Search Results (1,295)

Attitude estimation is critical for the stability and reliability of launch vehicle flight missions, especially under complex dynamic conditions with external disturbances and sensor uncertainties. To address the limitations of conventional estimation methods that ignore the coupling between thrust vector control (TVC) and attitude states, this paper proposes a robust attitude estimation framework based on the Right Invariant Extended Kalman Filter (IEKF). Two key innovations are incorporated: first, the control model of the launch vehicle is established as a TVC model, which explicitly characterizes the coupling between TVC inputs (thrust magnitude and gimbal deflections) and launch vehicle dynamics, instead of treating TVC effects as external disturbances. Second, TVC motion constraints are introduced into the classic IEKF filtering process, embedding TVC as a deterministic input into the state propagation model to enhance the structural rationality of the estimator. To verify the effectiveness of the proposed method, simulations of the launch vehicle ascent trajectory are conducted, with three comparative configurations tested under normal and sensor anomaly scenarios. The simulation results demonstrate that the proposed attitude estimation method, integrated with TVC modeling and motion constraints, is significantly superior to traditional methods in both accuracy and robustness, effectively suppressing state estimation drift and maintaining stable performance even under sensor degradation or outages. Full article

To address the problems of enhanced non-stationarity, significant feature distribution shift, and insufficient cross-condition generalization capability of traditional fault diagnosis methods under variable operating conditions such as varying speed and load, a rolling bearing fault diagnosis method integrating group sparse reconstruction and a multi-strategy improved quantum particle swarm optimization-based relevance vector machine (RVM) is proposed. First, group sparse representation learning is employed to reconstruct the original vibration signals, thereby suppressing background noise and enhancing fault-related impulsive components to improve signal separability and stability. Subsequently, a modal component selection criterion combining kurtosis and correlation coefficients is introduced to optimize and reconstruct the decomposed modal components, enabling the reconstructed signals to retain more fault-sensitive information. On this basis, multiple information entropy features are extracted from the reconstructed signals to construct high-dimensional state feature vectors for comprehensively characterizing the dynamic operating states of rolling bearings. To further enhance the parameter optimization capability, Chebyshev chaotic mapping is incorporated into the quantum particle swarm optimization (QPSO) algorithm to improve the uniformity of population initialization. Meanwhile, a Cauchy mutation strategy is introduced to strengthen the global search capability and avoid premature convergence, thereby forming a multi-strategy improved QPSO algorithm. Finally, the improved optimization algorithm is utilized to adaptively optimize the key hyperparameters of the RVM, resulting in a fault diagnosis model with high accuracy, strong generalization capability, and sparse characteristics. Experimental validation on the HUST and XJTU-SY bearing datasets demonstrates that the proposed MIQPSO-RVM framework achieves diagnostic accuracies of 96.70% and 94.83%, respectively. Compared with several representative intelligent diagnosis methods and deep learning models, the proposed method exhibits superior diagnostic performance, robustness, and generalization capability under complex operating conditions. Full article

In the domain of rotating machinery fault diagnosis, challenges such as multi-operating condition distribution heterogeneity and the difficulty of distinguishing fault features within multi-scale temporal signals persist. To address these issues, this paper introduces the Time-Gated Multi-Expert Generative Adversarial Network (TGME-GAN), a fault diagnosis approach that integrates a multi-expert gated conditional generative adversarial network with a clustering structure-aware feature enhancement. This method combines unsupervised K-means clustering with supervised discriminative learning. The optimal number of clusters is selected adaptively using the silhouette coefficient, and the distance vector from each sample to the cluster centers serves as a topological prior feature. A spatial–temporal joint representation matrix is then formed by concatenating PCA principal components, differential features, cumulative statistical features, and standardized change rates, which together capture both abrupt mutations and progressive degradation in fault signals. In the model, the discriminator incorporates a multi-expert gated network. Each expert learns a feature subspace corresponding to a distinct operating condition, and the gated network dynamically assigns fusion weights, allowing the discriminator to capture heterogeneous distributions across industrial conditions. The generator extracts multi-scale local patterns with a three-layer one-dimensional convolutional network and models sequential dependencies with a two-layer LSTM, producing high-quality fault samples that preserve intrinsic consistency. At the engineering level, TGME-GAN is deployed for gearbox fault diagnosis in uneven, small-sample industrial settings. In two gearbox fault experiments, this method substantially outperforms current mainstream models. Full article

Fault detection from electric vehicle charging segments is challenging because real-world records are noisy, verified fault labels are scarce, and weak signatures may evolve gradually across time and unevenly across a vehicle’s charging history. This study proposes an unsupervised dynamic multiscale state-space support vector data description framework for vehicle-level battery fault detection. A gated diagonal state-space encoder preserves long-range charging patterns while retaining a direct input path for transient changes. A progressive cross-scale fusion module then combines short-term fluctuations with accumulated deviations in the learned hidden representation. Finally, a two-stage hypersphere optimisation strategy first estimates the normal centre and then refines the boundary around that fixed centre. This coordinated design avoids sequence reconstruction and directly scores charging segments by their distance from normal behaviour before robust vehicle-level aggregation. On the two EVBattery subsets that permit statistically reliable evaluation, the proposed framework achieved vehicle-level areas under the receiver operating characteristic curves of 0.8849 and 0.8438. These results exceed those of the best-performing baseline on the corresponding subsets by 0.0889 and 0.0417, respectively. The results show that coordinating long-range encoding, cross-scale fusion, and staged boundary learning improves threshold-independent vehicle-level fault ranking in real charging data. Full article

The actuator-fault estimation problem is addressed for discrete-time semi-Markov jump neural networks subject to time-varying delays, external disturbances, and communication constraints induced by the weighted try-once-discard (WTOD) protocol. Under this protocol, only the measurement channel with the largest weighted error is transmitted at each sampling instant, while the unselected channels retain their previously stored measurements at the filter side. To estimate the actuator fault, a fault-weighting dynamic system is first introduced. Then, by incorporating the WTOD-induced held measurement into the state vector, an augmented estimation model is constructed to describe the fault-weighting dynamics and the protocol-induced data-holding behavior within a unified framework. Based on this model, a mode-dependent and channel-dependent reduced-order fault-estimation filter is designed. The distinctive feature of the proposed framework is that the reconstruction of selected state components and the estimation of the actuator fault are addressed within a unified reduced-order estimator whose parameters depend jointly on the semi-Markov mode and the active WTOD transmission channel. By employing a Lyapunov–Krasovskii functional and using the semi-Markov transition information together with the WTOD scheduling constraint, sufficient LMI-based conditions are derived to ensure mean-square exponential stability and strict $(T_1,T_2,T_3)-\delta$ dissipativity performance of the resulting estimation error system. Finally, two examples are provided to illustrate the numerical effectiveness of the proposed actuator-fault estimation method under different semi-Markov switching realizations. Full article

Rolling bearings are indispensable elements in mechanical equipment, and their condition is closely related to system reliability and operational safety. To enhance diagnostic performance with limited samples and reduce the dependence on manual parameter selection, this study proposes a fault diagnosis approach that combines Continuous Wavelet Transform (CWT), Convolutional Neural Network (CNN), Black-winged Kite Algorithm (BKA), and Least Squares Support Vector Machine (LSSVM). The original 1-D vibration signals are first processed by CWT to obtain 2-D time–frequency representations. CNN is then employed to learn deep fault-sensitive features, which are subsequently fed into LSSVM for state classification. To further improve classification performance, BKA is used to automatically search for the optimal LSSVM parameters, with validation accuracy adopted as the fitness criterion. Experiments conducted on three public bearing datasets, namely CWRU, JNU, and SEU, indicate that the proposed method outperforms CNN, CNN-SVM, and CNN-BiGRU under small-sample conditions. In addition, t-SNE results show more distinct feature clusters, while BKA exhibits faster convergence and better global search capability than Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). Full article

The increasing penetration of distributed energy resources (DERs) introduces significant operational uncertainties, challenging the reliability and robustness of conventional protection coordination in distribution networks. Traditional optimization methods can obtain high-quality relay settings, but their iterative computational burden limits their direct use for real-time adaptation. To address this issue, this paper proposes a deep learning-based preventive relay setting calibration framework for enhancing protection coordination robustness in DER-rich distribution networks. The proposed method adopts an offline–online architecture. In the offline stage, a refined heuristic algorithm is integrated with ETAP-based fault analysis to generate a comprehensive dataset of high-quality optimized time-multiplier settings (TMSs) and pickup current settings (PCSs) under a wide range of DER-generation and load-demand scenarios. Subsequently, a convolutional neural network (CNN) is trained to learn a nonlinear mapping from multidimensional fault-current signatures to the corresponding optimized relay-setting vectors. In the online stage, the trained CNN serves as a predictive surrogate model, rapidly recommending coordinated relay settings for the current operating condition. The framework is validated using a 16-bus distribution system and the IEEE 37-bus test feeder. The results show that the proposed method can restore correct primary–backup relay operating sequences and maintain coordination time intervals (CTIs) within the required 0.2–0.4 s range under the studied DER-rich operating scenarios. This CNN-based preventive calibration approach provides a rapid, adaptive decision-support tool to improve protection coordination robustness against DER-induced operating uncertainties. Full article

Aiming at the difficulty of extracting fault features from nonlinear and non-stationary vibration signals of planetary gearboxes, a planetary gearbox fault diagnosis method based on Refined Composite Multiscale Fuzzy Entropy (RCMFE), Parametric-t-distributed Stochastic Neighbor Embedding (P-t-SNE), and Artificial Jellyfish Search Algorithm Optimized Support Vector Machine (JS-SVM) is proposed. Firstly, RCMFE is used to calculate and combine the feature vectors of the original fault signals of the planetary gearbox to construct the original high-dimensional fault feature set. Secondly, Parametric-t-SNE (P-t-SNE) based on a deep feedforward neural network is employed to reduce the dimensionality of the high-dimensional features, thereby extracting sensitive low-dimensional features and achieving out-of-sample mapping. Finally, the low-dimensional features are inputted into the JS-SVM for the identification of fault types. The experimental results of planetary gearbox fault diagnosis show that the proposed method can accurately identify common faults in planetary gearboxes, demonstrating promising application prospects. Full article

Induction motors remain the workhorse of modern industry thanks to their robustness, cost effectiveness and high efficiency, but the growing demands of electrified transport, high-performance automation and Industry 4.0 impose increasingly stringent control requirements. This paper presents an integrated, application-oriented survey of control strategies for high-performance induction motor drives, covering classic scalar V/f control as a baseline and advanced field-oriented control (FOC), direct torque control (DTC), model predictive control (MPC), nonlinear/robust schemes and intelligent/data-driven and digital twin-assisted solutions. The methods are analyzed within a unified framework in terms of dynamic response, torque and flux ripple, current harmonic distortion, efficiency, robustness, implementation complexity and suitability for sensorless and fault-tolerant operation. Emphasis is placed on hybrid strategies that combine classical vector or DTC structures with MPC, fuzzy and neuro-fuzzy logic, neural network-based observers, reinforcement learning and digital twin-enabled monitoring to reconcile fast dynamics with high efficiency, low ripple and lifecycle reliability. Consolidated comparison tables and a hybrid control map highlight typical performance trends, trade-offs between simplicity and performance, and the complementary roles of AI and digital twins as system-level enablers. The survey also outlines promising research directions toward systematically designed hybrid controllers, lightweight digital twins for embedded platforms and experimentally validated benchmarks that can accelerate the industrial uptake of next-generation induction motor drives. Full article

Reliable wind turbine component diagnosis requires cross-machine knowledge transfer since verified fault cases are rare. However, coarse fault interval annotations and turbine-specific operating behavior make this transfer difficult. This paper introduces a benchmark framework for cross-machine wind turbine component diagnosis on a new industrial dataset derived from Supervisory Control and Data Acquisition (SCADA) and vibration-derived kinematics data. The dataset is publicly available upon request and contains anomaly score-based embeddings. These embeddings are feature vectors whose entries quantify how strongly signals or component-related features deviate from learned normal behavior. The benchmark compares classical machine learning models, deep learning models, adversarial domain adaptation variants, and a simple baseline. Hyperparameter selection is performed without target labels using source classification loss, target prediction entropy, or Soft Neighborhood Density (SND). Our experiments show that, in the SCADA validation stage, source classification loss achieves the highest mean case diagnosis score among the evaluated objectives. In our evaluation, simple baselines remain highly competitive. The SCADA component score baseline achieves the highest test case diagnosis accuracy, while an ensemble of one-class support vector machines achieves the highest kinematics test case diagnosis accuracy. These findings indicate that anomaly score-based embeddings provide a useful representation for real-world component diagnosis, but that the small number of verified cases, coarse fault interval annotations, and partial label space mismatch remain major obstacles for reliable cross-machine adaptation. Full article

The stability and reliability of temperature sensors in industrial cooling systems are critical to process quality, energy efficiency, and operational safety. However, existing approaches lack systematic stability metrics and intelligent predictive capabilities. This study proposes an AI-driven framework integrating stability feature engineering with machine learning models for fault identification and early prediction of temperature sensors in power plant cooling systems. The framework introduces three physics-based stability indicators—rolling standard deviation (σ_roll), variation intensity index (VII), and short-term variation magnitude (ΔT_short)—to quantify sensor signal quality. These features, combined with operational parameters, are used to train support vector machine (SVM) and Long Short-Term Memory (LSTM) models for binary classification. The framework is validated using over 260,000 one-minute records per unit collected from three parallel steam-turbine generating units (Units 1, 2, and 3) of the same coastal thermal power plant. Each unit is served by an independent once-through seawater cooling loop instrumented with redundant Pt-100 temperature sensors at the inlet and outlet manifolds; the three units differ in their operating profile—Unit 1 operates under variable load with frequent cold-start events, Unit 2 under moderate variable load, and Unit 3 under stable high-load conditions—with data collected at 1 min intervals from January to June 2025. Under an explicitly anomaly-positive evaluation, with the full confusion matrix reported for every unit and model, classification performance is limited and strongly unit-dependent. In real-time identification, AUC-based ranking ability varies across units (SVM AUC = 0.65, 0.75, and 0.98 for Units 1–3; LSTM AUC = 0.66, 0.31, and 0.52), but under the extreme class imbalance (anomaly rate ≈ 0.07–0.13% in the test partitions), the calibrated operating-point precision and F1-scores remain low for all unit–model combinations (F1 ≤ 0.26, MCC ≤ 0.28). McNemar’s test indicates statistically significant paired differences for Units 1 and 2 but not for Unit 3. These results show that, on this dataset, neither model attains reliable anomaly classification, and that all reported metrics must be interpreted together with the disclosed confusion-matrix counts and severe class imbalance. The primary contribution of the framework is therefore methodological—physics-based stability indicators, redundant sensor cross-checking, and an operational false-alarm analysis—rather than high-accuracy prediction, and the study highlights the difficulty of learning-based prediction for rare, rule-defined thermal sensor anomalies. Full article

Deep networks dominate photovoltaic (PV) thermographic fault detection but need large annotated datasets and resist interpretation. We present a lightweight, interpretable infrared workflow combining support-vector-machine (SVM) module/background segmentation from four handcrafted features with an adaptive grid analysis labelling regions as nominal-intensity, high-intensity anomaly or low-intensity anomaly relative to a module-internal reference; the anomaly classes are inspection candidates, not confirmed faults. Evaluation used 21 close-range images of one 20 W module—recorded with the camera’s visible-light edge fusion active, so they are fused infrared/visible frames—and all 596 of a public five-sector UAV dataset. Segmentation against manual masks reached a mean intersection-over-union of 0.64; a feature ablation shows intensity statistics dominate, and an end-to-end Otsu pipeline gives almost the same high-intensity share (4.54% versus 4.50%): the SVM contributes reproducibility—removing the manual segmentation threshold, though not the empirical +48/−60 offsets—not accuracy. High-intensity regions concentrated in the module’s lower half, co-locating with a bus-bar defect known from hardware inspection—suggestive, not validated. The single-module, image-level close-range evaluation is optimistic, and the UAV shares, from a separately trained SVM, illustrate cross-domain application only. Segmentation runs at about 15 images per second on CPU. The method is a relative-intensity thermal screening workflow, not a validated defect-diagnosis or plant-health assessment method, and applies only where acquisition is controlled and the offsets are recalibrated for the target camera and palette. Full article

Traveling-wave fault location in distribution networks confronts two fundamental challenges: insufficient robustness of the cost function against heavy-tailed synchronization noise, and the location-resolution bottleneck imposed by the discrete search step. Starting from first physical principles, we identify that faulty-branch identity is encoded in the ordering pattern of multi-terminal TW arrival times rather than in their absolute values. Building on this insight, we propose a faulty-branch identification and precise fault-location method that integrates amplitude-assisted rank correlation (AAC) features with random forest (RF). At the theoretical level, we employ Hampel’s finite-sample breakdown-point framework to quantitatively establish that the $L_2$ cost function has an asymptotic breakdown point of zero, whereas the Spearman rank correlation coefficient attains an asymptotic breakdown point of 0.5—providing a rigorous robustness justification for replacing the $L_2$ residual with a rank-consistency cost. At the algorithmic level, the method consists of a three-stage inference pipeline: AAC computes a joint rank correlation cost for every line section across the network and extracts a 42-dimensional feature vector encompassing cost statistics, timing residuals, and topological attributes; feature selection is performed via fused ranking, which combines Pearson correlation, point-biserial correlation, and RF out-of-bag permutation importance through a weighted harmonic mean; the RF classifier directly performs branch identification over the full edge space, and the RF regressor predicts the coarse-location residual from local cost-terrain statistical features along the correctly identified branch, breaking through the 20 m search-step resolution bottleneck. We construct a five-layer physical noise model covering wavefront detection, time synchronization, wave-velocity deviation, reflected-wave misdetection, and terminal failure. Experiments on three structurally distinct 10 kV radial distribution network topologies, each with 5000 independently generated fault samples, demonstrate that branch identification accuracy remains stably above 94%, and residual correction reduces the mean location error from approximately 60 m to approximately 40 m—an improvement exceeding 30%—confirming the effectiveness of the physics–data hybrid framework for TW fault location in distribution networks. Full article

Motor fault identification is often constrained by scarce labeled samples and the limited representation capability of a single time–frequency transform. Conventional CNN–Softmax models may also produce unstable decision boundaries under small-sample conditions. To address these issues, this paper proposes a motor fault identification method based on the fusion of fixed-resolution and multiscale time–frequency features. Each vibration segment is transformed into short-time Fourier transform (STFT) and synchrosqueezed wavelet transform (SWT) maps. Two parallel convolutional branches extract complementary features, which are fused by element-wise addition and classified using a radial basis function support vector machine. Experiments on the HUST motor multimodal fault dataset show that the proposed method achieves 100% accuracy under the conventional 70%/30% train–test split. When the training proportion is reduced to 20%, 15%, 10%, and 5%, the corresponding accuracies remain at 99.46%, 99.10%, 98.78%, and 96.77%, respectively. Across operating speeds of 5, 10, 20, and 30 Hz, the average accuracies reach 98.75% and 94.61% under the 20% and 5% training conditions. The model also maintains 100% accuracy at signal-to-noise ratios of 15 dB and above. These results demonstrate that complementary time–frequency feature fusion combined with maximum-margin classification improves identification accuracy and decision-boundary stability under limited training data. Full article

Western Anatolia is a tectonically and seismically active region shaped by the complex interaction among the Eurasian, African, and Arabian plates. Since the Late Cenozoic, it has been dominated by an extensional tectonic regime. This study investigates the morphotectonic, seismotectonic, and kinematic evolution of the Edremit and Bakırçay basins and their surroundings, located at the intersection zone of the right-lateral strike-slip North Anatolian Fault System (NAFS) and the subduction-zone-driven Aegean Extensional System (AES). Within the scope of this research study, paleostress analyses were conducted using slip data obtained from fault planes, and these data were compared with 240 earthquake focal mechanism solutions reflecting the contemporary seismicity of the region. The findings indicate that both basins underwent a synchronized, two-stage tectonic evolution throughout the Plio-Quaternary period. During the first phase, encompassing the Pliocene, back-arc extensional forces related to slab rollback in the Hellenic subduction zone were dominant, and the main graben-forming processes (NW-SE-trending extension) took place. In the second phase, spanning the Quaternary period, an axis shift occurred as the southern branches of the NAFS reached the region, leading to the development of transtensional pull-apart basin mechanisms dominated by NE-SW-trending extension. Also supported by GPS velocity vectors and paleomagnetic block rotation data, this kinematic model demonstrates that the neotectonic evolution of Northwest Anatolia is governed not only by upper-crustal deformations but also by deep asthenospheric/lithospheric processes, such as slab rollback, lithospheric slab tear, and the NAFS-controlled westward differential escape of the Anatolian block. Full article