Search Results (526)

This paper proposes a deep learning-based anomaly detection method using time-series vibration and current data, which were obtained from endurance tests on driving modules applied in industrial robots and machine systems. Unlike traditional classification models that depend on labeled fault data for detection, acquiring sufficient fault data in real industrial environments is highly challenging due to various conditions and constraints. To address this issue, we employ a semi-supervised learning approach that relies solely on normal data to effectively detect abnormal patterns, overcoming the limitations of conventional methods. The performance of semi-supervised models was first validated using a statistical feature-based anomaly detection approach, from which the GCN-VAE model was adopted. By combining the spatial feature extraction capability of Graph Convolutional Networks (GCNs) with the latent temporal feature modeling of Variational Autoencoders (VAEs), our method can effectively detect abnormal signs in the data, particularly in the lead-up to system failures. The experimental results confirmed that the proposed GCN-VAE model outperformed existing hybrid deep learning models in terms of anomaly detection performance in the pre-failure section. Full article

This paper presents an original approach to error correction in real-time systems. The proposed solution is based on the original multitasking system architecture, which was recently analyzed for energy. The authors have added a structure to correct random errors and distortions at the signal level, increasing reliability. The authors overview their original multitasking, time-predictable, multi-core system. The system has a regular structure with pipelined processing. The threads in each core are interleaved, eliminating the need for complex hazard control mechanisms. Previous works presented issues related to designing a predictable system and scheduling hardware threads with different design goals. The proposed fault detection method is based on scalable redundancy. Replicated processing units correct erroneous register file contents. The replication level can be adapted to current requirements. A mechanism for checking unused registers with “cycle stealing” is proposed with minimal impact on processing continuity. This paper presents the proposed hardware solution implemented in an FPGA device. Experiments using randomly generated errors showed that an additional structure can correct hardware errors. Furthermore, it was shown that the applied solution has a minimal impact on the system performance due to the use of thread interleaving and an error-checking and correction mechanism. Full article

This paper presents an advanced automatic fault classification method for detecting rotating rectifier faults in brushless synchronous machines (BSMs). The proposed approach employs a multilayer perceptron (MLP) neural network to classify the operational states of the rotating rectifier, including healthy conditions and common fault types: open-diode (OD), shorted-diode (SD), and open-phase (OP). Key machine measurements, available on an ordinary basis in the industry, such as active power (P), reactive power (Q), stator voltage (U), and excitation current (I_e), are used as inputs for this model, allowing for non-invasive, real-time fault detection. This model achieved an overall classification accuracy of 93.4%, with a precision of 94.9% for fault detection and strong recall performance across multiple fault types. The neural network’s robustness is enhanced by advanced data processing techniques, including Gaussian filtering and class balancing through the synthetic minority over-sampling technique (SMOTE). Experimental testing on a modified 5-kVA BSM setup, where rectifier faults were systematically induced, was used to train the network and validate the model’s performance. This method provides a promising tool for real-time condition monitoring of BSMs, improving machine reliability and minimizing downtime in industrial applications. Full article

Bearings are vital components in machinery, and their malfunction can result in equipment damage and reduced productivity. As a result, considerable research attention has been directed toward the early detection of bearing faults. With recent rapid advancements in machine learning algorithms, there is increasing interest in proactively diagnosing bearing faults by analyzing signals obtained from bearings. Although numerous studies have introduced machine learning methods for bearing fault diagnosis, the high costs associated with sensors and data acquisition devices limit their practical application in industrial environments. Additionally, research aimed at identifying the root causes of faults through diagnostic algorithms has progressed relatively slowly. This study proposes a cost-effective monitoring system to improve economic feasibility. Its primary benefits include significant cost savings compared to traditional high-priced equipment, along with versatility and ease of installation, enabling straightforward attachment and removal. The system collects data by measuring the vibrations of both normal and faulty bearings under various operating conditions on a test bed. Using these data, a deep neural network is trained to enable real-time feature extraction and classification of bearing conditions. Furthermore, an explainable AI technique is applied to extract key feature values identified by the fault classification algorithm, providing a method to support the analysis of fault causes. Full article

Early fault detection plays a crucial role in the field of predictive maintenance for wind turbines, yet the comparison of different algorithms poses a difficult task because domain-specific public datasets are scarce. Many comparisons of different approaches either use benchmarks composed of data from many different domains, inaccessible data, or one of the few publicly available datasets that lack detailed information about the faults. Moreover, many publications highlight a couple of case studies where fault detection was successful. With this paper, we publish a high quality dataset that contains data from 36 wind turbines across 3 different wind farms as well as the most detailed fault information of any public wind turbine dataset as far as we know. The new dataset contains 89 years worth of real-world operating data of wind turbines, distributed across 44 labeled time frames for anomalies that led up to faults, as well as 51 time series representing normal behavior. Additionally, the quality of training data is ensured by turbine-status-based labels for each data point. Furthermore, we propose a new scoring method, called CARE (Coverage, Accuracy, Reliability and Earliness), which takes advantage of the information depth that is present in the dataset to identify good early fault detection models for wind turbines. This score considers the anomaly detection performance, the ability to recognize normal behavior properly, and the capability to raise as few false alarms as possible while simultaneously detecting anomalies early. Full article

A method is proposed for fault classification in milling machines using advanced image processing and machine learning. First, raw data are obtained from real-world industries, representing various fault types (tool, bearing, and gear faults) and normal conditions. These data are converted into two-dimensional continuous wavelet transform (CWT) images for superior time-frequency localization. The images are then augmented to increase dataset diversity using techniques such as rotating, scaling, and flipping. A contrast enhancement filter is applied to highlight key features, thereby improving the model’s learning and fault detection capability. The enhanced images are fed into a modified AlexNet model with three residual blocks to efficiently extract both spatial and temporal features from the CWT images. The modified AlexNet architecture is particularly well-suited to identifying complex patterns associated with different fault types. The deep features are optimized using ant colony optimization to reduce dimensionality while preserving relevant information, ensuring effective feature representation. These optimized features are then classified using a support vector machine, effectively distinguishing between fault types and normal conditions with high accuracy. The proposed method provides significant improvements in fault classification while outperforming state-of-the-art methods. It is thus a promising solution for industrial fault diagnosis and has potential for broader applications in predictive maintenance. Full article

Grounding faults are a common type of fault in train auxiliary power supply systems (APS). Timely identification and localization of these faults are crucial for ensuring the stable operation of electric locomotives and the safety of passengers. Therefore, this paper proposes a fault diagnosis method for grounding faults (GFs) that integrates mechanistic insights with data-driven feature extraction. Firstly, this paper analyzes the mechanisms of grounding faults and summarizes the characteristics of their time–frequency distribution. Then, a Short-Time Fourier Transform (STFT) is employed to derive a frequency signature vector enabling classification into three principal categories. Concurrently, a time series sliding window approach is applied to extract time domain indicators for further subdivision of fault types. Finally, a time–frequency hybrid-driven diagnostic model framework is constructed by integrating the frequency distribution with the spatiotemporal map, and validation is conducted using an experimental platform that replicates system fault scenarios with a hardware-in-the-loop (HIL) simulation and executes the real-time diagnostic frameworks on a DSP diagnostic board card. The results demonstrate that the proposed method can detect and accurately locate grounding faults in real time. Full article

Accurate monitoring of complex industrial plants is crucial for ensuring safe operations and reliable management of desired quality. Early detection of abnormal events is essential to preempt serious consequences, enhance system performance, and reduce manufacturing costs. In this work, we propose a novel methodology for fault detection based on Slow Feature Analysis (SFA) tailored for time series models and statistical process control. Fault detection is critical in process monitoring and can ensure that systems operate efficiently and safely. This study investigates the effectiveness of various multivariate statistical methods, including Slow Feature Analysis (SFA), Kernel Slow Feature Analysis (KSFA), Dynamic Slow Feature Analysis (DSFA), and Principal Component Analysis (PCA) in detecting faults within the Tennessee Eastman (TE), Benchmark Simulation Model No. 1 (BSM 1) datasets and Beijing wastewater treatment plant (real world). Our comprehensive analysis indicates that KSFA and DSFA significantly outperform traditional methods by providing enhanced sensitivity and fault detection capabilities, particularly in complex, nonlinear, and dynamic data environments. The comparative analysis underscores the superior performance of KSFA and DSFA in capturing comprehensive process behavior, making them robust, cutting-edge choices for advanced fault detection applications. Such methodologies promise substantial improvements in industrial plant monitoring, contributing to heightened system reliability, safety, and overall operational efficiency. Full article

A global navigation satellite system (GNSS) for remotely piloted aircraft systems (RPASs) positioning is essential, thanks to the worldwide availability and continuity of this technology in the provision of positioning services. This makes the GNSS technology a critical element as malfunctions impacting on the determination of the position, velocity and timing (PVT) solution could determine safety issues. Such an aspect is particularly challenging in urban air mobility (UAM) scenarios, where low satellite visibility, multipath, radio frequency interference and cyber threats can dangerously affect the PVT solution. So, to meet integrity requirements, GNSS receiver measurements are augmented/fused with other aircraft sensors that can supply position and/or velocity information on the aircraft without relying on any other satellite and/or ground infrastructures. In this framework, in this paper, the algorithms of a hybrid navigation unit (HNU) for UAM applications are detailed, implementing a tightly coupled sensor fusion between a dual-frequency multi-constellation GNSS receiver, an inertial measurements unit and the barometric altitude from an air data computer. The implemented navigation algorithm is integrated with autonomous fault detection and exclusion of GPS/Galileo/BeiDou satellites and the estimation of navigation solution integrity/accuracy (i.e., protection level and figures of merit). In-flight tests were performed to validate the HNU functionalities demonstrating its effectiveness in UAM scenarios even in the presence of cyber threats. In detail, the navigation solution, compared with a real-time kinematic GPS receiver used as the reference centimetre-level position sensor, demonstrated good accuracy, with position errors below 15 m horizontally and 10 m vertically under nominal conditions (i.e., urban scenarios characterized by satellite low visibility and multipath). It continued to provide a valid navigation solution even in the presence of off-nominal events, such as spoofing attacks. The cyber threats were correctly detected and excluded by the system through the indication of the valid/not valid satellite measurements. However, the results indicate a need for fine-tuning the EKF to improve the estimation of figures of merit and protection levels associated to the navigation solution during the cyber-attacks. In contrast, solution accuracy and integrity indicators are well estimated in nominal conditions. Full article

Machine learning (ML) techniques have permeated various domains, offering intelligent solutions to complex problems. ML has been increasingly explored for applications in active power filters (APFs) due to its potential to enhance harmonic compensation, reference signal generation, filter control optimization, and fault detection and diagnosis. This paper reviews the most recent applications of ML in APFs, highlighting their abilities to adapt to nonlinear load conditions, improve fault detection and classification accuracy, and optimize system performance in real time. However, this paper also highlights several limitations of these methods, such as the high computational complexity, the need for extensive training data, and challenges with real-time deployment in distributed power systems. For example, the marginal improvements in total harmonic distortion (THD) achieved by ML-based methods often do not justify the increased computational overhead compared to traditional control methods. This review then suggests future research directions to overcome these limitations, including lightweight ML models for faster and more efficient control, federated learning for decentralized optimization, and digital twins for real-time system monitoring. While traditional methods remain effective, ML-based solutions have the potential to significantly enhance APF performance in future power systems. Full article

Regular on-site inspection is crucial for promptly detecting faults in water supply networks (WSNs) and auxiliary facilities, significantly reducing leakage risks. However, the fragmentation of information and the separation between virtual and physical networks pose challenges, increasing the cognitive load on inspectors. Furthermore, due to the lack of real-time computation in current research, the effectiveness in detecting anomalies, such as leaks, is limited, hindering its ability to provide immediate and direct-decision support for inspectors. To address these issues, this research proposes a mixed reality (MR) inspection method that integrates multi-source information, combining building information modeling (BIM), Internet of Things (IoT), monitoring data, and numerical simulation technologies. This approach aims to achieve in situ visualization and real-time computational capabilities. The effectiveness of the proposed method is demonstrated through case studies, with user feedback confirming its feasibility. The results indicate improvements in inspection task performance, work efficiency, and standardization compared to traditional mobile terminal-based methods. Full article

One of the main goals of the International Energy Agency (IEA) is to manage and utilize clean energy to achieve net zero emissions by 2050. Hydropower plants can significantly contribute to this goal as they are vital components of the global energy infrastructure, providing a clean, safe, and sustainable power source. Accordingly, there is great interest in developing methods to prevent errors and anomalies and ensure full operational availability. With modern hydropower plants equipped with sensors that capture extensive data, machine learning algorithms utilizing these data to detect and predict anomalies have gained research attention. This paper demonstrates that deep learning algorithms are particularly powerful in predicting time series. Three well-known deep learning networks are examined and compared to previous approaches, followed by the introduction of a new, innovative hybrid network. Using real-world data from two hydropower plants, the hybrid model outperforms individual deep learning models by achieving more accurate fault detection, reducing false positives, offering early fault prediction, and identifying faults several weeks before occurrence. These results showcase the hybrid network’s potential to enhance maintenance planning, reduce downtime, and improve operational efficiency in energy systems. Full article

Compressed air ranks among the most expensive forms of energy. In recent decades, increased efforts have been made to enhance the overall energy efficiency of pneumatic actuator systems and develop reliable fault detection methods for preventing energy losses. However, most of the methods developed so far require additional sensors, resulting in extra costs, and/or are not applicable during machine operation, which leads to their limited use in the industry. This article introduces a cycle time-based method for detecting faults in pneumatic actuators through the use of proximity switches, enabling cost-effective monitoring in real time without the necessity of further sensors. A systematic analysis is conducted, expanding the current state of knowledge by detailing the influence of all potential leakage points on the movement times of a pneumatic drive and taking into account the different velocity control strategies (meter-out and meter-in) and operating points expressed via the pneumatic frequency ratio. Previously unassessed specifics of internal leakage, including the impact of pressure profiles and differences between differential cylinders and cylinder with equal piston areas, are also presented. The applicability of the proposed method and its detection limits in an industrial environment are examined using pneumatic assembly machines. Full article

Many industrial processes, from manufacturing to food processing, incorporate rotating elements as principal components in their production chain. Failure of these components often leads to costly downtime and potential safety risks, further emphasizing the importance of monitoring their health state. Vibration signal analysis is now a common approach for this purpose, as it provides useful information related to the dynamic behavior of machines. This research aimed to conduct a comprehensive examination of the current methodologies employed in the stages of vibration signal analysis, which encompass preprocessing, processing, and post-processing phases, ultimately leading to the application of Artificial Intelligence-based diagnostics and prognostics. An extensive search was conducted in various databases, including ScienceDirect, IEEE, MDPI, Springer, and Google Scholar, from 2020 to early 2024 following the PRISMA guidelines. Articles that aligned with at least one of the targeted topics cited above and provided unique methods and explicit results qualified for retention, while those that were redundant or did not meet the established inclusion criteria were excluded. Subsequently, 270 articles were selected from an initial pool of 338. The review results highlighted several deficiencies in the preprocessing step and the experimental validation, with implementation rates of 15.41% and 10.15%, respectively, in the selected prototype studies. Examination of the processing phase revealed that time scale decomposition methods have become essential for accurate analysis of vibration signals, as they facilitate the extraction of complex information that remains obscured in the original, undecomposed signals. Combining such methods with time–frequency analysis methods was shown to be an ideal combination for information extraction. In the context of fault detection, support vector machines (SVMs), convolutional neural networks (CNNs), Long Short-Term Memory (LSTM) networks, k-nearest neighbors (KNN), and random forests have been identified as the five most frequently employed algorithms. Meanwhile, transformer-based models are emerging as a promising venue for the prediction of RUL values, along with data transformation. Given the conclusions drawn, future researchers are urged to investigate the interpretability and integration of the diagnosis and prognosis models developed with the aim of applying them in real-time industrial contexts. Furthermore, there is a need for experimental studies to disclose the preprocessing details for datasets and the operational conditions of the machinery, thereby improving the data reproducibility. Another area that warrants further investigation is differentiation of the various types of fault information present in vibration signals obtained from bearings, as the defect information from the overall system is embedded within these signals. Full article

Detecting faulty pipelines in water management systems is crucial for ensuring a reliable supply of clean water. Traditional inspection methods are often time-consuming, costly, and prone to errors. This study introduces an AI-based model utilizing images to detect pipeline defects, focusing on leaks, cracks, and corrosion. The YOLOv8 model is employed for object detection due to its exceptional performance in detecting objects, segmentation, pose estimation, tracking, and classification. By training on a large dataset of labeled images, the model effectively learns to identify visual patterns associated with pipeline faults. Experiments conducted on a real-world dataset demonstrate that the AI-based model significantly outperforms traditional methods in detection accuracy. The model also exhibits robustness to various environmental conditions such as lighting changes, camera angles, and occlusions, ensuring reliable performance in diverse scenarios. The efficient processing time of the model enables real-time fault detection in large-scale water distribution networks implementing this AI-based model offers numerous advantages for water management systems. It reduces dependence on manual inspections, thereby saving costs and enhancing operational efficiency. Additionally, the model facilitates proactive maintenance through the early detection of faults, preventing water loss, contamination, and infrastructure damage. The results from the three conducted experiments indicate that the model from Experiment 1 achieves a commendable mAP50 of 90% in detecting faulty pipes, with an overall mAP50 of 74.7%. In contrast, the model from Experiment 3 exhibits superior overall performance, achieving a mAP50 of 76.1%. This research presents a promising approach to improving the reliability and sustainability of water management systems through AI-based fault detection using image analysis. Full article