Search Results (706)

Maglev trains are susceptible to various types of operational challenges, including track irregularities, load variations, and actuator faults. It is evident that these factors can compromise suspension performance and even pose a serious risk to operational safety. This paper proposes a prescribed performance event-triggered fault-tolerant control method for the electromagnetic suspension system of a maglev train subject to multiple constraints. A projection-based adaptive extended state observer is designed to estimate the unknown gain caused by actuator faults and load variations, as well as the external disturbance. In light of the disparity in upper and lower safety margins inherent to the suspension gap error, arising from track irregularities, an asymmetric prescribed performance function and an error transformation are devised to ensure that the gap tracking error perpetually complies with the asymmetric prescribed performance constraint. In addressing the issue of rapid variations in the suspension gap, the vertical velocity is also constrained through the implementation of prescribed performance, resulting in a joint constraint framework that encompasses both the gap tracking error and the vertical motion. A dynamic event-triggered mechanism has been incorporated into the backstepping design with a view to reducing unnecessary control updates under limited communication resources, while Zeno behavior has been excluded from the closed-loop system. Within this framework, a dynamic gain adjustment mechanism with an explicitly bounded rate of variation is further developed to achieve smoother gain adaptation. The uniform ultimate boundedness of all closed-loop signals is demonstrated through Lyapunov stability analysis under the prescribed multiple constraints. The efficacy of the proposed method is demonstrated through comparative simulation results. Full article

This paper presents an adaptive noise-aware bearing fault diagnosis framework that integrates Fast Fourier Transform (FFT)-windowed feature extraction, wavelet-based Signal-to-Noise Ratio (SNR) estimation, and Long Short-Term Memory (LSTM) classification to maintain high diagnostic accuracy under both clean and severely noisy operating conditions. The core novelty of the proposed framework lies in its adaptive model selection mechanism, which automatically selects the most appropriate LSTM classifier according to the estimated SNR, thereby improving diagnostic robustness across different noise environments. Experiments were conducted on two benchmark datasets, the Case Western Reserve University (CWRU) dataset and the Huazhong University of Science and Technology (HUST) bearing dataset, to evaluate the generalization capability of the proposed approach. Two preprocessing pipelines were examined: time-domain normalization before FFT and frequency-domain normalization after FFT. Vibration signals were segmented without overlap to ensure unbiased evaluation. The results demonstrate that both the choice of window function and the normalization strategy significantly influence classification accuracy and robustness. Under noise-free conditions, several window types achieved accuracies above 99%, with triangular and Hamming windows providing the best performance. The combination of triangular windowing and time-domain normalization achieved the highest accuracy of 99.69%. Furthermore, time-domain normalization combined with triangular windowing exhibited superior stability and noise resistance compared with frequency-domain normalization. Under noisy conditions, noise-augmented training was found to be essential for achieving robust generalization. Models trained with moderate noise levels (8–12 dB) provided the best trade-off between accuracy and robustness, whereas excessive noise during training degraded performance. To accommodate varying noise environments, a lightweight wavelet-based SNR estimator was used to categorize operating conditions into low-, medium-, and high-SNR regions and select the corresponding LSTM classifier. The proposed framework was successfully implemented on a ZedBoard FPGA (Field-Programmable Gate Array) development board using a System-on-Chip (SoC) architecture. Experimental results show that, with a sampling frequency of 48 kHz and a processing window of 2048 samples, the proposed system updates the diagnostic result every 42.7 ms, demonstrating its suitability for real-time industrial condition monitoring and intelligent predictive maintenance applications. Full article

This paper studies the automatic berthing control of an unmanned surface vessel under cyber attacks. An adaptive neural-network-based fault-tolerant control method is developed. Unknown vessel dynamics, external disturbances, measurement noise, and cyber attacks are considered at the same time. First, the signal scaling, bias, and power-type distortion caused by cyber attacks are described by a unified nonlinear measurement model. The model has a known structure and unknown parameters. It converts different attack effects into structured uncertainties. Based on the corrupted position and attitude measurements, the tracking errors are defined. The vessel heading is reconstructed by integrating the unaffected yaw-rate signal. A Nussbaum-type function is introduced to handle the unknown gain in the measurement channel. A first-order filter is used to generate a smooth approximation of the virtual control signal. A neural network is then employed to approximate the unknown vessel dynamics. Adaptive laws are designed to estimate the composite uncertainties and external disturbances. Lyapunov analysis shows that all closed-loop signals remain bounded. The berthing tracking errors ultimately converge to a compact set around the origin. Finally, a berthing simulation with time-varying cyber attacks, measurement noise, and marine disturbances is conducted to evaluate the proposed method. 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

Edge monitoring balances diagnostic information against high-rate sensing costs. We formulate active acquisition: Low-cost signals screen each window, while high-information channels are acquired when alarms require confirmation or the screen is uncertain or out of distribution. The confirmation-complete controller includes an optional watchdog to bound blind intervals. On a five-stress benchmark, it retains 98.42% Macro-F1 versus 99.02% for always-full sensing, with 77.59% activation and 19.27% lower normalized resource costs. CWRU evaluation yields 99.25 ± 0.41% Macro-F1 at 83.30% activation. Paderborn condition-transfer evaluation matches always-full sensing at 91.08 ± 17.55% but activates every window; few-shot commissioning increases 15-bearing performance from 58.42 ± 18.60% to 76.52%. When each damage type is excluded from training and bearing identities are separated, the policy activates for 85.25 ± 18.84% of unseen-fault windows versus 83.61 ± 25.69% for a learned error gate. Across 40 healthy-to-unseen replays, 95% activate within five decision windows; an $H=10$ watchdog limits the inactive run to nine. These rates measure escalation, not unknown-class identification. An ESP32 pilot verifies telemetry feasibility but not sensor-rail power or end-to-end diagnosis. Reduced sensing is credible when the confirm stage transfers; otherwise, commissioning or conservative acquisition is required. Full article

Asynchronous motors are widely used in electric vehicle drive systems because of their simple structure, low cost, and high reliability. Accurate speed tracking and smooth transient response are important during start-up, acceleration, and deceleration. However, sensing uncertainties and sensor faults may affect the measured signals and reduce control performance. In this study, an adaptive prescribed performance control (PPC) method is developed for asynchronous motor speed regulation. A nonlinear mapping and an improved tangent-type barrier Lyapunov function (BLF) are used to remove the requirement that the initial tracking error must lie within the prescribed performance bounds. Radial basis function neural networks are used to approximate the unknown nonlinear terms. The stability analysis shows that all closed-loop signals remain bounded and that the tracking error enters and remains within the prescribed performance region after the initial expansion stage. Simulations under different initial motor speeds, the considered sensor-fault conditions, and load disturbances are conducted. Under the adopted comparative conditions, the proposed method reduces the convergence time, steady-state error, maximum tracking error, and recovery time by 69.5%, 93.4%, 92.2%, and 49.4%, respectively. The results show that the proposed method improves the transient response, tracking accuracy, and disturbance recovery of the asynchronous motor drive system. Full article

The Tan–Lu Fault Zone (TLFZ) is a lithosphere-scale fault system in eastern Asia with pronounced along-strike heterogeneity in structure and fluid activity. Previous geochemical studies have largely focused on individual segments, sample media, or single tracers, leaving the fault-zone-scale organization of fluid geochemical signals unresolved. Here, published helium-isotope data and cross-fault soil-gas CO₂ and Rn observations are integrated within a common fault-parallel coordinate framework to compare source-sensitive proxies with those more responsive to transport and near-surface processes. The three proxy groups define contrasting spatial patterns. Mantle-derived He is strongest and spatially focused in Liaoning, intermediate but comparatively persistent in Anhui–Jiangsu, and generally subdued in the available Shandong dataset. Soil-gas CO₂ and Rn anomalies, by contrast, are most continuous in Anhui–Jiangsu, locally enhanced in Liaoning, and subdued to intermediate in the available Shandong transects. Combining the mantle-derived He state with the soil-gas response identifies four proxy-association types. The most laterally continuous Type I interval extends for approximately 200 km in the Anhui–Jiangsu segment, whereas southern Liaoning is characterized by spatially focused, adjacent Type II and Type I intervals. These contrasting associations show that the near-surface expression of deep-derived fluids depends not only on volatile availability, but also on crustal pathway connectivity, groundwater circulation, and modification during transport and release. The integrated comparison reveals where deep-source and shallow-response signals are coupled or decoupled along the TLFZ, providing a basis for evaluating fault-zone fluid segmentation. Full article

This paper presents a structured review of antenna and electromagnetic spectrum monitoring techniques for non-invasive fault detection in electrical and electronic equipment. Electromagnetic emissions from partial discharges, arc faults, insulation degradation, and component ageing carry diagnostic signatures detectable through remote radio-frequency sensing. We review (1) antenna technologies spanning magnetic-field loops to ultra-high-frequency electric-field sensors, including fractal, Vivaldi, spiral, and bio-inspired designs; (2) data acquisition platforms ranging from laboratory oscilloscopes to software-defined radio receivers and IoT edge nodes; (3) signal processing methods including time–frequency analysis, adaptive decomposition, and statistical techniques; and (4) machine learning approaches from classical classifiers to deep learning architectures such as convolutional neural networks, recurrent neural networks, and Transformer-based models. Unlike prior surveys focusing on individual fault types or specific equipment classes, this review connects all five layers of the sensing pipeline—from electromagnetic emission physics through antenna selection, signal acquisition, processing, and intelligent classification—for partial-discharge, arc, and insulation faults and analyses the cross-layer constraints that couple them. Design optimisation techniques based on computational electromagnetic methods (FDTD, FEM) and sensitivity calibration challenges are discussed. Open challenges, including the lack of standardised UHF calibration, cross-equipment generalisation, and the scarcity of open electromagnetic fault datasets, are identified, along with emerging directions in flexible antennas, edge AI, and digital twin integration. Full article

When marine chillers operate under complex marine conditions, they suffer from severe cross-equipment feature distribution shifts, scarce labeled fault samples in the target domain, industrial vibration noise mixed in sensor signals, and difficulties in accurately identifying subtle faults with varying severity levels. To tackle these issues, this paper improves upon the domain difference perception network (DDPN) and proposes a dual-hybrid attention feature discriminant domain-Adversarial network (DAFDAN) to realize intelligent fault diagnosis across different equipment and working conditions under few-shot scenarios. The proposed method constructs a dual-branch feature encoder consisting of a source domain compressor and a target domain extender to accommodate the distinct sensor dimensions of two heterogeneous chiller types. A hybrid attention module is formed by integrating squeeze-and-excitation efficient channel attention (SE-ECA, a module for screening channel-wise features) and spatial attention, which adaptively amplifies time-series features sensitive to faults and suppresses irrelevant noise. Residual connections (shortcut paths in deep neural networks to mitigate the vanishing gradient problem during deep-layer training) are introduced to optimize feature transmission. A dual-layer domain alignment framework is built with gradient reversal layers and maximum mean discrepancy (MMD). Combined with adversarial training (a training paradigm that learns domain-agnostic features through a game between a feature extractor and a domain discriminator), the framework achieves joint optimization of implicit feature confusion and explicit distance constraints. Meanwhile, a five-stage progressive training strategy is designed, which activates multiple loss functions, including weighted cross-entropy, mean square error (MSE), binary cross-entropy (BCE), and Kullback–Leibler (KL) divergence stage by stage. Class weighting and early stopping strategies are adopted to alleviate sample imbalance and model overfitting. In this paper, the public ASHRAE RP-1043 centrifugal chiller dataset is used as the source domain, and time-series measurement data collected from a self-developed laboratory marine screw chiller serves as the target domain. Verification experiments are carried out covering one normal steady-state operating condition and 15 gradient faults falling into five major categories with different severity degrees. Results from ablation experiments (controlled-variable comparative experiments that quantify the independent contribution of each component by comparing model performance with or without a specific module/loss), multi-algorithm comparisons, and confusion matrix visualization demonstrate that the cross-domain fault diagnosis accuracy of the proposed DAFDAN approaches is 100%, outperforming mainstream transfer learning algorithms such as support vector machine (SVM), deep neural network (DNN), MMD, correlation alignment (CORAL), and domain-adversarial neural network (DANN). Multiple ablation experiments verify that the three core components—hybrid attention, adversarial training, and semi-supervised learning—jointly boost the model’s diagnosis accuracy and operational stability. The loss curves of the complete five-stage training process converge smoothly. The confusion matrix reveals zero misjudgments and zero false alarms across all 16 refined operating states, enabling precise identification of subtle incipient faults of all severity levels. This study proves that DAFDAN can effectively address the pain points of few-shot cross-equipment fault diagnosis for marine chillers and provides a reliable algorithmic reference for the intelligent operation and maintenance of ship refrigeration equipment. Full article

Induction machines play a crucial role in industrial applications, making preventive maintenance combined with fault diagnosis techniques essential for ensuring reliable operation. One of the most widely used diagnostic methods for induction machines is Motor Current Signature Analysis (MCSA). However, this technique has certain limitations, particularly in the detection of incipient or small faults. Another well-established technique is Motor Square Current Signature Analysis (MSCSA), which overcomes some of the limitations of MCSA by extracting additional fault-related information from the motor current signals. This paper proposes a new diagnostic technique, designated MSCSA-APT (Motor Square Current Signature Analysis–Alternative Park Transform), based on the spectral analysis of motor currents. Compared with the conventional MSCSA method, the proposed approach provides additional information from the frequency-domain analysis, thereby improving fault detection capability. The method is based on the square of the motor square current signal and employs an Alternative Park Transform (APT) to enhance the extraction of fault signatures. Simulation and experimental results are presented to validate the proposed approach. Although the method has been evaluated for the identification of different types of faults, it is particularly effective in detecting stator short-circuit faults. Full article

Gearbox fault diagnosis under noisy operating conditions remains a critical yet unsolved challenge for industrial condition monitoring. The primary challenge originates from a fundamental conflict: fault signatures are present within certain frequency ranges, yet standard deep learning models process raw vibration signals without recognizing which frequencies are relevant. Moreover, noise affects the entire spectrum uniformly. Existing transformer-based methods for vibration analysis treat time steps as tokens and therefore fail to capture cross-sensor dependencies, while conventional denoising approaches apply fixed filters that cannot adapt to the varying spectral characteristics of different fault types and noise levels. We propose the Adaptive Frequency-Aware Inverted Transformer (AF-iTransformer), a lightweight transformer framework that lets the model learn which frequencies to attend to on a per-sample basis. In particular, we propose a learnable spectral filter that transforms the input signal to the frequency domain via FFT. Then it predicts a soft frequency mask conditioned on signal statistics and applies it before reconstructing the filtered signal through iFFT, allowing the model to suppress noise bands while preserving fault-relevant spectral content dynamically. After adaptive filtering, the architecture employs channel-level tokenization to uniformly represent heterogeneous channels as input tokens, relying on cross-channel attention to automatically learn their distinct contributions to fault diagnosis. Feature-wise linear modulation is introduced to inject signal-level statistics at every encoder layer. Furthermore, the framework utilizes residual attention propagation to stabilize deep training, and an auxiliary spectrum prediction head provides spectral regularization during training. On the UConn Gearbox dataset with nine fault categories, AF-iTransformer achieves 99.63% accuracy on clean data and maintains 95.1% at 0 dB signal-to-noise ratio, substantially outperforming all baselines under noisy conditions. On the SEU gearbox dataset with five fault categories, AF-iTransformer achieves 99.74% clean accuracy. On 2 GB edge GPUs, AF-iTransformer achieves a per-window inference latency of 7.3–13 ms with peak memory below 17 MB, and 1.4–4.7 ms on modern CPUs, confirming its viability for real-time industrial deployment. Full article

Aiming at the problems of fault samples being difficult to obtain in fault diagnosis research on heavy-duty bearings of thin-seam shearers and the insufficient diagnostic performance of existing methods under small-sample conditions, this study focuses on dataset construction, sample augmentation and fault diagnosis. First, based on the virtual prototype model of the cutting-unit transmission system of a thin-seam shearer, three-dimensional models of healthy bearings and four typical fault types (inner ring fault, outer ring fault, rolling-element fault and cage fault) of heavy-duty bearings were built using SolidWorks 2024. Vibration signals were collected through ADAMS dynamic simulation and converted into time-frequency images via Continuous Wavelet Transform (CWT), thereby constructing an original fault dataset with five states. Furthermore, a conditional generative adversarial network incorporating VGG perceptual loss (VGG-CGAN) was proposed to achieve targeted sample augmentation for the five bearing states, effectively alleviating the class-imbalance problem. On this basis, an improved ResNet50 fault-diagnosis model was constructed, and Bayesian optimization was used to automatically tune key hyperparameters. Experimental results show that the improved ResNet50 model achieved an accuracy of 87.14% on the self-built thin-seam shearer heavy-duty bearing dataset and 98.28% on the public CWRU dataset. The proposed method exhibits strong diagnostic performance and generalization ability under small-sample and imbalanced data conditions. This study can provide new ideas and useful references for fault diagnosis of heavy-duty bearings in thin-seam shearers. Full article

To address class imbalance in transmission line fault traveling-wave samples, the strong non-stationarity of transient traveling-wave features, and the limited identification capability of single-representation methods, this paper proposes a fault type identification method that integrates Polar Lights Optimizer (PLO)-based feature selection with a Gramian Angular Field (GAF) attention fusion network. First, the Borderline Synthetic Minority Over-sampling Technique (Borderline-SMOTE) is applied to balance six fault categories in the training set, and time domain, frequency domain, time–frequency domain, and waveform-edge features are extracted from traveling-wave signals acquired by online monitoring devices. Then, PLO is used to select key explicit features, while the preprocessed traveling-wave sequences are encoded into dual-branch images using the Gramian Angular Summation Field (GASF) and the Gramian Angular Difference Field (GADF). Finally, a Gramian Angular Field–Parallel Convolutional Neural Network–Attention (GAF-PCNN-AT) model is constructed to fuse deep image features with selected explicit features for fault identification. Validation on the independent real test set under a representative stratified 8:2 split shows that the proposed method achieves an accuracy of 95.40% and an average area under the curve (AUC) of 0.9900 in the six-class fault identification task. The results indicate that the proposed method can effectively integrate deep image features of traveling-wave signals with PLO-selected explicit features, thereby providing high identification accuracy and good overall classification performance. Full article

The problem of fault diagnosis in electrical motors has an important impact on the supervision of dynamic systems, and model-based methods are efficient tools for this purpose. In this regard, this work presents a novel method for detecting inter-turn short circuits (ITSCs) in the stator windings of permanent magnet synchronous motors (PMSMs). The approach is based on algebraic identification to process the motor voltage signals, estimating the offsets, amplitudes, and phases of the fundamental and third-harmonic components. Fault detection is performed in two steps: first, a voltage imbalance index is evaluated to determine the presence of abnormal operating conditions. Subsequently, characteristic patterns in the estimated parameters are analyzed to identify both the fault type and the affected phase(s). The experimental results show that single-phase ITSC faults produce a reduction in the offset of the faulted phase together with an increase in its third-harmonic amplitude, whereas phase-to-phase ITSC faults lead to an increase in the offsets of the affected phases and nearly identical third-harmonic amplitudes between them. In both cases, only minor variations are observed in the estimated phase angles. The effectiveness of the proposed methodology is supported through theoretical analysis and validated experimentally using voltage measurements acquired from a PMSM test bench. The results demonstrate that the proposed technique can accurately identify fault conditions through voltage imbalance and harmonic-pattern analysis, providing a practical and computationally efficient methodology for PMSM stator winding fault diagnosis. Full article

Satellite constellation fault diagnosis presents significant challenges, including excessive inter-satellite communication overhead, data heterogeneity, satellite platform heterogeneity, and limited model generalization. To address these issues, this paper proposes an Adaptive Federated Dual Knowledge Distillation (AFDL) framework. First, we develop a heterogeneous federated learning architecture where different satellite types are modeled as independent local clients. Each client incorporates a dedicated local feature extractor to capture its personalized characteristics. Second, a collaborative knowledge distillation mechanism is designed to integrate soft supervision signals from the global server model with personalized feature knowledge from diverse local clients. Finally, a task-specific knowledge distillation strategy is introduced, which employs targeted distillation and dynamic weight adaptation to enhance the generalization performance of local clients. Extensive experiments demonstrate that AFDL achieves 92.3% server accuracy and 84.8% client unseen fault accuracy on our self-collected dataset, outperforming the strongest federated learning baselines by 11.2 and 21.2 percentage points, respectively, while reducing communication overhead by 57.1% compared with centralized learning. Experiments on the public ESA anomaly dataset further confirm the generalization capability of AFDL under real satellite telemetry data. These results validate that AFDL enables efficient and adaptive fault diagnosis across heterogeneous satellite constellations with moderate communication costs. Full article