Search Results (3,086)

State estimation is a fundamental component of model-based Fault Detection and Diagnosis (FDD) in dynamic systems, underpinning real-time monitoring, predictive maintenance, and safety-critical operations across industries such as aerospace, power systems, robotics, and autonomous vehicles. Traditional estimators, including the Kalman Filter (KF) and its variants, provide physically interpretable residuals for fault detection but often fail to deliver reliable performance under nonlinear dynamics, modeling uncertainties, sensor faults, and non-Gaussian noise. This paper presents a comprehensive review of state estimation-based FDD approaches, with a particular focus on Artificial Intelligence (AI)-augmented Kalman filtering and hybrid frameworks that integrate Machine Learning (ML) models, including Neural Networks (NNs), Support Vector Machines (SVMs), and Gaussian Processes (GPs), with classical estimation theory. The review systematically evaluates model-based, data-driven, and hybrid methods, comparing their robustness, accuracy, computational efficiency, scalability, and interpretability in complex Cyber-Physical Systems (CPSs). Furthermore, emerging trends and open research challenges are identified, including online adaptation, fault-tolerant estimation, sensor fusion, explainable artificial intelligence (XAI), and deployment in Industry 4.0 and Internet of Things (IoT)-enabled environments. By bridging classical estimation theory with modern AI techniques, this review provides a roadmap for designing intelligent, adaptive, and resilient FDD systems capable of enhancing reliability, operational safety, and real-world applicability. Full article

In renewable-powered distribution systems and microgrids, reliable cable condition monitoring is essential for operational security and early fault detection. Sheath circulating current signals provide valuable information for identifying grounding abnormalities and incipient faults, but their diagnosis is difficult because the signals exhibit strong inter-phase coupling, and fault samples are limited in practice. This study proposes a dual-view Mixup-ResNet framework for fault diagnosis of cable sheath circulating current signals. Specifically, physical-range normalization is employed to retain magnitude-related fault information and inter-phase proportional relationships, while sample-wise z-score normalization is used to emphasize waveform morphology. These two complementary views are concatenated to form a six-channel input for a lightweight one-dimensional residual network, which is trained with Mixup, label smoothing, dropout, and cosine annealing. On an ATP-EMTP-generated eight-class dataset, the proposed method achieves an average accuracy of 91.50%, a weighted F1-score of 91.69%, and a macro F1-score of 91.69% under a unified 5 × 5 repeated stratified cross-validation protocol. Additional tests under 12% relative Gaussian noise show that the method maintains competitive Gaussian-noise tolerance within the tested condition, although broader field disturbances remain to be further validated. These findings suggest that the proposed method has potential for small-sample fault diagnosis of cable sheath circulating current signals and provides a preliminary basis for intelligent cable condition monitoring. Full article

Existing reliability assessment methods for distribution networks insufficiently characterize the impacts of faults in key components other than branches, and they often suffer from high computational complexity and repeated searches when identifying fault-affected areas. To address these issues, this paper proposes an analytical method for calculating reliability indices in distribution networks based on extended component fault modeling. First, the fault modeling objects in distribution networks are extended to multiple types of key components, including branches, sectionalizing switches, ring main units, and distribution transformers. Second, a spatial correlation matrix is constructed to describe the topology of the distribution system, source-to-load power supply paths, and the positional relationships of switching components. On this basis, an extended component fault impact correlation matrix is derived to characterize the spatial correlations between different types of component faults and the affected load nodes. Finally, through a single algebraic operation between the extended component fault–impact correlation matrix and the reliability parameter vector, explicit analytical expressions of both load-level and system-level reliability indices are obtained, thereby avoiding the repeated iterative searches required in the fault enumeration process of existing reliability assessment methods. Case study results show that the proposed method improves the evaluation efficiency by one order of magnitude while maintaining result accuracy. It can also explicitly quantify the impacts of faults in branches, sectionalizing switches, ring main units, and distribution transformers on system reliability, thereby more accurately reflecting the actual level of secure and reliable operation of the distribution network. This method can provide theoretical support and a methodological basis for reliability assessment and planning of complex distribution systems. Full article

The boost chopper (HS) is a core electrical component of the 440 V grid in high-speed maglev trains, providing reliable power for battery charging and auxiliary systems. Fault diagnosis of the HS is crucial for identifying operational faults and ensuring stable train operation. However, HS faults exhibit both long-period fluctuations and transient characteristics, which are difficult for a single network to capture synchronously. This paper proposes a multi-scale fault diagnosis method based on a TimesNet-CNN dual-branch architecture, constructing a parallel and complementary feature extraction mechanism. The TimesNet branch uses Fast Fourier Transform (FFT) to adaptively identify dominant periods, reshaping the 1D sequence into a 2D structure to explicitly model the global evolution of intra-period fluctuations and inter-period trends via Inception convolution. Meanwhile, the CNN branch employs stacked small convolutional kernels and hierarchical downsampling to extract local high-frequency anomaly features. After feature fusion, the method achieves synergistic discrimination of global periodicity and local transiency. Finally, experiments were conducted on a real-world dataset containing 11 system states (10 fault types and 1 normal state). Experimental results show that the proposed method outperforms TimesNet, CNN, ResNet and Informer models in precision, recall and F1-score. This validates the effectiveness of the dual-branch feature fusion mechanism in capturing multi-scale fault features, achieving high-precision identification of HS faults. Full article

On-grid solar microgrids (SMGs) are increasingly deployed to support sustainable and distributed energy generation. However, the low fault current levels, power-electronic interfaces, and dynamic operating conditions of SMGs create significant challenges for conventional protection systems, which may struggle to accurately detect and locate line faults (LFs). While artificial intelligence (AI) has shown promise in addressing these challenges, there remains limited comparative evidence regarding the suitability of different AI techniques for LF detection in on-grid SMGs under identical operating conditions. Therefore, this study investigates and compares the performance of four AI techniques, namely, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Support Vector Machine (SVM), and Random Forest (RF), for LF detection in on-grid SMGs. An on-grid SMG test system based on the IEEE 6-bus benchmark is implemented in MATLAB/Simulink 2025a to simulate various LF conditions and generate voltage and current datasets for model training and testing. All models are trained and evaluated under identical performance metrics, including accuracy, precision, recall, F1-score, noise robustness, and computational speed. The results show that deep learning (DL) models outperform classical machine learning approaches, with CNN achieving the highest performance of 99.79% accuracy and a 99.78% F1-score, followed by LSTM with 98.97% accuracy and a 98.92% F1-score. SVM and RF achieved accuracies of 98.25% and 95.75%, respectively, while requiring less than three minutes of training time, highlighting their suitability for real-time and resource-constrained applications. These findings provide a robust comparative benchmark for AI-based LF detection in on-grid SMGs and offer practical guidance for selecting appropriate AI techniques based on performance and computational requirements. Full article

Fault diagnosis in power electronic systems is challenging when fault categories geometrically overlap within the measurement space, limiting class separability and introducing classification ambiguity. This work proposes an edge-oriented hybrid fault-space restructuring methodology that utilizes UMAP-based embeddings and hierarchical clustering to group overlapping fault conditions into robust hybrid representations. Subsequently, supervised machine learning models execute the final classification over this optimized space. Validation was conducted using a large-scale synthetic dataset generated via real-time hardware-in-the-loop (HIL) simulation, evaluating electrical measurements from three-dimensional RMS values to 60-dimensional instantaneous waveforms. Tested with Decision Tree and Random Forest algorithms, the restructuring strategy significantly improves robustness under geometric ambiguity compared to conventional classification without space restructuring. Specifically, low-dimensional measurements achieved F1-score improvements of approximately 72% and 46% for the Decision Tree and Random Forest algorithms, respectively, while high-dimensional measurement configurations still exhibited significant improvements of 36% and 52%. Consequently, these results confirm that the combined restructuring and classification pipeline is highly effective across the analyzed measurement dimensionalities, establishing a dependable cluster-based diagnostic strategy that enhances classification robustness while accepting a trade-off in individual fault-isolation granularity. Finally, hardware deployment experiments on a Raspberry Pi 4 platform demonstrated the feasibility of executing the trained classifiers for real-time inference under constrained computational environments. The experimental evaluation validated real-time execution capabilities, achieving sub-millisecond inference latencies (as low as 0.32 ms), a memory footprint under 0.14 MB, and processing rates exceeding 2600 inferences per second using lightweight Decision Tree classifiers. Ultimately, these findings indicate that the proposed strategy improves fault detection across the evaluated measurement configurations while ensuring a highly viable execution on resource-constrained devices once the classifiers are trained. Full article

China’s offshore wind power is rapidly developing towards the direction of “deep-water and far-shore, large-scale, and clustered”. Existing offshore wind power transmission schemes based on the MMC are technologically mature but highly expensive. Although transmission schemes based on the DRU possess economic advantages, they lack AC voltage support and reverse power flow capability. To combine the control performance of the MMC and the economic advantages of the DRU, this paper proposes a heterogeneous DC transmission system for offshore wind power based on the parallel operation of MMC-HVDC and DRU-HVDC, which can realize the clustered transmission of deep-water and far-shore wind power. First, the configuration scheme of the system is introduced, and the basic control strategy is proposed. Secondly, the small-signal model of the system is established, and the small-signal stability analysis is conducted. Then, the control strategies for the system under near-zero power conditions and AC/DC faults are proposed, respectively. Finally, the effectiveness of the proposed topology and control strategies is verified through PSCAD electromagnetic transient simulations. Full article

With the development of the socio-economic landscape and the increasing demand for urban power supply, user expectations for power supply reliability have risen significantly. To address this challenge, dual-petal distribution networks, characterized by multiple tie-line structures and inter-regional load transfer paths, have significantly enhanced fault recovery capability and are gradually replacing traditional radial configurations as a key form of modern distribution systems. However, their multi-regional coupling characteristics introduce complex issues such as dynamic changes in load transfer paths and islanded operation, resulting in significant limitations in the accuracy and adaptability of existing reliability assessment methods. To this end, this paper proposes an analytical method for calculating reliability indices of dual-petal distribution networks, considering the characteristics of load transfer zones. First, typical operation modes of dual-petal distribution networks are extracted, and a time-sequential component reliability analysis model is established. Second, a load transfer zone matrix is constructed based on the impact of distribution network faults on load nodes across different regions. Third, based on the fault ride-through capability of distributed generation (DG), a load restoration strategy considering load transfer zone characteristics is formulated, and the DG Island Recovery Matrix (DGIRM) is derived. Finally, by performing algebraic operations among various matrices and reliability parameter vectors, an explicit analytical calculation of reliability indices for dual-petal distribution networks with different DG configurations is achieved. The effectiveness of the proposed method is validated using a typical dual-petal network. The results demonstrate that the proposed method offers high computational efficiency and accuracy, effectively quantifying the impact of DG on the power supply reliability of dual-petal distribution networks, and providing theoretical and methodological support for the reliability assessment and planning of complex distribution systems. Full article

Accurate fault location is essential for improving the reliability and service restoration capability of distribution networks. With the increasing penetration of distributed generation, power electronic devices, and flexible loads, fault transient signals become increasingly nonlinear and nonstationary, posing challenges to conventional impedance-based, traveling-wave-based, and feature-engineering-based methods. To improve transient fault feature representation, this paper proposes a wavelet-embedded residual attention convolutional neural network (CNN) for distribution network fault location. The task is formulated as a multi-class classification problem, in which each predefined line section is treated as a candidate fault location class. The proposed method embeds discrete wavelet decomposition into the convolutional feature extraction process, enabling low-frequency trend components and high-frequency transient components to be jointly represented and fused by subsequent trainable network modules. Residual connections improve deep feature propagation, and an attention mechanism enhances fault-sensitive representations. Simulation studies on the IEEE 33-bus distribution system show that the proposed method outperforms multi-layer perceptron (MLP), support vector machine (SVM), standard CNN, ResNet, and Attention-CNN, achieving 98.27% accuracy and a 98.33% F1-score. The class-wise results and robustness tests under different transition resistances, noise levels, and fault types further verify the effectiveness and adaptability of the proposed method. Full article

DC series arc faults (SAFs) are a significant safety hazard on the DC side of photovoltaic (PV) systems, with current signals characterized by strong randomness, obvious non-stationarity, and concealed fault features, posing challenges for rapid and accurate detection. With the development of application models such as agricultural PV integration, photovoltaic greenhouses, solar-powered irrigation, and livestock energy supply, the demand for the safe operation of photovoltaic systems in agricultural production scenarios is becoming increasingly prominent. To address the difficulty in fully characterizing the multi-scale dynamic features and local amplitude disturbances of DC SAF signals, this paper proposes a SAF detection method based on multi-scale generalized amplitude-aware permutation entropy (MS-GAAPE). The method extracts MS-GAAPE from arc current signals at various scales using sliding window-based generalized coarse-graining, which preserves temporal sequence information while improving the characterization of local amplitude variations. Particle swarm optimization (PSO) is applied to optimize these multi-scale features, strengthening fault-related information and reducing interference. The optimized features are then processed by a support vector machine (SVM) for SAF detection. The dataset used contains 50,000 samples covering transient conditions such as voltage fluctuations and is divided into a training set and an independent test set in a 70% to 30% ratio. The training set is utilized for feature parameter determination, feature weight optimization, and classification model construction, while the independent test set is reserved solely for final performance evaluation. Experimental results demonstrate that the proposed method achieves excellent detection performance under various operating conditions and load levels, with an accuracy of 99.32% and a total detection time of 103.62 ms, meeting the requirements of the UL1699B standard, thus showcasing strong real-time detection capability and potential for embedded implementation. Full article

Conventional soft open points (SOPs) suffer from limited transfer capacity during distribution network faults. To address this issue, this paper proposes an integrated energy storage system and soft open point (ES-SOP) along with a power path dynamic reconfiguration method. The device consists of an M × N AC switch matrix, N AC/DC converters, and a common DC bus with energy storage. This structure provides three distinct power paths: a mechanical direct path, a third-party grid path, and an energy storage path. A seamless reconfiguration technology is developed to eliminate inrush currents during mechanical switching. It combines multi-unit virtual synchronous generator (VSG) pre-synchronization with a DC bus voltage droop coordination mechanism. The overall control follows a two-time-scale strategy. On a long time scale, a heuristic rule selects the most suitable healthy grid as the mechanical source. On a short time scale, the droop parameters of the converters are optimized to autonomously share the remaining power between the third-party grid path and the energy storage path. This allocation minimizes losses and requires no fast communication. Hardware-in-the-loop experiments verify the performance: the proposed method completely suppresses inrush current, keeps DC bus voltage fluctuation below 20 V during mode transitions, and achieves a transfer efficiency of approximately 98.5%. Full article

At present, photovoltaic (PV) systems are becoming the core of low-carbon power systems, but their large-scale integration is still limited by weather-driven intermittency, heterogeneous data, equipment failures, operational uncertainty, and life-cycle sustainability requirements. Unlike specific task reviews that only focus on photovoltaic forecasting, fault diagnosis, or general artificial intelligence applications in renewable energy, this review develops an integrated data-driven perspective for machine learning and artificial intelligence in photovoltaic power generation systems. It links data governance, feature engineering, prediction, and uncertainty quantification, fault diagnosis and predictive maintenance, energy management, market participation, and carbon-aware optimization within a framework for photovoltaic systems. This review indicates that traditional machine learning, deep learning, graph learning, reinforcement learning, generative artificial intelligence, and physics-based artificial intelligence are suitable for different photovoltaic tasks based on data structure, time range, operational constraints, and deployment maturity. The main contribution is cross-task integration, which links the output of artificial intelligence models, including scheduling, storage scheduling, maintenance planning, virtual power plant operation, and low-carbon management, with actual decision-making. The review further identified the most critical deployment barriers, such as incomplete benchmarks, weak cross-site generalization, insufficient uncertainty calibration, limited interpretability, network security risks, and computational costs. The resulting methodological approach emphasizes data management, uncertainty awareness, physical constraints, decision orientation, and sustainability-driven photovoltaic intelligence. Full article

Geothermal energy is a locally available, low-carbon resource that may support heat supply, building decarbonisation and regional energy diversification in non-volcanic crystalline settings. This study proposes an exploratory GIS-based approach for geothermal favourability mapping in the Guarda District, Central Portugal, where Hercynian granites, major fault systems and thermal and mineral water occurrences define a structurally controlled hydrogeothermal framework. Hydrogeochemical data from 54 groundwater abstraction points were integrated through silica-derived apparent geothermometric indicators, classical hydrothermal-parameter estimation and Empirical Bayesian Kriging Regression Prediction (EBKRP). Apparent silica-derived temperature indicators, circulation depth, geothermal gradient and theoretical thermal power were estimated, with log₁₀ transformed thermal power used as the dependent variable and distance to major mapped faults as the structural covariate. Apparent silica-derived temperature indicators range from 21.3 °C to 121.2 °C, with a mean of 64.6 °C, while estimated geothermal gradients range from 20.3 °C/km to 92.1 °C/km. Higher estimated values occur preferentially near NE–SW and NNW–SSE fault systems, suggesting that structural permeability may influence deep groundwater circulation. The interpretation explicitly acknowledges that, in low-temperature systems, dissolved silica may be influenced by chalcedony or amorphous silica control, as well as by cooling, mixing and incomplete re-equilibration during fluid ascent. The resulting map is interpreted as a screening-level favourability product, not as a definitive assessment of exploitable geothermal resources, and supports the prioritisation of future structural mapping, geophysical surveys, exploratory drilling, borehole temperature logging and applied geothermal assessment in fractured granitic terrains. Full article

Chillers serve as the core high-energy-consuming equipment in heating, ventilation, and air conditioning (HVAC) systems. During long-term continuous operation, they tend to suffer gradual subtle degradation, with a performance deviation less than 5%. Conventional fault diagnosis methods rely on manual threshold judgment or labeled fault data, which fail to realize accurate early warning signals. In addition, existing algorithms lack multi-dimensional baseline comparisons to verify their practical engineering performance. To address these limitations, this paper proposes an unsupervised health assessment method combining an LSTM autoencoder and Euclidean distance (LSTM-AE-ED). A multi-gradient fault time-series dataset is generated via a MATLAB R2022b/Simscape mechanism model verified by both summer field measurements and refrigeration pressure-enthalpy cycles, which resolves the practical engineering challenges of scarce on-site fault samples and potential equipment damage caused by actual fault tests. The proposed model is trained solely on healthy time-series data. It extracts dynamic coupling characteristics of chillers through LSTM, constructs a dimensionless health index based on Euclidean distance in feature space, and introduces the standard deviation of health index to improve evaluation stability. Baseline comparisons with vanilla AE and single-layer LSTM are carried out. Experimental results demonstrate that the proposed method achieves an identification accuracy of 96.3% and exhibits high sensitivity to mild degradation of four typical faults, adapting to dynamic multi-working-condition scenarios. This approach requires no additional acquisition devices for derived parameters such as power consumption and COP; online assessment can be realized merely with standard temperature, pressure, and flow sensors equipped on chillers. With lightweight inference performance, it is suitable for edge monitoring terminals of chillers in data centers, providing a low-cost and practical quantitative technical scheme for predictive maintenance and hierarchical early warning signals of refrigeration equipment. Full article