Electrical Faults Research Articles

Spark: A Statistical Comparison and Evaluation of Classification Algorithms for Fault Prediction in Electrical Secondary Distribution Network

Managing faults in the electrical secondary distribution network is a challenging task given the nature, size, and complexity. Predicting faults early before they occur helps in increasing the safety and reliability of the power distribution system. Various statistical and machine learning techniques are being used to predict different types of faults. This study applies classification algorithms available in the big data framework Apache Spark through its python interface PySpark to predict electrical secondary distribution network faults. The study evaluates and compares nine algorithms: Decision tree, Gradient-boosted tree, Logistic regression, Naïve Bayes, Multilayer perceptron, Random forest, Linear Support Vector Machine, One-versus-rest and Factorization machines. The research uses Friedman’s test followed by the Nemenyi post hoc test to find the significance of performance differences among the algorithms. The results show significant differences among the algorithms. Gradient-boosted tree and One-versus-rest with Gradient-boosted tree had the best performance for binary and multiclass classification, respectively, while Naïve Bayes had the worst performance.

Integration of drone and machine learning technology for predicting power infrastructure faults efficiently

Power transmission and distribution networks frequently face issues, especially in harsh environments, leading to high maintenance costs and the need for uninterrupted electricity. Current field inspections by skilled personnel are labor-intensive, costly, and slow, often lacking efficiency and posing safety risks. While automated helicopters, flying robots, and climbing robots have been explored for visual inspections, the widespread adoption of automatic vision-based inspection remains limited due to high accuracy demands and unique challenges. This highlights the need for a fully autonomous vision-based system to inspect electrical power infrastructure and predict potential future faults. This research introduces Unmanned Aerial Vehicles (UAVs) as a promising solution for infrastructure inspection, deep learning for data analysis and prediction, and a mathematical model to ensure system accuracy doesn't rely solely on the dataset. As a proof of concept, YOLO V8 was employed to predict electrical faults in insulators, achieving a box loss of 0.525, a classification loss of 0.3887, and a precision of 0.8976, demonstrating high accuracy and low loss.

Resilience enhancement for interdependent power systems by AI-assisted disaster response

The failure of urban Electrical Distribution Systems (EDSs) can lead to direct or indirect consequences for their interdependent critical infrastructures, for example, the hospitals, the fire department, etc., negatively affecting the well-being of citizens in the city. To improve the resilience of the coupled power network, the Operational Interdependence Simulator (OIS) is proposed to help prioritize the queue of failure recovery and Minimum Spanning Tree and Shortest Path Tree topology reconfiguration to minimize critical load downtime. Additionally, AI agents are introduced to assist decision-making processes. By utilizing machine learning and training in thousands of offline scenarios, the system can be used for real-time calculation of the optimal recovery paths when given the number and location of electrical faults. The IEEE 70-node distribution system case validated the high prediction accuracy and post-disaster topology reconfiguration while considering the interdependencies.

Simulation Environment for the Testing of Electrical Arc Fault Detection Algorithms

Simulation Environment for the Testing of Electrical Arc Fault Detection Algorithms

Smart Building, Nuisance Electrical Failure, Remote Monitoring and Fault Recovery System

Smart Buildings are the fastest growing buildings compared to conventional buildings and are expected to grow at a rate of 8.3% for the next decay. The global commercial building automation market was valued at US$32.96 billion in 2020 and is expected to reach US76.49 billion by the year 2031. The implementation of technological advancement, demand for energy-efficient construction, low operational cost, and occupant comfortability have helped Smart Building to grow. However, Smart Buildings are still facing issues, from various sensor network diversity, clear definitions of Smart Buildings, and continuous smartness during full or partial electrical internal fault occurrence. This indicates the building is smart as long as a continuous power supply is present. Thus, this research study investigated Smart Building's drawbacks and designed a circuit to be a solution to one of the drawbacks to rectify the issues. The design provides full monitoring for real and nuisance failures and enables the performance of fault recovery procedures remotely. The circuit interfaces with the safety Residual Current Devices (RCD) and the wireless smart Wi-Fi-controlled socket outlets. Food industries, hotels, and restaurants could be the beneficiaries of this circuit. This is due to cold stores and fridges, which can lead to significant production loss/reduction when failure time increases.

Industrial Fault Detection Systems

This project presents an industrial fault detection system that monitors important electrical and environmental conditions to improve equipment reliability and safety. Using an ESP32 microcontroller, the system checks for issues like fuse and Miniature Circuit Breaker (MCB) status, as well as under and over-voltage situations with a ZMPT101B sensor. It also tracks temperature and humidity levels using a DHT11 sensor. The system displays real-time information on a 16x2 LCD and can be accessed via a web page, allowing operators to monitor conditions from anywhere. By quickly detecting electrical faults and environmental changes, this system helps reduce downtime and maintenance costs.

Motor Fault Diagnosis and Detection with Convolutional Autoencoder (CAE) Based on Analysis of Electrical Energy Data

This study develops a Convolutional Autoencoder (CAE) and deep neural network (DNN)-based model optimized for real-time signal processing and high accuracy in motor fault diagnosis. This model learns complex patterns from voltage and current data and precisely analyzes them in combination with DNN through latent space representation. Traditional diagnostic methods relied on vibration and current sensors, empirical knowledge, or harmonic and threshold-based monitoring, but they had limitations in recognizing complex patterns and providing accurate diagnoses. Our model significantly enhances the accuracy of power data analysis and fault diagnosis by mapping each phase (R, S, and T) of the electrical system to the red, green, and blue (RGB) channels of image processing and applying various signal processing techniques. Optimized for real-time data streaming, this model demonstrated high practicality and effectiveness in an actual industrial environment, achieving 99.9% accuracy, 99.8% recall, and 99.9% precision. Specifically, it was able to more accurately diagnose motor efficiency and fault risks by utilizing power system analysis indicators such as phase voltage, total harmonic distortion (THD), and voltage unbalance. This integrated approach significantly enhances the real-time applicability of electric motor fault diagnosis and is expected to provide a crucial foundation for various industrial applications in the future.

A Mechanical Fault Diagnosis Method for UCG-Type On-Load Tap Changers in Converter Transformers Based on Multi-Feature Fusion

The On-Load Tap Changer (OLTC) is the only movable mechanical component in a converter transformer. To ensure the reliable operation of the OLTC and to promptly detect mechanical faults in OLTCs to prevent them from developing into electrical faults, this paper proposes a fault diagnosis method for OLTCs based on a combination of Particle Swarm Optimization (PSO) algorithm and Least Squares Support Vector Machine (LSSVM) with multi-feature fusion. Firstly, a multi-feature extraction method based on time/frequency domain statistics, synchrosqueezed wavelet transform, singular value decomposition, and multi-scale modal decomposition is proposed. Meanwhile, the random forest algorithm is used to screen features to eliminate the influence of redundant features on the accuracy of fault diagnosis. Secondly, the PSO algorithm is introduced to optimize the hyperparameters of LSSVM to obtain optimal parameters, thereby constructing an optimal LSSVM fault diagnosis model. Finally, different types of feature combinations are utilized for fault diagnosis, and the impact of these feature combinations on the fault diagnosis results is compared. Experimental results indicate that features of different types can complement each other, making the OLTC state information carried by multi-dimensional features more comprehensive, which helps to improve the accuracy of fault diagnosis. Compared with four traditional fault diagnosis methods, the proposed method performs better in fault diagnosis accuracy, achieving the highest accuracy of 98.58%, which can help to detect mechanical faults in the OLTC early and reduce the system’s downtime.

Enhancing induction machine fault detection through machine learning: Time and frequency analysis of vibration signals

The integration of machine learning algorithms into fault diagnosis is regarded as an advanced and effective method for detecting electrical system faults. Vibration signals are identified as valuable and easily accessible data for fault identification in electrical machines. In this study, experiments were conducted to assemble a dataset consisting of 525 × 3 instances, each containing 200 three-axis vibration signal measurements. These measurements were obtained from a laboratory test bench equipped with a customized winding three-phase induction machine. Instead of directly analyzing the vibration signals, a feature extraction approach was employed, calculating a comprehensive set of statistical, harmonic, and impulsive features from the time domain (e.g., ShapeFactor, SINAD, ClearanceFactor, ImpulseFactor, CrestFactor, Kurtosis, Skewness, THD, Std, RMS, Mean, PeakValue, SNR), along with spectral features from the frequency domain (e.g., Peak Frequencies, Amplitudes, BandPower). To improve model efficiency, Analysis of Variance (ANOVA) was applied to select only the most significant features, with F-statistics used to rank feature importance. Features with higher F-statistics were prioritized for their ability to explain more variance in motor fault classification. This selective approach reduced model complexity, helping to minimize overfitting and focus on features that had a substantial impact on predictive accuracy. By concentrating on these high-impact features, a balance between simplicity and performance was achieved. These selected features were then used to train five machine learning classifiers: Ensemble (Bagged Trees), Quadratic Support Vector Machine, Weighted K-Nearest Neighbors, Efficient Logistic Regression, and Neural Networks. The performance of these classifiers was evaluated using various metrics, with validation accuracy rates ranging from 78.3% to 98.8%. A comparative study with similar works in the literature was conducted, demonstrating that high performances were obtained with the proposed approach while maintaining computational efficiency.

Diagnosis and Identification of Common Electrical Faults in PM Machine Drives

Diagnosis and Identification of Common Electrical Faults in PM Machine Drives

Electric Vehicle Motor Fault Detection with Improved Recurrent 1D Convolutional Neural Network

Electric Vehicle Motor Fault Detection with Improved Recurrent 1D Convolutional Neural Network

Epoxy Coating as a Novel Method to Prevent Avian Electrocutions and Electrical Faults on Distribution Pylons with Grounded Steel Crossarms

Electrical faults caused by power escaping electric systems can lead to power outages, equipment damage, and fires. Faults sometimes occur when birds perched on power structures are electrocuted. Distribution power lines supported by concrete and steel pylons are particularly fault-prone because small separations between conductors and grounded components allow even small birds to inadvertently create faults while being electrocuted. Most conservation solutions focus on covering energized wires and components to prevent contact by birds and, although usually effective when installed correctly, covers can sometimes be dislodged thus becoming ineffective. Glass Flake Epoxy (GFE) is a non-conductive thermoset plastic that can adhere to steel crossarms and not be dislodged. We hypothesized that GFE-coated crossarms might reduce faults (proxies for avian electrocutions), and we conducted laboratory and field trials to evaluate that hypothesis. In the laboratory, we found a 2000 micrometer (μm)-thick layer of GFE coating that created a dielectric strength of 12.30 ± 0.21 kV, which was sufficient to prevent the formation of a phase-to-ground fault on up to 20 kV distribution lines. This should allow birds to perch on metal crossarms without being electrocuted. In field trials, we substituted 24% of a 20 kV distribution pylon’s crossarms with GFE-treated crossarms and found that doing so correlated with a 28% decrease in faults. Although we did not measure avian electrocutions directly, our findings suggest GFE coatings may offer a novel method of reducing avian electrocutions on power lines.

Assessment of Envelope- and Machine Learning-Based Electrical Fault Type Detection Algorithms for Electrical Distribution Grids

This study introduces envelope- and machine learning (ML)-based electrical fault type detection algorithms for electrical distribution grids, advancing beyond traditional logic-based methods. The proposed detection model involves three stages: anomaly area detection, ML-based fault presence detection, and ML-based fault type detection. Initially, an envelope-based detector identifying the anomaly region was improved to handle noisier power grid signals from meters. The second stage acts as a switch, detecting the presence of a fault among four classes: normal, motor, switching, and fault. Finally, if a fault is detected, the third stage identifies specific fault types. This study explored various feature extraction methods and evaluated different ML algorithms to maximize prediction accuracy. The performance of the proposed algorithms is tested in an emulated software–hardware electrical grid testbed using different sample rate meters/relays, such as SEL735, SEL421, SEL734, SEL700GT, and SEL351S near and far from an inverter-based photovoltaic array farm. The performance outcomes demonstrate the proposed model’s robustness and accuracy under realistic conditions.

Failure mechanism and thermal runaway behavior of lithium-ion battery induced by arc faults

As the widespread of lithium-ion battery systems such as electric vehicles and energy storage systems, the number of safety incidents due to electrical faults are increasing. Many accident reports have demonstrated that arc faults have become one of the main triggers of LIB system accidents, however, the related studies are inadequate. In this study, an arc imitation system is employed to investigate the influence of different arc energies on battery safety valve, as well as the electrochemical characteristics of faulty batteries. The results show that the minimum arc power to breach the safety valve ranges from 110 to 441 W. The maximum temperature rise rate on the battery surface can exceed 15 °C/s with arc power of around 1000 W. Further, the testing of in-situ and ex-situ indicate the faulty batteries undergo degradation and failure due to that moisture in the air enters the battery interior, resulting in increased internal resistance, loss of active materials and cyclable lithium. Finally, the faulty battery has no valve opening during thermal runaway, and the ignition time is four hundred seconds earlier than that of the normal battery, indicating more severe fire dangers. The results are valuable for safety design of battery systems in relation to arc faults, as well as the characteristic for fault detection and early warning.

Research on Wind Turbine Fault Detection Based on CNN-LSTM

With the wide application of wind energy as a clean energy source, to cope with the challenge of increasing maintenance difficulty brought about by the development of large-scale wind power equipment, it is crucial to monitor the operating status of wind turbines in real time and accurately identify the specific location of faults. In this study, a CNN-LSTM-based wind motor fault detection model is constructed for four types of typical faults, namely gearbox faults, electrical faults, yaw faults, and pitch faults of wind motors, combining CNN’s advantages of excelling in feature extraction and LSTM’s advantages of dealing with long-time sequence data, to achieve the simultaneous detection of multiple fault types. The accuracy of the CNN-LSTM-based wind turbine fault detection model reaches 90.06%, and optimal results are achieved for the effective discovery of yaw system faults, pitch system faults, and gearbox faults, obtaining 94.09%, 96.46%, and 97.39%, respectively. The CNN-LSTM wind turbine fault detection model proposed in this study improves the fault detection effect, avoids the further deterioration of faults, provides direction for preventive maintenance, reduces downtime loss due to restorative maintenance, and is essential for the sustainable use of wind turbines and maintenance of wind turbine service life, which helps to improve the operation and maintenance level of wind farms.

Preface

On behalf of the organizing committee, we are very pleased to introduce the proceedings of 2024 The 17th International Conference on Computer and Electrical Engineering (ICCEE 2024), which was held in Shenzhen, China (virtual) on June 28-30, 2024. Because more than two-thirds of the authors chose to attend the conference online, we had to switch to totally virtual conference to ensure the effectiveness of the conference. It is with great pleasure and anticipation that we convene once again to explore the latest advancements, challenges, and opportunities in the dynamic fields of Computer and Electrical Engineering. In today’s interconnected world, computer and electrical engineering play critical roles in shaping the technological landscape. ICCEE 2024 serves as a platform for fostering interdisciplinary collaboration, knowledge sharing, and networking among researchers, practitioners, and industry leaders. ICCEE 2024 lasted 3 days. There are online test sessions on ZOOM on the first day, and then followed with a wonderful array of 2 keynote speeches and 2 invited speeches, along with 4 technical sessions during June 29-30. The authors presentations cover topics on Power System Control Model and Simulation Analysis, Electrical Fault Detection and Maintenance Strategy, Digital Communication and Information Systems, Intelligent Electronic Systems and Status Monitoring, with 15 minutes for each presentation, including 2 minutes for the Q&A. Additionally, there are around 100 delegates attending online conference. Delegates had a wide range of sessions to choose from and had enough time in deciding which sessions to attend. List of Committee and Statement of Peer Review are available in this Pdf.

A novel zero-shot learning approach for cross-domain fault diagnosis in high-voltage circuit breakers

High-voltage circuit breakers (HVCBs) are crucial for power system reliability, yet diagnosing their mechanical failures is a significant challenge due to their complex design and unique operating conditions, especially when facing new, unseen fault types. To address this challenge, we propose a novel zero-shot HVCB fault diagnosis method, named X-SAM, leveraging the Xception network and self-attention mechanism (SAM). X-SAM aims to identify new, unseen fault classes solely using known class fault samples during the training phase. X-SAM innovatively combines adaptive feature extraction from multi-source signals and a novel attribute learning system that maps these features to a universal set of fault attributes. This enables the diagnosis of new fault types by analyzing the similarity between predicted attribute vectors and a predefined attribute matrix. Demonstrated through zero-shot diagnosis tasks on multiple HVCBs, X-SAM not only successfully identifies unseen faults using limited data but also paves the way for cross-domain applications, offering a significant advancement in HVCB and electrical equipment fault diagnosis.

A comprehensive review of BMS fault analysis in pure electric vehicles

Pure electric vehicle technology faces numerous technical challenges during the process of independent research and development, with the safety and endurance of power batteries being particularly critical. The Battery Management System (BMS) is a core factor affecting the performance and safety of electric vehicles. The normal operation of the BMS is essential for ensuring the reliability of electric vehicles. However, in practical applications, the BMS may encounter faults that can lead to a decline in battery performance, a reduction in lifespan, and even trigger safety incidents. Therefore, the development of an efficient and accurate fault analysis and diagnostic system is particularly important. This paper systematically explores the fault issues of electric vehicle BMS, including the composition, working principles, and main functions of the BMS, as well as the classification, level definition, case analysis, and resolution measures of faults. The article also provides a detailed introduction to fault analysis methods, including qualitative and quantitative analyses. Finally, based on recent hot topics and the latest research progress, it is concluded that model-based fault diagnosis will become increasingly important. This paper aims to provide a reference for the development of the field of electric vehicle battery management fault diagnosis technology.

Intelligent MPPT for High Gain Zeta Converter for Standalone PV Application with Galvanic Isolation

In this paper, Standalone PV system is designed to operate without the need of electric utility grid which are commonly designed to supply specific DC electric loads. These type of PV system are generally powered using photovoltaic array and consist of solar charging modules, controllers and regulators. The objective of this work is to implement the Radial Basis Function Neural Network (RBFNN) based Maximum Power Point Tracking (MPPT) technique to attain constant DC link voltage of the ZETA converter. This method utilizes a ZETA converter to achieve better voltage gain and lower ripple in the output current and voltage. Using an Artificial Neural Network (ANN) controller to operate a high frequency converter, which improves power conversion efficiency. To ensure safety and prevent electrical faults, an isolation transformer provides galvanic isolation between the high frequency converter and the PV system. Galvanic isolation avoids electrical faults from being transmitted and safeguards connected loads. The rectifier is used to supply the Direct Current (DC) load with the output from the isolation transformer. The rectifier changes the transformer’s Alternating Current (AC) output into DC current to power DC loads. An intelligent MPPT is employed to stabilize the converter’s output voltage and address the intermittent characteristics of PV, and also assists in sustaining the DC link voltage without alterations and ripples from the converter. The efficiency of this work is authenticated via MATLAB simulation 2021a.

Imbalanced Diagnosis Scheme for Incipient Rotor Faults in Inverter-Fed Induction Motors

Recently, fault diagnosing supervised classifiers have been widely proposed to diagnose both electric and mechanical faults in induction motors (IM). However, many of them require a large amount of data, which implies a great effort required for processing fault-related features and building the training set. Furthermore, in real-world datasets, it is required to deal with highly skewed data distributions, also known as class imbalance, which is a limiting issue and can misguide the tuning of machine learning algorithms. Resampling techniques based on a synthetic generation of minority class observations aim to address this problem. Last but not least is the fact that inverter-fed IM introduces undesired harmonics in the monitoring signal altering the diagnosis patterns. This diagnosis scheme is evaluated on experimental imbalanced data oriented to deal with the diagnosis of a rotor in situations where it is fed with an inverter. The results show how this imbalanced approach determines the actual diagnosis performance on a small amount of data. The experimental results demonstrate that balanced training sets built with class balancing techniques improve the classifier and therefore its performance for diagnosing incipient rotor faults in inverter-fed IM with studied and interpretable features recently proposed in this field of study.