Search Results (200)

Real-world power transmission inspection faces acute data scarcity and severe class imbalance, as defective insulator instances are exceptionally rare compared to normal samples. To enable robust defect detection under such constraints, we present MS-LaT—a backbone networkthat fuses multi-granularity feature learning with latent context-aware fusion. The architecture processes visual inputs through a streamlined pipeline: an input stage employing AdaptTeLU-augmented inverted multi-scale separable-residual convolutions to discern subtle local anomalies; a contextual reasoning stage powered by a Latent Transformer encoder with Multi-Head Latent Attention (MLA) for holistic scene understanding; and an output stage utilizing AdaptTeLU-refined inverted multi-scale convolutions to produce precise diagnostic decisions. Domain-adaptive batch normalization (AdaBN) is embedded to minimize cross-domain feature divergence, substantially boosting generalization across diverse operational environments. Research utilising real-world engineering datasets demonstrates the proposed method’s robust insulator defect detection capability in complex environments. Full article

With the advent of ubiquitous healthcare and advancements in textile industry, non-invasive wearable biomedical solutions are becoming an increasingly attractive alternative to in-hospital monitoring, allowing for timely diagnostics and prediction of severe medical conditions. Non-contact biopotential monitoring is particularly promising because non-contact biopotential electrodes can be applied over clothing or embedded in the material without almost any preparation. However, due to the intricacies of capacitive coupling they rely on, the design of such electrodes and their interface with the body plays a key role in achieving measurement repeatability and their widespread utilization in clinical-grade diagnostics. Based on exhaustive investigation of several decades of the literature on non-contact and capacitive biopotential electrodes and electric potential sensors, this study is intended to serve as a state-of-the-art overview of their historical development and design challenges, a collecting point for important research theories and development milestones, a starting point for anyone seeking for a soft head start into this research area, and a remedy for occasional misnomers and conceptual errors identified in the existing papers. The ultimate goal of this comprehensive analysis is to demystify phenomena of non-contact biopotential monitoring and capacitive coupling, systematically reconciliate terminological inconsistencies, and enhance accessibility to the most important findings for future research. To accomplish this, fundamental concepts are thoroughly revisited—from fundamentals of electrochemistry and working principles of capacitors and operational amplifiers to system stability and frequency-domain analysis. With the use of various mathematical tools (Laplace transform, phasors and Fourier analysis, and time-domain differential calculus), discussions on non-contact and capacitive biopotential electrodes, collected from the 1960s onward, are for the first time compiled into a unified, abstracted, bottom-up analysis. The laid-out inspection provides analytical explanation for various aspects of measurement results available in the referenced literature, but also serves an educative purpose by devising a methodological framework that can be easily applied to other similar research fields. Firstly, the differences and similarities between wet, dry, surface-contact, non-contact, capacitive, insulated, on-body, and off-body biopotential electrodes are clarified. For this purpose, equivalent electrical models of various non-invasive biopotential electrodes are analyzed and compared. As a result, a proposal for a revised classification of biopotential electrodes is given. Secondly, instead of using the concept of a purely capacitive biopotential electrode, a test is proposed for assessing the predominant coupling mechanism achieved with an electrode over an insulating layer. Thirdly, a fundamental model of a buffer active non-contact biopotential electrode and its interface with the body is built and generalized, and the proposed test is applied for analyzing the influence of voltage attenuation and phase shifts on signal morphology. Lastly, guidelines for designing the described electrode–body interfaces are proposed, along with a discussion on practical aspects of their implementation. Full article

Partial discharge (PD) signals in gas-insulated switchgear (GIS) exhibit complex characteristics, and single-modal feature recognition methods face limitations in achieving satisfactory diagnostic accuracy due to incomplete fault information representation. This paper proposes a multi-modal fault diagnosis framework that effectively integrates complementary information from different sensing modalities to improve defect identification performance. First, PRPD time-domain statistical features from HFCT measurements and frequency-domain features from UHF signals are extracted to construct a comprehensive hybrid feature set. Z-score normalization is applied to eliminate scale differences between heterogeneous features. Principal component analysis (PCA) is then employed for dimensionality reduction, preserving essential discriminative information while removing redundancy. Finally, a ResNet-MLP classifier with skip connections is designed to enhance nonlinear feature extraction and alleviate gradient vanishing problems in deep network training. Experimental validation on four typical defect types—protrusion defect, floating discharge, metal particle discharge, and surface discharge on insulator—demonstrates that the proposed method achieves 99.38% classification accuracy on the test set, with consistently high precision, recall, and F1-score across all categories. The proposed approach significantly outperforms standard MLP without residual connections, achieving 98.94% ± 0.49% accuracy compared to 95.47% ± 3.72% over 20 independent runs, demonstrating superior diagnostic accuracy and generalization capability for GIS insulation fault diagnosis. Full article

Low-voltage instrumentation and control (I&C) cables in nuclear power plants are continuously exposed to gamma (γ) radiation within containment areas, leading to cumulative degradation of their polymer insulation over decades of operation. Since conventional mechanical aging assessments are destructive, this study establishes a non-destructive diagnostic framework using high-frequency dielectric spectroscopy. Cable samples with ethylene propylene rubber (EPR) insulation and chlorosulfonated polyethylene (CSPE) jackets were subjected to controlled γ-irradiation at doses up to 1200 kGy. The broadband dielectric response was analyzed along with derived novel diagnostic parameters from capacitance and loss tangent spectra and a machine learning AI algorithm. The results show a strong, material-dependent relationship between radiation dose and dielectric indicators. For EPR insulation, the central capacitance (CC) and (C × F × LF) exhibit high positive sensitivity for Black and White EPR materials, respectively, whereas for CSPE jackets, the central frequency (CF) shows a pronounced monotonic decrease with the radiation exposure. These findings enable a straightforward, transparent interpretation of dielectric data and implement a new, accurate method of irradiated cables diagnosis. Full article

Although solar photovoltaic (PV) technology is a well-known sustainable energy source, as glass-on-glass bifacial modules have dominated the market during the rapid scaling of the PV industry, glass breakage has become an environmental concern. This study explores the reuse of broken modules to further improve PV sustainability through case studies of 3.45 MWp and 1.4 MWp solar farms, comprising over 12,700 modules. After cleaning and testing, 1.45% of PV modules were physically damaged due to glass breakage during transport or handling at the solar farms in Brazil. Recycling of PV modules is infrequent; therefore, the reuse of modules under these conditions was explored. Nine modules with glass damage were connected to the electricity grid using a carport-type structure, and 36 diagnostic current–voltage (I-V) tests were carried out over an 18-month experimental period. Tests to detect faults and low system insulation resistance indicated that the implementation of non-invasive, remote, online, and periodic monitoring enabled the system to operate and enabled the reuse of damaged modules. Although the electrical results were promising, future work is needed to evaluate methods to ensure the broken glass is sealed to prevent electric shock hazards and to maintain long-term safe performance. Full article

During the operation of above-ground main oil and gas pipelines, their elastic bends occur due to the properties of the soils in which the pipeline bases are installed, climatic factors, and the intersection of geodynamic zones. Exceeding the stress values in the pipeline wall above their permissible values leads to a rupture of the wall metal and major accidents. Most methods for estimating the values of bending stresses in the pipeline wall cannot be implemented during their operation, when the pipeline already has a bend, and the installation of any additional equipment on the pipeline requires additional investments. At the same time, the most widely used method for estimating bending stresses based on data from in-pipe diagnostics does not allow for evaluation in areas with varying internal diameters of the pipeline, as well as right-angle turns. The most promising method for estimating bending stresses is aerial laser scanning of pipelines, which consists of obtaining a cloud of points on the pipeline surface, estimating its spatial position, and calculating stress values. However, this method requires the development of more accurate algorithms for processing laser scanning data, and the method is associated with a number of difficulties that can be eliminated by developing the correct sequence of actions during scanning. Within the framework of this article, an algorithm has been developed for analyzing the coordinates of a cloud of points on the pipeline surface, which makes it possible to estimate the values of bending stresses in the pipeline wall. The influence of the unevenness of the thermal insulation surface on the stress assessment results was also studied, taking into account the minimum angle of the scanned pipeline sector, which ensures the accuracy of determining stress values up to 5% using the developed method. Full article

As a non-invasive diagnostic technique, evolved gas analysis (EGA) holds significant value in assessing the insulation conditions of critical equipment such as power cables. Current analytical methods face two major challenges: insulation materials may undergo multiple aging mechanisms simultaneously, leading to interfering characteristic gases; and traditional approaches lack the multi-label recognition capability to address concurrent fault patterns when processing mixed-gas data. These limitations hinder the accuracy and comprehensiveness of insulation condition assessment, underscoring the urgent need for intelligent analytical methods. This study proposes a deep convolutional neural network (DCNN)-based multi-label classification framework to accurately identify the gas generation characteristics of five typical power cable insulation materials—ethylene propylene diene monomer (EPDM), ethylene-vinyl acetate copolymer (EVA), silicone rubber (SR), polyamide (PA), and cross-linked polyethylene (XLPE)—under fault conditions. The method leverages concentration data of six characteristic gases (CO₂, C₂H₄, C₂H₆, CH₄, CO, and H₂), integrating modern data analysis and deep learning techniques, including logarithmic transformation, Z-score normalization, multi-scale convolution, residual connections, channel attention mechanisms, and weighted binary cross-entropy loss functions, to enable simultaneous prediction of multiple degradation states or concurrent fault pattern combinations. By constructing a gas dataset covering diverse materials and operating conditions and conducting comparative experiments to validate the proposed DCNN model’s performance, the results demonstrate that the model can effectively learn material-specific gas generation patterns and accurately identify complex label co-occurrence scenarios. This approach provides technical support for improving the accuracy of insulation condition assessment in power cable equipment. Full article

Tip discharge in oil-immersed transformers poses a significant threat to insulation integrity. Conventional detection methods, such as gas and electrical analysis, are limited by slow response times or susceptibility to interference. Additionally, the lack of systematic comparisons between aged and fresh oil using multi-modal signal correlations hinders the development of accurate diagnostic strategies. To address this, a multi-modal sensing platform employing optical, UHF, and HFCT sensors, complemented by visual observation, was developed to investigate the evolution characteristics and mechanisms of tip discharge and to compare the detection effectiveness of these methods. Experimental results reveal that aged oil undergoes a novel four-stage evolution, where discharge signals first rise to a local peak, then experience suppression, followed by a dramatic surge, and finally decline slightly before breakdown. This process is governed by an “Impurity-Assisted Cumulative Breakdown Mechanism,” driven by impurity bridge growth and space charge effects, with signal transitions from ‘decoupling’ to synchronization. The optical sensor demonstrated superior sensitivity in early discharge stages compared to electrical methods. In contrast, fresh oil exhibited a “High-Field-Driven Stochastic Breakdown Mechanism,” with isolated pulses from micro-bubble discharges maintaining a metastable state until a critical threshold triggers instantaneous failure. This study enhances the understanding of how oil condition alters discharge mechanisms and underscores the value of multi-modal sensing for insulation condition assessment. Full article

Social housing plays a key role in the Colombian residential market, showing a growing commitment to sustainability: currently, a high percentage of EDGE-certified homes belong to this segment. However, in hot and humid areas such as Montería, most VIS homes have deficiencies in their thermal envelopes and poor roof insulation, which leads to a heavy reliance on air conditioning. This study addresses the lack of practical and replicable methodologies for improving energy efficiency in social housing located in hot–humid climates. The research aims to develop and apply a methodological framework that integrates architectural rehabilitation strategies with quantitative evaluation using the EDGE App tool. The proposed approach was implemented in Montería, Colombia, through a case study that combines diagnostic analysis of existing housing conditions, simulation of energy-saving measures, and assessment of environmental and economic performance. A real home in Montería was used as a reference, and more than 600 simulations were carried out considering different orientations and passive strategies. Through a Pareto analysis, the three most efficient measures were identified: natural ventilation, high-solar-reflectance roofing, and moderate reduction in the U-value. Together, these measures reduced energy consumption by up to 50%, with minimal increases in construction costs (≤1.2% of the commercial value). It was also found that excessive insulation can induce unwanted nighttime heating demands, highlighting the need for adjustments to the climatic context. The results confirm the technical and economic feasibility of mass rehabilitation of VIS in hot and humid climates using standard passive measure packages, consolidating the role of the EDGE App as a key tool for guiding sustainable design, investment, and environmental certification decisions. Full article

Oil–paper insulation in oil-immersed transformers undergoes a concealed degradation process that is difficult to detect during operation. To understand its discharge behavior, this study examines partial discharge characteristics under controlled moisture absorption and thermal aging. Experiments on S-PD (Surface Partial Discharge) and N-PD (Needle Partial Discharge) were carried out, and partial discharge patterns, discharge frequency, and breakdown voltage were collected to analyze discharge evolution. The results show that partial discharge develops through three stages: initiation, development, and pre-breakdown. In the initiation stage, pulses are sparse with low amplitudes and appear near the voltage peak. During development, both amplitude and discharge frequency increase, and the phase range expands. As breakdown approaches, pulse amplitude rises sharply, the phase distribution covers almost the full cycle, and conductive channels begin to form. Skewness, Peak Degree, and Maximum Steepness were extracted from statistical discharge maps to compare moisture-affected and aged samples. The findings provide experimental support for developing state-evolution-based failure warning models and diagnostic criteria, contributing to improved operational safety of oil–paper insulation systems. Full article

Dissolved Gas Analysis (DGA) is a diagnostic strategy that monitors oil-immersed transformers by correlating their health status with various insulation degradation by-products, where the Health Index (HI) offers a unified metric for asset evaluation. Existing studies frequently emphasize classification accuracy or single-model regression, overlooking interpretability, feature reduction, and systematic benchmarking. This paper introduces a feature-enhanced multi-experimental methodology for HI prediction incorporating SHapley Additive exPlanations (SHAP) in a dual role—as both an interpretability and a feature selection tool. Models from four algorithmic families (linear, kernel/tree-based, boosting, and hybrid ensembles) were systematically benchmarked using a publicly available dataset. Results demonstrate that the proposed LightGBM–CatBoost hybrid ensemble, enhanced by SHAP-guided feature pruning, achieves superior predictive accuracy while reducing model complexity and improving transparency. Unlike prior works carried out using the same dataset, the proposed framework not only provides a balanced approach that combines interpretability and reduced complexity, but also surpasses previous regression-based approaches, reducing MAE and RMSE by 4.93% and 2.31%, respectively, and enhancing HI predictive accuracy by 1.45%. Full article

Accurate assessment of high-voltage cable insulation condition is essential for safe operation in complex tunnel environments. Traditional methods relying on single diagnostic indicators and fixed weighting schemes often suffer from limited accuracy and adaptability. This paper proposes a multi-parameter assessment method integrating game theory with fuzzy comprehensive evaluation. Five types of online monitoring data, namely cable surface temperature, sheath grounding current, partial discharge, tunnel humidity, and ambient temperature, are selected as diagnostic parameters. Subjective and objective weights are first derived using the analytic hierarchy process and the entropy weight method, and then optimally integrated through a game-theoretic framework. Fuzzy membership functions are applied to construct an evaluation matrix, enabling quantitative and graded assessment of insulation condition. A case study on 110 kV tunnel high-voltage land cables in Zhejiang, China, verifies the effectiveness of the approach. Results show that the proposed method more accurately reflects actual operating conditions and provides higher diagnostic precision and robustness compared with single-feature and traditional weighting methods. By combining expert knowledge with real monitoring data, this study develops a scientific and practical framework for insulation condition assessment, offering reliable support to real-time insulation monitoring and predictive maintenance applications of high-voltage power transmission systems. Full article

Detecting anomalies in electrical equipment and improving maintenance efficiency are critical for ensuring operational safety, reliability, and sustainability. To address the structural limitations of conventional manual and visual inspection methods, this study developed an object-recognition-based automated damage diagnosis system for lightning rods and insulators (ADS-LI), which enabled non-contact and fully automated diagnosis of lightning rods and insulators. ADS-LI employs a dual-module architecture. The first module precisely detects lightning rods and insulators using the PointRend algorithm applied to drone-acquired aerial imagery. The second module is a formula-based diagnostic model that quantitatively determines structural anomalies using the geometric attributes of the detected objects. Specifically, anomalies in lightning rods are identified by analyzing variations in inclination derived from center-coordinate shifts ($\Delta x$), while insulator anomalies are evaluated based on the mask area conservation ratio ($r$). The performance of ADS-LI was validated using 90 independent test datasets, achieving a 0.89 F1-score and 99% overall accuracy. These results demonstrate that ADS-LI effectively automates labor-intensive diagnostic tasks that previously relied on skilled experts. Furthermore, by quantifying anomaly detection criteria, it ensures consistency and reproducibility for diagnostic outcomes. This study is also expected to contribute, in the long term, to the transition of elevated electrical installations toward a sustainable maintenance regime. Full article

Lithium-ion batteries are extensively employed in electric vehicles (EVs) and energy storage systems (ESSs) owing to their high energy density, long cyclability, and cost-effectiveness. However, the use of flammable electrolytes makes them inherently susceptible to thermal runaway (TR), which can lead to ignition, explosion, and large-scale fires. Accordingly, early detection of defect internal conditions that precede thermal events is essential for ensuring battery safety. This study proposes a time-resolved partial discharge (TRPD)-based diagnostic method for identifying early electrical precursors of fire hazards in lithium-ion batteries. Both destructive (ex situ) and non-destructive (in situ) experiments were performed to collect defect signal data under physical deformation and accelerated degradation conditions. Through fast fourier transform (FFT) analysis of the acquired signals, specific frequency-domain characteristics associated with micro internal short circuits (MISC) were identified, particularly within the 3.9 MHz, 11.9 MHz, and 19 MHz bands. Defect signals were clearly distinguishable from background common-mode voltage (CMV) noise, confirming the diagnostic sensitivity of the proposed approach. The results demonstrate that the TRPD-based technique enables early recognition of latent insulation degradation and internal short-circuit phenomena before thermal runaway occurs. This work bridges the gap between conventional insulation monitoring and battery safety diagnostics, providing a scalable framework for integrating high-frequency signal analysis into EV and ESS battery management systems for fire prevention. Full article

The maritime industry is undergoing a digital transformation, in which predictive maintenance and intelligent diagnostics play a crucial role in enhancing operational safety and efficiency. This paper investigates the application of infrared thermography (IRT) for fault detection and condition monitoring of ship machinery, with particular emphasis on its integration within condition-based and predictive maintenance frameworks. A systematic review was conducted in accordance with the PRISMA 2020 methodology, analyzing 210 publications retrieved from the Web of Science (WoS), Scopus, and Google Scholar databases to identify prevailing technological trends and research gaps. The results indicate that IRT enables early detection of critical faults such as overheating, insulation degradation, and poor electrical connections, thereby reducing unplanned downtime and improving system reliability. When integrated with artificial intelligence (AI), deep learning (DL), and convolutional neural networks (CNNs), diagnostic accuracy can be automated through enhanced data interpretation. Despite its proven effectiveness, standardized protocols and real-world validation of IRT–AI systems remain limited in the maritime sector. IRT is therefore recognized as a key enabler of safer, smarter, and more sustainable ship maintenance within the broader maritime digitalization framework. Full article