-energy subcategories, and the generation mechanism of each pattern is discussed in depth. Based on a large number of collected sample data, the AIC algorithm, short-to-long window amplitude ratio, short-window amplitude average, and single-point amplitude triggering method are adopted to extract the recognition features of the above six patterns, including waveform interval time Δt, waveform duration t_c, dominant frequency f_d, number of independent events, and their combinations. Probability statistics are performed on each characteristic value, and an automatic pattern recognition algorithm for mine microseismic waveform characteristics is constructed. Meanwhile, a two-stage intelligent recognition model is established using the convolutional neural network machine learning method. A total of 1500 typical samples are selected and divided into training and test sets at a ratio of 7:3. After 5000 training iterations, the average accuracies of the three classifiers reached 87%, 84%, and 90%, respectively. The intelligent microseismic signal recognition method developed on this basis was field-tested at the Xianglushan Tungsten Mine, achieving a recognition accuracy of 94.9% for low-energy effective events. It shows favorable engineering adaptability and meets the expected research objectives. Full article

Background: Neural stability, defined as trial-by-trial fluctuations in neural responses to the repetitive sensory input, is an indicator of neural processing stability. The auditory brainstem response (ABR) can provide an electrophysiological measure of neural stability. Findings on neural stability differences between autistic and neurotypical individuals are inconsistent, potentially due to methodological differences and sample heterogeneity. This study aimed to investigate the relationship between neural stability in the brainstem and autistic traits in a group of children with and without a diagnosis of autism. We examined whether the degree of neural stability differs based on the evoking stimulus and response component analyzed, and whether neural stability relates to parent-reported autistic traits, as measured by the Autism Spectrum Quotient (AQ) and social responsiveness scale-2 (SRS-2). Methods: In total, 41 participants had usable click ABRs and 34 had usable sABRs. Neural stability was quantified using Pearson correlation analyses between binaurally evoked subaverage ABR waveforms. Parent-reported measures of autistic traits were collected. Results: Neural stability differed across ABR components, with the click ABR being significantly more stable than sABR components. Decreased neural stability is significantly related to autistic traits measured by the AQ but not the SRS-2. There was no significant response component by AQ interaction. Conclusions: Neural stability in the auditory brainstem pathway is linked to individual differences in autistic traits measured by the AQ but not the SRS, implying that early sensory processing neural stability may be related to broader features of autistic traits rather than social communication alone. Full article

To address the challenges of scarce anomaly samples, inadequate modeling of temporal dynamic features, and limited feature selection capability of lightweight models in industrial anomalous sound detection, this paper proposes a method under an unsupervised framework. In the time-domain feature extraction branch, a Lightweight Temporal Pyramid Module (LTPM) is introduced to enhance the multi-scale temporal modeling capability of TgramNet, capturing both short-term and long-term temporal dependencies. In the classification network, the Efficient Channel Attention (ECA) mechanism is embedded into the bottleneck structure of MobileFaceNet to enable adaptive channel recalibration. Furthermore, three waveform-level data augmentation strategies—noise perturbation, time shifting, and amplitude scaling—are adopted. Experimental results on the DCASE 2020 Task 2 dataset demonstrate that the proposed method achieves competitive performance compared with existing approaches, attaining optimal or highly competitive results across multiple machine types. The minimum Area Under the Curve (mAUC) across different machine IDs, along with ROC curve analysis, verifies the stability and generalization capability of the model. This method offers a promising lightweight approach for industrial anomalous sound detection and condition monitoring applications. Full article

Accurate damage characterization in thermoset Carbon Fiber-Reinforced Polymer (CFRP) composites using Acoustic Emission (AE) requires statistically robust and interpretable models. This study employs multinomial logistic regression with forward selection and Type III analysis to identify the minimal set of AE parameters necessary for classifying damage mechanisms (fiber breaks, delamination, matrix cracks) in quasi-isotropic thermoset CFRP laminates under synchronously recorded load conditions. Starting from 18 conventional time- and frequency-domain descriptors, forward selection yielded seven candidate predictors. However, Type III analysis revealed that only four parameters, Load, Initiation Frequency, Amplitude, and Average Frequency, provide unique, statistically significant contributions (p < 0.05). The remaining predictors became redundant once these four were included. Machine learning and deep learning models trained on this minimal feature set achieved validation accuracies up to 98.7% on external specimens. High-frequency components (>1 MHz), as recorded at the sensor location after propagation and sensor convolution, were associated with fiber break events at elevated loads, while delamination events exhibited higher amplitude and lower-frequency content (<200 kHz) compared to matrix crack events. These observed frequency ranges reflect the combined effects of source mechanisms, guided wave dispersion in the 2.4 mm thick laminate, PWAS sensor response, and HDT-based hit segmentation, and are consistent with established AE damage signatures in literature. The results indicate that this four-parameter set is sufficient to classify the labeled AE waveform classes under monotonic tensile loading of quasi-isotropic [45/90/−45/0]_2s laminates, achieving 98.7% agreement with reference labels assigned via waveform morphology and spectral analysis. The proposed approach reduces computational overhead and enhances interpretability for structural health monitoring applications, pending validation across broader material systems and loading scenarios. A limitation of this study is that reference labels were assigned using waveform morphology and spectral analysis, lacking independent physical validation (e.g., microscopy). Full article

Full-waveform inversion (FWI) is a powerful interpretation method in geophysics for inferring high-resolution subsurface models by minimizing the difference between observed and simulated seismic data. In mineral exploration, FWI has shown particular promise for delineating complex ore bodies in hard-rock environments where conventional reflection seismic methods often fail. However, traditional FWI remains computationally expensive due to the iterative solution of forward and adjoint problems. The integration of deep learning, particularly the U-Net architecture, has recently emerged as a promising approach to address these computational challenges. Originally developed for biomedical image segmentation, U-Net employs a symmetric encoder–decoder structure with skip connections, enabling precise localization and efficient feature extraction from complex data. This paper proposes a modified dual-path architecture, termed DU-Net, specifically designed for the simultaneous detection and extraction of high-contrast velocity anomalies (representing potential ore bodies) and reconstruction of the background velocity model. The key innovation lies in parallel processing branches—one dedicated to anomaly segmentation and another to background reconstruction—combined with a specialized composite loss function, SeismoLoss, that independently supervises each component. This design allows the network to focus on the distinctive features of the anomaly while filtering out background complexity that typically degrades prediction quality in single-path approaches. We provide a detailed description of the DU-Net architecture and evaluate its performance on two synthetic datasets representing different styles of mineralization and host-rock complexity. Experimental results demonstrate that DU-Net achieves superior accuracy in localizing anomalous bodies and reconstructing background geology compared to the standard U-Net baseline, with a substantial reduction in boundary blurring artifacts. Full article

Electromagnetic signal waveform recognition (ESWR) constitutes a fundamental enabling technology for modern spectrum management, cognitive radio, and electronic warfare applications. Among various ESWR subtasks, automatic modulation recognition (AMR) has attracted the most intensive research efforts and serves as the primary focus of this survey. Over the past decade, deep learning (DL) has fundamentally transformed ESWR by replacing hand-crafted feature engineering with data-driven end-to-end learning paradigms. However, the rapid proliferation of DL-based approaches has resulted in a fragmented research landscape. This paper addresses this gap by proposing a unified system-component framework that decomposes any DL-ESWR system into four foundational modules: (i) dataset construction and data augmentation, (ii) signal representation and preprocessing, (iii) core network architecture, and (iv) training and optimization strategy. Through this systematic lens, we provide a comprehensive review that catalogs the state of the art across recent publications and precisely attributes each innovation to specific modules within our framework. Furthermore, we identify eight core challenges confronting the practical deployment of DL-ESWR systems and systematically analyze how targeted modular innovations address each challenge. A critical analysis of prevalent benchmark datasets reveals significant limitations in channel diversity, modulation coverage, and ecological validity. Finally, we outline seven promising future research directions, including foundation models for wireless signals, physics-informed neural networks, and waveform recognition for emerging communication paradigms, such as semantic communications and integrated sensing and communication (ISAC). This survey aims to provide researchers and practitioners with a structured roadmap for understanding, evaluating, and advancing the field of AI-enabled electromagnetic signal waveform recognition. Full article

Acoustic Emission (AE) monitoring offers high sensitivity in detecting faults and defects in rotating machinery. Hit-based AE acquisition systems produce only short, intermittent waveform signals rather than continuous recordings. This work addresses the challenge of fault detection from such fragmented sensor data. It is demonstrated that individual AE hits are insufficient for reliable fault detection, as waveforms from different fault conditions overlap substantially in feature spaces. To overcome this, a distributional feature aggregation approach is proposed. AE hit features are extracted from each waveform, grouped into non-overlapping sequential bags, and summarised through order statistics and distribution moments. Four one-class classifiers namely: (i) Isolation Forest, (ii) PCA one class classifier, (iii) K-nearest neighbour one class classifier, and (iv) Local Outlier Factor were evaluated on a Drivetrain Dimulator (DTS) test rig that simulates faulty gear and bearing conditions. AE signals coming from the healthy condition were used to train the classifiers. Signal deviations due to the presence of gear and bearing faults were subsequently identified. Fault detection results show that bag-level distributional features substantially outperform per-hit features: four of five faults achieve 100% single-bag detection under five-fold cross-validation, while per-hit detection rates remain below 50% for four of five faults. The PCA one class classifier achieves 100% detection for all faults individually but is excluded from the final ensemble due to a 99% false alarm rate caused by the limited healthy training sample in a high-dimensional feature space. A CUSUM sequential detector applied to a three-method ensemble (Isolation Forest, KNN, and LOF) is evaluated on a chronological 80/20 split of the healthy data, triggering alarms for all five fault conditions with a false alarm rate of 0% at the recommended setting. Four faults are detected with sustained alarm patterns (54–100% alarm rates), while bearing outer race, the most challenging fault, is detected intermittently (10.5% alarm rate), demonstrating that sequential evidence accumulation can identify faults that are invisible to single-bag thresholding. Full article

Accurate demagnetization fault diagnosis is critical to ensuring the safety and reliability of permanent magnet synchronous motors (PMSMs). However, the number, location, and severity of demagnetized permanent magnets are mutually coupled, leading to a combinatorial explosion of fault patterns. Existing methods are largely limited to idealized assumptions involving single-magnet demagnetization or uniform demagnetization of multiple magnets, making it difficult to characterize the random nature of demagnetization in practical operation. Thus, this paper proposes a precise demagnetization fault diagnosis method based on a novel search coil (SC) configuration, in which only two toroidal-yoke-type search coils are installed in the stator slots. The proposed method partitions the rotor permanent magnets into several modules and categorizes the infinite demagnetization fault patterns into 26 representative patterns, effectively addressing the issue of fault mode explosion. Theoretical analysis and experimental results show that the voltage waveforms of the search coil over a single electrical period exhibit significant and stable differences across the identified patterns. By constructing feature vectors based on these differences, a physically interpretable mapping between the feature vectors and fault patterns is established. Combined with a corresponding pattern recognition algorithm, the proposed method enables fast and accurate differentiation of the 26 patterns without the need for complex machine learning models, thereby achieving precise localization of demagnetized permanent magnets. Simulation and experimental results verify the correctness and effectiveness of the proposed method. Full article