Search Results (1,381)

High-frequency vibrations in annular gap type pressure-regulating valves of wind tunnels can induce fatigue, fracture, and operational failures, posing challenges to safe and reliable operation. This study proposes a hybrid leakage fault diagnosis framework that integrates wavelet packet-based signal analysis with advanced deep learning techniques. Time-domain acceleration signals collected from multiple sensors are processed to extract maximum component energy and its variation rate, identified as sensitive and robust indicators for leakage detection. A fluid–solid coupled finite element model of the valve system further validates the reliability of these indicators under different operational scenarios. Based on this foundation, a Vision Transformer (ViT)-based model is trained on a dedicated database encompassing multiple leakage conditions and sensor arrangements. Comparative evaluation demonstrates that the ViT model outperforms conventional deep learning architectures in terms of accuracy, stability, and predictive reliability. The integrated framework enables fast, automated, and robust leakage diagnosis, providing a comprehensive solution to enhance the monitoring, maintenance, and operational safety of wind tunnel valve systems. Full article

Induction motors (IMs) are crucial in many industrial applications, offering a cost-effective and reliable source of power transmission and generation. However, their continuous operation imposes considerable stress on electrical and mechanical parts, leading to progressive wear that can cause unexpected system shutdowns. Bearings, which enable shaft motion and reduce friction under varying loads, are the most failure-prone components, with bearing ball defects representing most severe mechanical failures. Early and accurate fault diagnosis is therefore essential to prevent damage and ensure operational continuity. Recent advances in the Internet of Things (IoT) and machine learning (ML) have enabled timely and effective predictive maintenance strategies. Among various diagnostic parameters, vibration analysis has proven particularly effective for detecting bearing faults. This study proposes a hybrid diagnostic framework for induction motor bearings, combining vibration signal analysis with Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs) in an IoT-enabled Industry 4.0 architecture. Statistical and frequency-domain features were extracted, reduced using Principal Component Analysis (PCA), and classified with SVMs and ANNs, achieving over 95% accuracy. The novelty of this work lies in the hybrid integration of interpretable and non-linear ML models within an IoT-based edge–cloud framework. Its main contribution is a scalable and accurate real-time predictive maintenance solution, ensuring high diagnostic reliability and seamless integration in Industry 4.0 environments. Full article

Early and accurate detection of distributed bearing faults is essential to prevent equipment failures and reduce downtime in industrial environments. This study explores the optimal selection of input signal sources for high-accuracy distributed fault classification, employing wavelet transform and machine learning algorithms. The primary contribution of this work is to demonstrate that robust distributed bearing fault diagnosis can be achieved through optimal sensor fusion and wavelet-based feature engineering, without the need for deep learning or high-dimensional inputs. This approach provides interpretable, computationally efficient, and generalizable fault classification, setting it apart from most existing studies that rely on larger models or more extensive data. All experiments were conducted in a controlled laboratory environment across multiple loads and speeds. A comprehensive dataset, including three-axis vibration, stray magnetic flux, and two-phase current signals, was used to diagnose six distinct bearing fault conditions. The wavelet transform is applied to extract frequency-domain features, capturing intricate fault signatures. To identify the most effective input signal combinations, we systematically evaluated Random Forest, XGBoost, and Support Vector Machine (SVM) models. The analysis reveals that specific signal pairs significantly enhance classification accuracy. Notably, combining vibration signals with stray magnetic flux consistently achieved the highest performance across models, with Random Forest reaching perfect test accuracy (100%) and SVM showing robust results. These findings underscore the importance of optimal source selection and wavelet-transformed features for improving machine learning model performance in bearing fault classification tasks. While the results are promising, validation in real-world industrial settings is needed to fully assess the method’s practical reliability and impact on predictive maintenance systems. Full article

The increasing sophistication of grid-connected photovoltaic (GCPV) systems necessitates advanced fault detection and diagnosis (FDD) methods to ensure operation efficiency and security. In this paper, a novel two-stage hybrid AI architecture is analyzed that couples an autoencoder using Long Short-Term Memory (LSTM) for unsupervised anomaly detection with an RF classifier for focused fault diagnosis. The architecture is critically compared to that of a baseline-only RF baseline on a synthetic dataset. The results of this two-stage hybrid AI show a strong overall accuracy of (83.1%). The hybrid model’s first stage trains only on unlabeled healthy data, reducing the reliance on extensive and often unavailable labeled fault datasets. This design has the safety-critical advantage of marking unfamiliar faults as anomalies instead of committing to a misclassification. By integrating anomaly detection with classification, the architecture enables early stage screening of faults and targeted categorization, even in data-scarce scenarios. This offers a scalable, interpretable solution suitable for deployment in real-world GCPV systems where robustness and early detection are critical. While the method exhibits reduced sensitivity to subtle or recurring faults, it demonstrates strong reliability in confidently detecting distinct and significant anomalies. Additionally, the approach improves interpretability, facilitating clearer identification of performance constraints such as the autoencoder’s moderate fault sensitivity (AUC = 0.61). This study confirms the hybrid approach as a very promising FDD solution, in which the architectural advantages of safety and maintainability offer a more worthwhile proposition to real-world systems than incremental improvements in a single accuracy measure. Full article

The growth of greenhouse gas emissions, driven by the use of internal combustion engines (ICE), highlights the urgent need for sustainable solutions, particularly in the shipping sector. Non-invasive predictive maintenance using acoustic signal analysis has emerged as a promising strategy for fault diagnosis in ICEs. In this context, the present study proposes a hybrid Deep Learning (DL) model and provides a novel publicly available dataset containing real operational sound samples of ICEs, labeled across 12 distinct fault subclasses. The methodology encompassed dataset construction, signal preprocessing using log-mel spectrograms, and the evaluation of several Machine Learning (ML) and DL models. Among the evaluated architectures, the proposed hybrid model, BiGRUT (Bidirectional GRU + Transformer), achieved the best performance, with an accuracy of 97.3%. This architecture leverages the multi-attention capability of Transformers and the sequential memory strength of GRUs, enhancing robustness in complex fault scenarios such as combined and mechanical anomalies. The results demonstrate the superiority of DL models over traditional ML approaches in acoustic-based ICE fault detection. Furthermore, the dataset and hybrid model introduced in this study contribute toward the development of scalable real-time diagnostic systems for sustainable and intelligent maintenance in transportation systems. Full article

Gears are the core components of transmission systems, and their health status is critical to the safety and stability of the entire system. In order to efficiently identify the typical fault types such as missing teeth and broken teeth in gears, this paper collects a rich sample under complex backgrounds from different shooting angles and lighting conditions. Then a hierarchical approach is used to describe gear faults on the image. The gear samples are first segmented for image extraction and then finely labeled for gear fault regions. In addition, imbalanced datasets are produced to simulate the environment with fewer fault samples in the actual industrial process. Finally, a semi-supervised learning framework is trained based on the above method and applied in actual environment. The experimental results show that the model performs well in gear target detection and fault diagnosis, demonstrating the effectiveness of the proposed method. Full article

The detection and extraction of weak signals are crucial in various engineering and scientific fields, yet current acoustic sensing technologies are restricted by fundamental pressure detection methods. This paper proposes gradient-equivalent medium-coupled metamaterials (GEMCMs) utilizing strong wave compression and an equivalent medium mechanism to capture weak signals in complex environments and enhance target acoustic signals. Overcoming shape and impedance mismatch limitations of traditional gradient structures, GEMCMs significantly improve control performance. Experimental and numerical simulations indicate that GEMCMs can effectively enhance specific frequency components in acoustic signals, outperforming traditional gradient structures. This enhancement of specific frequency components relies on the resonance effect of the unit cell structure. By introducing acoustic resonance within a spatially wound acoustic channel, a significant amplification of weak acoustic signals is achieved. This provides a new research direction for acoustic wave manipulation and enhancement, and holds significant importance in fields such as mechanical fault diagnosis and medical diagnostics. Full article

Wind turbines face significant operational challenges due to their complex electromechanical systems, exposure to harsh environmental conditions, and high maintenance costs. Reliable structural health monitoring and condition monitoring are therefore essential for early fault detection, minimizing downtime, and optimizing maintenance strategies. Traditional approaches typically rely on either Trend Monitoring (TM) or Change Point Detection (CPD). TM methods track the long-term behaviour of process parameters, using statistical analysis or machine learning (ML) to identify abnormal patterns that may indicate emerging faults. In contrast, CPD techniques focus on detecting abrupt changes in time-series data, identifying shifts in mean, variance, or distribution, and providing accurate fault onset detection. While each approach has strengths, they also face limitations: TM effectively identifies fault type but lacks precision in timing, while CPD excels at locating fault occurrence but lacks detailed fault classification. This review critically examines the integration of TM and CPD methods for wind turbine diagnostics, highlighting their complementary strengths and weaknesses through an analysis of widely used TM techniques (e.g., Fast Fourier Transform, Wavelet Transform, Hilbert–Huang Transform, Empirical Mode Decomposition) and CPD methods (e.g., Bayesian Online Change Point Detection, Kullback–Leibler Divergence, Cumulative Sum). By combining both approaches, diagnostic accuracy can be enhanced, leveraging TM’s detailed fault characterization with CPD’s precise fault timing. The effectiveness of this synthesis is demonstrated in a case study on wind turbine blade fault diagnosis. Results shows that TM–CPD integration enhances early detection through coupling vibration and frequency trend analysis with robust statistical validation of fault onset. Full article

This paper addresses the challenges of fault diagnosis in gas turbines (GTs) utilized in oil and gas pipeline systems by proposing a novel multiparameter analysis framework that integrates dynamic, quantile-based Statistical Process Control (SPC) with prior domain knowledge. The proposed approach initially employs a dynamic quantile SPC model to establish adaptive control limits, effectively handling the non-stationarity and non-normality of gas turbine operational data. By analyzing parameter variations under typical operating conditions and incorporating expert insights, a multiparameter fault analysis matrix and corresponding weighting factors are constructed to facilitate fault diagnosis with prior knowledge. Furthermore, a fault probability model based on parameter change rates and weighting factors is developed to quantify the likelihood of different fault modes. An operating condition clustering and correction mechanism enables the dynamic adjustment of control limits, thereby preventing misdiagnoses caused by varying operational states. The validity of the proposed method is demonstrated using real data from a domestic pipeline gas turbine, validated by real domestic pipeline GT data, outperforming existing models, with a fault accuracy up to 10%. The approach efficiently estimates fault probabilities and accurately detects both sudden and gradual faults, significantly enhancing intelligent fault diagnosis capabilities for gas turbines. Full article

With the development of the Industrial Internet of Things (IIoT) technology, fault diagnosis has emerged as a critical component of its operational reliability, and machine learning algorithms play a crucial role in fault diagnosis. To achieve better fault diagnosis results, it is necessary to have a sufficient number of fault samples participating in the training of the model. In actual industrial scenarios, it is often difficult to obtain fault samples, and there may even be situations where no fault samples exist. For scenarios without fault samples, accurately identifying the unknown faults of equipment is an issue that requires focused attention. This paper presents a method for the normal-sample-based mechanical equipment unknown fault detection. By leveraging the characteristics of the autoencoder network (AE) in deep learning for feature extraction and sample reconstruction, normal samples are used to train the AE network. Whether the input sample is abnormal is determined via the reconstruction error and a threshold value, achieving the goal of anomaly detection without relying on fault samples. In terms of input data, the frequency domain features of normal samples are used to train the AE network, which improves the training stability of the AE network model, reduces the network parameters, and saves the occupied memory space at the same time. Moreover, this paper further improves the network based on the traditional AE network by incorporating a convolutional neural network (CNN) and a long short-term memory network (LSTM). This enhances the ability of the AE network to extract the spatial and temporal features of the input data, further improving the network’s ability to extract and recognize abnormal features. In the simulation part, through public datasets collected in factories, the advantages and practicality of this method compared with other algorithms in the detection of unknown faults are fully verified. Full article

To tackle the difficulties in cross-domain fault diagnosis for rolling bearings, researchers have devised numerous domain adaptation strategies to align feature distributions across varied domains. Nevertheless, current approaches tend to be vulnerable to noise disruptions and often neglect the distinctions between marginal and conditional distributions during feature transfer. To resolve these shortcomings, this study presents an innovative fault diagnosis technique for cross-domain applications, leveraging the Attention-Enhanced Residual Network (AttenResNet18). This approach utilizes a one-dimensional attention mechanism to dynamically assign importance to each position within the input sequence, thereby capturing long-range dependencies and essential features, which reduces vulnerability to noise and enhances feature representation. Furthermore, we propose a Dynamic Balance Distribution Adaptation (DBDA) mechanism, which develops an MMD-CORAL Fusion Metric (MCFM) by combining CORrelation ALignment (CORAL) with Maximum Mean Discrepancy (MMD). Moreover, an adaptive factor is employed to dynamically regulate the balance between marginal and conditional distributions, improving adaptability to new and untested tasks. Experimental validation demonstrates that AttenResNet18 achieves an average accuracy of 99.89% on two rolling bearing datasets, representing a significant improvement in fault detection precision over existing methods. Full article

Insulation degradation in photovoltaic (PV) cables can cause electrical faults and fire hazards, thereby compromising system reliability and safety. Early detection of precursor signals is crucial for preventive maintenance. However, conventional diagnostic techniques are limited to static assessments and fail to capture early-stage electrical anomalies in real-time. This study investigates the time-series behavior of voltage, current, and temperature in PV cables under thermal stress conditions. Experiments were conducted using TFR-CV cables installed in a vertically stacked and tight-contact configuration. A gas torch was applied for localized heating to induce insulation degradation. A grid-connected testbed with six series-connected PV modules was constructed. Each module was instrumented with PV-M sensors, temperature sensors, and an infrared camera. Data were acquired at 1 Hz intervals. Results showed that cable surface temperature exceeded 280 °C during degradation. The output voltage exhibited transient surges of up to +13.3% and drops of −68%, while the output current decreased by over 20%, particularly in the PV-M3 module. These anomalies, such as thermal imbalance, voltage spikes/dips, and current drops, were closely associated with critical degradation points and are interpreted as precursor signals. This work confirms the feasibility of identifying fire-related precursors through real-time monitoring of PV cable electrical characteristics. The observed correlation between electrical responses and thermal expansion behaviors suggests a strong link to the stages of insulation degradation. Future work will focus on quantifying the relationship between degradation and electrical behavior under controlled environmental conditions. Full article

The On-Load Tap Changer (OLTC), as a critical component of transformers, undergoes frequent switching operations that can lead to faults such as contact wear and arc discharge, which are often difficult to detect at an early stage using traditional monitoring methods. In particular, dissolved gas analysis (DGA) in OLTC oil is challenged by the unique oil gas decomposition mechanisms and the presence of background noise, making conventional DGA criteria less effective. Moreover, OLTC oil monitoring data are typically obtained through intermittent sampling, resulting in sparse time series with low resolution that complicate fault prediction. To address these challenges, this paper proposes an integrated framework combining LGOD-based anomaly detection, Locally Weighted Regression (LWR) for data repair, and the ETSformer temporal prediction model. This approach effectively identifies and corrects anomalies, restores the dynamic variation trends of gas concentrations, and enhances prediction accuracy through deep temporal modeling, thereby providing more reliable data support for OLTC state assessment and fault diagnosis. Experimental results demonstrate that the proposed method significantly improves prediction accuracy, enhances sensitivity to gas concentration evolution, and exhibits robust adaptability under both normal and fault scenarios. Furthermore, ablation experiments confirm that the observed performance gains are attributable to the complementary contributions of LGOD, LWR, and ETSformer, rather than any single component alone, highlighting the effectiveness of the integrated approach. Full article

Induction motors (IMs) are the backbone of modern industry. Despite their robustness and reliability, they are prone to a range of problems that can result in periods of inactivity, diminished operational efficiency, and potential safety risks. Rapid identification and assessment of faults is important to maintain efficient motors operation and avoid serious malfunctions. The paper offers a comprehensive analysis of the existing body of knowledge in IMs’ faults detection, highlighting areas of deficiency and obstacles. Our review is built according to the IMs diagnosis process, presenting for each step of this process several approaches. Finally, we discuss the effectiveness of each fault classification approach in addressing data-driven challenges such as high-dimensionality, class imbalance, nonlinearity, noise, and overfitting. This paper highlights the rising transition to data-driven strategies, with deep learning increasingly taking center stage in tackling the complex challenges of fault diagnosis. It underscores the significant impact of these advancements on the field, actively facilitating future research into intelligent, real-time condition monitoring systems. Full article

It is well known that power converters have the highest failure rate in the energy conversion chain in different industrial applications. This could definitely affect the reliability of the system. The reliability of converters in power conversion systems is crucial, as failures can lead to critical consequences and damage other system components. Therefore, it is important to predict and detect failures and take corrective actions to prevent them. One of the most common types of failure in power converters is semiconductor failure, which can manifest as an open circuit or a short circuit. This paper focuses on single and double open-circuit switch failures in a 5-level cascaded H-bridge inverter, for which a fast, precise method is required. A data-driven approach is employed here, using the output voltage and voltages across each H-bridge as diagnostic signals. A 1D-CNN LSTM neural network is trained to accurately detect and localize open-circuit faults, providing a reliable, practical solution. Full article