Search Results (479)

The integration of machine learning (ML) into industrial automation is fundamentally reshaping how manufacturing systems are monitored, inspected, and optimized. By applying machine learning to real-time sensor data and operational histories, advanced models enable proactive fault prediction, intelligent inspection, and dynamic process control—directly enhancing system reliability, product quality, and efficiency. This review explores the transformative role of ML across three key domains: Predictive Maintenance (PdM), Quality Control (QC), and Process Optimization (PO). It also analyzes how Digital Twin (DT) and Edge AI technologies are expanding the practical impact of ML in these areas. Our analysis reveals a marked rise in deep learning, especially convolutional and recurrent architectures, with a growing shift toward real-time, edge-based deployment. The paper also catalogs the datasets used, the tools and sensors employed for data collection, and the industrial software platforms supporting ML deployment in practice. This review not only maps the current research terrain but also highlights emerging opportunities in self-learning systems, federated architectures, explainable AI, and themes such as self-adaptive control, collaborative intelligence, and autonomous defect diagnosis—indicating that ML is poised to become deeply embedded across the full spectrum of industrial operations in the coming years. Full article

To enhance the reliability of electric propulsion in electric aircraft and address power interruptions caused by current sensor failures, this study proposes a current sensorless fault-tolerant control strategy for permanent magnet synchronous motors (PMSMs) based on a long short-term memory (LSTM) network. First, a hierarchical architecture is constructed to fuse multi-phase electrical signals in the fault diagnosis layer (sliding mode observer). A symbolic function for the reaching law observer is designed based on Lyapunov theory, in order to generate current predictions for fault diagnosis. Second, when a fault occurs, the system switches to the LSTM reconstruction layer. Finally, gating units are used to model nonlinear dynamics to achieve direct mapping of speed/position to phase current. Verification using a physical prototype shows that the proposed method can complete mode switching within 10 ms after a sensor failure, which is 80% faster than EKF, and its speed error is less than 2.5%, fully meeting the high speed error requirements of electric aircraft propulsion systems (i.e., ≤3%). The current reconstruction RMSE is reduced by more than 50% compared with that of the EKF, which ensures continuous and reliable control while maintaining the stable operation of the motor and realizing rapid switching. The intelligent algorithm and sliding mode control fusion strategy meet the requirements of high real-time performance and provide a highly reliable fault-tolerant scheme for electric aircraft propulsion. Full article

As power systems evolve rapidly, cables, essential for electric power transmission, demand accurate and timely fault diagnosis to ensure grid safety and stability. However, current cable fault diagnosis technologies often struggle with incomplete feature extraction from complex fault signals and inefficient parameter tuning in diagnostic models, hindering efficient and precise fault detection in modern power systems. To address these, this paper proposes a data-driven strategy for cable fault diagnosis in substation secondary circuits, enhanced by effective parameter optimization. Initially, wavelet packet decomposition is employed to finely divide collected cable fault current signals into multiple levels and bands, effectively extracting fault feature vectors. To tackle the challenge of selecting penalty and kernel parameters in Support Vector Machine (SVM) models, an improved Golden Jackal Optimization (GJO) algorithm is introduced. This algorithm simulates the predatory behavior of golden jackals in nature, enabling efficient global optimization of SVM parameters and significantly improving the classification accuracy and generalization capability of the fault diagnosis model. Simulation verification using real cable fault cases confirms that the proposed method outperforms traditional techniques in fault recognition accuracy, diagnostic speed, and robustness, proving its effectiveness and feasibility. This study offers a novel and efficient solution for cable fault diagnosis. Full article

In industrial systems, sensors often classify collected time series data for incipient fault diagnosis. However, time series data from sensors during the initial stages of a fault often exhibits minor fluctuation characteristics. Existing time series classification (TSC) methods struggle to achieve high classification accuracy when these minor fluctuations serve as the primary distinguishing feature. This limitation arises because the low-amplitude variations of these fluctuations, compared with trends, lead the classifier to prioritize and learn trend features while ignoring the minor fluctuations crucial for accurate classification. To address this challenge, this paper proposes a novel graph-based time series classification framework, termed MFSI-TSC. MFSI-TSC first extracts the trend component of the raw time series. Subsequently, both the trend series and the raw series are represented as graphs by extracting the “visible relationship” of the series. By performing a subtraction operation between these graphs, the framework isolates the differential information arising from the minor fluctuations. The subtracted graph effectively captures minor fluctuations by highlighting topological variations, thereby making them more distinguishable. Furthermore, the framework incorporates optimizations to reduce computational complexity, facilitating its deployment in resource-constrained sensor systems. Finally, empirical evaluation of MFSI-TSC on both real-world and publicly available datasets demonstrates its effectiveness. Compared with ten benchmark methods, MFSI-TSC exhibits both high accuracy and computational efficiency, making it more suitable for deployment in sensor systems to complete incipient fault detection tasks. Full article

This study presents a Variational Autoencoder (VAE)-based framework for the unsupervised mechanical fault diagnosis of high-voltage isolation switches. By analyzing voltage and current signals to compute instantaneous power sequences, the method detects anomalies through reconstruction errors. Experimental results from both laboratory and real-world datasets demonstrate that the VAE model outperforms traditional methods, offering high diagnostic accuracy and robustness without the need for labeled data or manual feature extraction. This approach provides an effective solution for the real-time monitoring and predictive maintenance of high-voltage switchgear. Full article

Coastal areas are prone to thunderstorms. Lightning strikes can damage power facilities and communication systems, thereby leading to serious consequences. The lightning location network achieves lightning location through data fusion from multiple lightning locator nodes and can detect the location and intensity of lightning in real time. It is an important facility for thunderstorm warning and protection in coastal areas. However, when a sensor node in a lightning location network experiences a soft fault, it causes distortion in the lightning location. To achieve fault diagnosis of lightning locator nodes in a multi-node data fusion mode, this study proposes a new lightning location mode: the observer pattern. This paper first analyzes the main factors contributing to the error of the lightning location algorithm under this mode, proposes an observer pattern estimation algorithm (OPE) for lightning location, and defines the proportion of improvement in lightning positioning accuracy (PI) caused by the OPE algorithm. By analyzing the changes in PI in the process of lightning location, this study further proposes a diagnostic algorithm (OPSFD) for soft-fault nodes in a lightning location network. The simulation experiments in the paper demonstrate that the OPE algorithm can effectively improve the positioning accuracy of existing lightning location networks. Therefore, the OPE algorithm is also a low-cost and efficient method for improving the accuracy of existing lightning location networks, and it is suitable for the actual deployment and upgrading of current lightning locators. Meanwhile, the experimental results show that when a soft fault causes the observation error of the node to exceed the normal range, the OPSFD algorithm proposed in this study can effectively diagnose the faulty node. Full article

Ships play a crucial role in modern society, serving purposes such as marine transportation, tourism, and exploration. Malfunctions or defects in the main engine, which is a core component of ship operations, can disrupt normal functionality and result in substantial financial losses. Consequently, early fault diagnosis of abnormal engine conditions is critical for effective maintenance. In this paper, we propose a deep hybrid model for fault diagnosis of ship main engines, utilizing exhaust gas temperature data. The proposed model utilizes both time-domain features (TDFs) and time-series raw data. In order to effectively extract features from each type of data, two distinct feature extraction networks and an attention module-based classifier are designed. The model performance is evaluated using real-world cylinder exhaust gas temperature data collected from the large ship low-speed two-stroke main engine. The experimental results demonstrate that the proposed method outperforms conventional methods in fault diagnosis accuracy. The experimental results demonstrate that the proposed method improves fault diagnosis accuracy by 6.146% compared to the best conventional method. Furthermore, the proposed method maintains superior performanceeven in noisy environments under realistic industrial conditions. This study demonstrates the potential of using exhaust gas temperature using a single sensor signal for data-driven fault detection and provides a scalable foundation for future multi-sensor diagnostic systems. Full article

In the era of rapid industrial automation advancements, the complexity of intelligent manufacturing equipment has been steadily escalated. Stringent demands for high-efficiency and high-precision diagnosis are increasingly being unmet by conventional fault diagnosis methods. To address these challenges, a novel fault diagnosis approach grounded in quantum Q-learning is presented in this paper. The distinct advantages of quantum computing are innovatively integrated with the decision-making framework of Q-learning through this method. By harnessing the multi-information-carrying capacities of qubits, vast amounts of multi-source heterogeneous data generated during equipment operation can be efficiently processed. Latent fault features are thereby rapidly uncovered, significantly reducing the time required for fault-feature extraction. Furthermore, optimal decisions can be dynamically formulated by Q-learning within evolving production environments, leveraging precise analysis outcomes from quantum computing. Real-time equipment status is continuously monitored to accurately identify fault types, pinpoint locations, and promptly generate targeted maintenance strategies. Fault-diagnosis tests conducted on typical industrial intelligent manufacturing equipment demonstrate that the quantum Q-learning method outperforms traditional approaches in terms of diagnosis accuracy, efficiency, and adaptability to complex fault patterns. This breakthrough opens up new frontiers for fault diagnosis in intelligent manufacturing systems. Full article

In high-voltage transmission lines, insulators subjected to prolonged electromechanical stress are prone to zero-value defects, leading to insulation failure and posing significant risks to power grid reliability. The conventional detection method of spark gap is vulnerable to environmental interference, while the emerging electric field distribution-based techniques require complex instrumentation, limiting its applications in scenes of complex structures and atop tower climbing. To address these challenges, this study proposes an electroluminescent sensing strategy for zero-value insulator identification based on the electroluminescence of ZnS:Cu. Based on the stimulation of electrical stress, real-time monitoring of the health status of insulators was achieved by applying the composite of epoxy and ZnS:Cu onto the connection area between the insulator steel cap and the shed. Experimental results demonstrate that healthy insulators exhibit characteristic luminescence, whereas zero-value insulators show no luminescence due to a reduced drop in electrical potential. Compared with conventional detection methods requiring access of electric signals, such non-contact optical detection method offers high fault-recognition accuracy and real-time response capability within milliseconds. This work establishes a novel intelligent sensing paradigm for visualized condition monitoring of electrical equipment, demonstrating significant potential for fault diagnosis in advanced power systems. Full article

Large turbine generators rely on shaft earthing brushes to safely divert harmful shaft currents to ground, protecting bearings from electrical damage. This paper presents a novel deep learning-based diagnostic framework to detect and classify faults in shaft earthing brushes of large turbine generators. A key innovation lies in the use of FFT-derived spectrograms from both voltage and current waveforms as dual-channel inputs to the CNN, enabling automatic feature extraction of time–frequency patterns associated with different SEB fault types. The proposed framework combines advanced signal processing and convolutional neural networks (CNNs) to automatically recognize fault-related patterns in shaft grounding current and voltage signals. In the approach, raw time-domain signals are converted into informative time–frequency representations, which serve as input to a CNN model trained to distinguish normal and faulty conditions. The framework was evaluated using data from a fleet of large-scale generators under various brush fault scenarios (e.g., increased brush contact resistance, loss of brush contact, worn out brushes, and brush contamination). Experimental results demonstrate high fault detection accuracy (exceeding 98%) and the reliable identification of different fault types, outperforming conventional threshold-based monitoring techniques. The proposed deep learning framework offers a novel intelligent monitoring solution for predictive maintenance of turbine generators. The contributions include the following: (1) the development of a specialized deep learning model for shaft earthing brush fault diagnosis, (2) a systematic methodology for feature extraction from shaft current signals, and (3) the validation of the framework on real-world fault data. This work enables the early detection of brush degradation, thereby reducing unplanned downtime and maintenance costs in power generation facilities. Full article

This article presents a hybrid fault diagnosis framework for DC–DC converters in photovoltaic (PV) systems, combining digital twin (DT) modelling and detection with machine learning anomaly classification. The proposed method addresses both hardware faults such as open and short circuits in insulated-gate bipolar transistors (IGBTs) and diodes and sensor-level false data injection attacks (FDIAs). A five-dimensional DT architecture is employed, where a virtual entity implemented using FMI-compliant FMUs interacts with a real-time emulated physical plant. Fault detection is performed by comparing the real-time system behaviour with DT predictions, using dynamic thresholds based on power, voltage, and current sensors errors. Once a discrepancy is flagged, a second step classifier processes normalized time-series windows to identify the specific fault type. Synthetic training data are generated using emulation models under normal and faulty conditions, and feature vectors are constructed using a compact, interpretable set of statistical and spectral descriptors. The model was validated using OPAL-RT Hardware in the Loop emulations. The results show high classification accuracy, robustness to environmental fluctuations, and transferability across system configurations. The framework also demonstrates compatibility with low-cost deployment hardware, confirming its practical applicability for fault diagnosis in real-world PV systems. Full article

Ensuring the reliability and robustness of spacecraft systems remains a key challenge, particularly given the limited feasibility of continuous real-time monitoring during on-orbit operations. In the domain of Fault Detection, Isolation, and Recovery (FDIR), no universal strategy has yet emerged. Traditional approaches often rely on precise, model-based methods executed onboard. This study explores data-driven alternatives for self-diagnosis and fault detection using Machine Learning techniques, focusing on spacecraft Guidance, Navigation, and Control (GNC) subsystems. A high-fidelity functional engineering simulator is employed to generate realistic datasets from typical onboard signals, including sensor and actuator outputs. Fault scenarios are defined based on potential failures in these elements, guiding the data-driven feature extraction and labeling process. Supervised learning algorithms, including Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs), are implemented and benchmarked against a simple threshold-based detection method. Comparative analysis across multiple failure conditions highlights the strengths and limitations of the proposed strategies. Results indicate that Machine Learning techniques are best applied not as replacements for classical methods, but as complementary tools that enhance robustness through higher-level self-diagnostic capabilities. This synergy enables more autonomous and reliable fault management in spacecraft systems. Full article

Under complex operating conditions, vibration signals from rotating machinery often exhibit non-stationary characteristics with non-proportional and closely spaced instantaneous frequency (IF) components. Traditional time–frequency analysis (TFA) methods struggle to accurately extract such features due to energy leakage and component mixing. In response to these issues, an enhanced time–frequency analysis approach, termed Local Entropy Selection Scaling–Reassigning Chirplet Transform (LESSRCT), has been developed to improve the representation accuracy for complex non-stationary signals. This approach constructs multi-channel time–frequency representations (TFRs) by introducing multiple scales of chirp rates (CRs) and utilizes a Rényi entropy-based criterion to adaptively select multiple optimal CRs at the same time center, enabling accurate characterization of multiple fundamental components. In addition, a frequency reassignment mechanism is incorporated to enhance energy concentration and suppress spectral diffusion. Extensive validation was conducted on a representative synthetic signal and three categories of real-world data—bat echolocation, inner race bearing faults, and wind turbine gearbox vibrations. In each case, the proposed LESSRCT method was compared against SBCT, GLCT, CWT, SET, EMCT, and STFT. On the synthetic signal, LESSRCT achieved the lowest Rényi entropy of 13.53, which was 19.5% lower than that of SET (16.87) and 35% lower than GLCT (18.36). In the bat signal analysis, LESSRCT reached an entropy of 11.53, substantially outperforming CWT (19.91) and SBCT (15.64). For bearing fault diagnosis signals, LESSRCT consistently achieved lower entropy across varying SNR levels compared to all baseline methods, demonstrating strong noise resilience and robustness. The final case on wind turbine signals demonstrated its robustness and computational efficiency, with a runtime of 1.31 s and excellent resolution. These results confirm that LESSRCT delivers robust, high-resolution TFRs with strong noise resilience and broad applicability. It holds strong potential for precise fault detection and condition monitoring in domains such as aerospace and renewable energy systems. Full article

This paper introduces a novel end-to-end fault diagnosis framework that integrates Bidirectional Long Short-Term Memory (BiLSTM) networks with Time-Domain Reflectometry (TDR) for the detection, characterization, and localization of wiring faults. The method is designed to operate directly on TDR signals, requiring no manual feature extraction or preprocessing. A forward model is used to simulate TDR responses across various fault scenarios and topologies, serving as the basis for supervised learning. The proposed BiLSTM-based model is trained and validated on common wiring network topologies, demonstrating high diagnostic performance. Experimental results show a diagnostic accuracy of 98.97% and a macro-average sensitivity exceeding 98%, outperforming conventional machine learning techniques. In addition to technical performance, the proposed approach supports sustainable and predictive maintenance strategies by reducing manual inspection efforts and enabling real-time automated diagnostics. Full article

Real-time bearing fault diagnosis necessitates highly accurate, computationally efficient, and energy-conserving models suitable for deployment on resource-constrained edge devices. To address these demanding requirements, we propose the Spike Convolutional Attention Network (SpikeCAN), a novel spike-driven neural architecture tailored explicitly for real-time industrial diagnostics. SpikeCAN utilizes the inherent sparsity and event-driven processing capabilities of spiking neural networks (SNNs), significantly minimizing both computational load and power consumption. The SpikeCAN integrates a multi-dilated receptive field (MDRF) block and a convolution-based spike attention module. The MDRF module effectively captures extensive temporal dependencies from signals across various scales. Simultaneously, the spike-based attention mechanism dynamically extracts spatial-temporal patterns, substantially improving diagnostic accuracy and reliability. We validate SpikeCAN on two public bearing fault datasets: the Case Western Reserve University (CWRU) and the Society for Machinery Failure Prevention Technology (MFPT). The proposed model achieves 99.86% accuracy on the four-class CWRU dataset through five-fold cross-validation and 99.88% accuracy with a conventional 70:30 train–test random split. For the more challenging ten-class classification task on the same dataset, it achieves 97.80% accuracy under five-fold cross-validation. Furthermore, SpikeCAN attains a state-of-the-art accuracy of 96.31% on the fifteen-class MFPT dataset, surpassing existing benchmarks. These findings underscore a significant advancement in fault diagnosis technology, demonstrating the considerable practical potential of spike-driven neural networks in real-time, energy-efficient industrial diagnostic applications. Full article