Electrical Equipment Fault Research Articles

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.

Classification of Multi-Source Partial Discharge in GIS

Abstract Partial discharge (PD) analysis is an important method to identify electrical equipment faults. However, due to the influence of environmental electromagnetic interference and other equipment discharges in the power supply circuit during the on-site PD test, the collected PD signal is the combination of various PD and noise, which makes it challenging to identify the type or source of on-site partial discharge. A multi-source PD classification method based on the multiple threshold and K-means clustering algorithm is pro-posed to solve this problem. First, wavelet transform with an improved threshold is used to initially denoise the original signal. Then the multiple threshold method is used to filter the residual ripple between every two pulses. Finally, spectrum analysis is carried out for each pulse, and the maximum value of the spectrum is extracted as the feature quantity. Then, the K-means algorithm is used to classify the PD pulses, and the PRPD images of PD pulses in different frequency domains are obtained. The results show that the method adopted in this paper can denoise, extract and classify the PD signals collected on the site, and the PRPD diagram of PD pulse after classification is more obvious, which provides a basis for identifying the PD source on the site.

A Novel Electrical Equipment Status Diagnosis Method Based on Super-Resolution Reconstruction and Logical Reasoning.

The accurate detection of electrical equipment states and faults is crucial for the reliable operation of such equipment and for maintaining the health of the overall power system. The state of power equipment can be effectively monitored through deep learning-based visual inspection methods, which provide essential information for diagnosing and predicting equipment failures. However, there are significant challenges: on the one hand, electrical equipment typically operates in complex environments, thus resulting in captured images that contain environmental noise, which significantly reduces the accuracy of state recognition based on visual perception. This, in turn, affects the comprehensiveness of the power system's situational awareness. On the other hand, visual perception is limited to obtaining the appearance characteristics of the equipment. The lack of logical reasoning makes it difficult for purely visual analysis to conduct a deeper analysis and diagnosis of the complex equipment state. Therefore, to address these two issues, we first designed an image super-resolution reconstruction method based on the Generative Adversarial Network (GAN) to filter environmental noise. Then, the pixel information is analyzed using a deep learning-based method to obtain the spatial feature of the equipment. Finally, by constructing the logic diagram for electrical equipment clusters, we propose an interpretable fault diagnosis method that integrates the spatial features and temporal states of the electrical equipment. To verify the effectiveness of the proposed algorithm, extensive experiments are conducted on six datasets. The results demonstrate that the proposed method can achieve high accuracy in diagnosing electrical equipment faults.

Condition Assessment of Electrical Power Devices using Infrared Thermography: A Review

Departures from the stable operation of electrical equipment usually appear as changes in parameters such as vibrations, pressure, temperature, power, and flow. Excessive changes in these parameters will indicate significant damage, leading to total or partial breakdown of equipment. This paper reviews the use of infrared thermography (IRT) for the operating condition temperature monitoring of electrical equipment. Infrared thermography is a contactless method that is based on thermal radiation principles and used for determining the temperature distribution on the surface of objects by measuring the intensity of radiation emitted by the object. The basic principles underlying IRT are presented in this review, showing its pros and cons, the various IRT methods, processes involved in IRT image acquisition, intelligent techniques for IR image analysis, and factors that affect the accuracy of results, including technical, environmental, and procedural factors. Also presented is an overview of common applications of IRT condition monitoring to solar energy, medicine, civil infrastructure, and aerospace equipment. Common faults in electrical equipment, including those in transformers, circuit breakers, feeder pillars and arrestors, are discussed with illustrations from recent research studies. These studies have demonstrated the effectiveness of IRT in the predictive maintenance of electrical installations. Hence, the replication of the techniques reviewed in this work is recommended so as to reduce current costs incurred in maintaining and replacing damaged equipment, and the associated time losses.

Optimized OTSU Segmentation Algorithm-Based Temperature Feature Extraction Method for Infrared Images of Electrical Equipment.

Infrared image processing is an effective method for diagnosing faults in electrical equipment, in which target device segmentation and temperature feature extraction are key steps. Target device segmentation separates the device to be diagnosed from the image, while temperature feature extraction analyzes whether the device is overheating and has potential faults. However, the segmentation of infrared images of electrical equipment is slow due to issues such as high computational complexity, and the temperature information extracted lacks accuracy due to the insufficient consideration of the non-linear relationship between the image grayscale and temperature. Therefore, in this study, we propose an optimized maximum between-class variance thresholding method (OTSU) segmentation algorithm based on the Gray Wolf Optimization (GWO) algorithm, which accelerates the segmentation speed by optimizing the threshold determination process using OTSU. The experimental results show that compared to the non-optimized method, the optimized segmentation method increases the threshold calculation time by more than 83.99% while maintaining similar segmentation results. Based on this, to address the issue of insufficient accuracy in temperature feature extraction, we propose a temperature value extraction method for infrared images based on the K-nearest neighbor (KNN) algorithm. The experimental results demonstrate that compared to traditional linear methods, this method achieves a 73.68% improvement in the maximum residual absolute value of the extracted temperature values and a 78.95% improvement in the average residual absolute value.

Fault Feature Mining and Identification Method of 10kV XLPE Cable Combining SAE and RF

Background: Feature extraction methods such as statistical features and image features based on traditional partial discharge spectrograms require the support of expert experience and prior knowledge, making their engineering applications have significant limitations. Currently, electrical equipment fault diagnosis is moving towards intelligent and scientific directions, and how to apply deep learning methods for more accurate, intelligent, and autonomous diagnosis has become a hot issue in the current field. background: Feature extraction methods such as statistical features and image features based on traditional partial discharge spectrograms require the support of expert experience and prior knowledge, making their engineering applications have significant limitations. Methods: The construction and optimal selection of high-voltage cable partial discharge feature space is an important means to improve recognition accuracy. This paper proposes a new method that can independently and deeply mine partial discharge image features to quickly identify partial discharge types. Firstly, a self encoder is used to encode and decode partial discharge images, and a multi-level stack structure is used to achieve the goal of deep feature mining; then, the partial discharge data features decoded based on a stack self encoder are imported into a random forest network for type recognition; Finally, based on the random forest algorithm, the redundant feature space is optimized and compared with other traditional recognition methods. Results: The recognition accuracy of the proposed method is about 10% higher than that of traditional methods. Conclusion: The optimized feature parameters can maintain more than 90% recognition accuracy in both random forest algorithms, common support vector machines, and BP neural networks, proving the feasibility and effectiveness of the method in this paper. result: The recognition accuracy of the proposed method is about 10% higher than that of traditional methods.

The use of power information technology in fault diagnosis of electrical equipment

Abstract As the electric power industry rapidly advances, diagnosing faults in electrical equipment has emerged as a critical challenge. In this study, we leverage advancements in power information technology to develop a method for extracting feature volumes, incorporating multiple characteristics to address mixed faults. Our approach begins with the application of a Backpropagation (BP) neural network to extract fault features from electrical equipment. Subsequently, we employ a Bayesian-optimized Correlation Vector Machine (CVM) classifier for precise diagnosis of mixed faults in transformer windings. We evaluated the performance of our BP-RVM model against traditional diagnostic models through real-world electrical fault diagnosis tests. The results demonstrated high diagnostic accuracy, with a maximum of 99.19%, a minimum of 96.41%, and an average accuracy of 97.73%, indicating a significant success rate in diagnosing types of electrical equipment faults. By providing new theoretical support and technical guidance, this study can improve the accuracy and efficiency of electrical equipment fault diagnosis.

Research on visualization monitoring technology of vulnerable high-voltage electrical equipment in substation based on BP artificial neural network

Abstract This study develops a visualization monitoring system for substation equipment operational status, utilizing mobile monitoring technologies. The system architecture integrates a core functional module aligned with comprehensive system requirements, enhanced by a BP neural network to optimize the server’s data mining capabilities. The research focuses on the analysis of typical faults in crucial substation electrical equipment, applying a Fourier algorithm for preprocessing the fault data. Employing the diagnostic principles of the BP neural network, the study designs a thermal fault diagnosis process for the substation apparatus. Experimental scenarios were established to evaluate the BP neural network’s performance by comparing three linear regression sample values. The practical application of the BP neural network model was assessed through integration with substation field data. Cross-validation of the field data indicates that the fault location algorithm accurately identifies 11 types of faults from 85 alarm signals in the secondary condition monitoring of substations, achieving a reliability of 98% or higher, which underscores its high applicability and operational feasibility.

Real-Time Monitoring of Air Discharge in a Switchgear by an Intelligent NO2 Sensor Module.

An air-insulated power equipment adopts air as the insulating medium and is widely implemented in power systems. When discharge faults occur, the air produces decomposition products represented by NO2. The efficient NO2 sensor enables the identification of electrical equipment faults. However, single-sensor-dependent NO2 detection is vulnerable to interfering gases. Implementing the sensor array could reduce the interference and improve detection efficiency. In the field of NO2 detection, In2O3 sensors have exhibited tremendous advantages. In our work, four composites based on In2O3 are integrated into sensor arrays, which could detect 250 ppb of NO2 and exhibit excellent selectivity when simultaneously exposed to CO. To further reduce the impact of humidity on gas-sensing performance, a convolutional neural network and a long short-term memory model equipped with an attention mechanism are proposed to evaluate NO2 concentration within 1 ppm, and the detection error is 63.69 ppb. In addition, the NO2 concentration estimation platform based on a microgas sensor is established to detect air discharge faults. The average concentration of NO2 generated by 10 consecutive discharge faults at 15 kV is 726.58 ppb, which indicates severe discharge in the switchgear. Our NO2 estimation method has great potential for large-scale deployment in low- and medium-voltage switchgears.

Fault diagnosis of electrical equipment based on virtual simulation technology

Abstract In order to efficiently and accurately diagnose train electrical faults, we propose a fault diagnosis method for electrical equipment based on virtual simulation technology. First, Creo software was used to build a subway train model. Then, 3DMAX software was used to make animation and demonstrate the working principle and action process of the train electrical system. Finally, using Unity 3D software, a human–computer interaction mechanism was established, achieving presence and realism. This system realizes the functions of knowledge learning, student assessment, principal display, and troubleshooting of the electrical system of subway trains and is compared with the method of manual diagnosis. Experimental results show that in the designed fault diagnosis system, the detection time for various types of faults is shorter than 30 s, whereas the diagnosis time of the manual diagnosis method is 30–52 s. It shows that the electrical equipment fault diagnosis system based on virtual simulation has the advantages such as short fault diagnosis time and high efficiency. In addition, the highest diagnostic accuracy of the manual diagnosis method is 75.48%, which is far lower than the accuracy of the diagnostic system. Conclusion: It is proved that the designed fault diagnosis system has the advantages such as short detection time and high accuracy and can meet the safety requirements of industrial production.

Retracted: Neural Network Based on Health Monitoring Electrical Equipment Fault and Biomedical Diagnosis.

[This retracts the article DOI: 10.1155/2022/8358794.].

A New Method for Diagnosing Motor Bearing Faults Based on Gramian Angular Field Image Coding and Improved CNN-ELM

The most common cause of electric motor failure is the bearings, and so methods for fast and accurate diagnosis of motor bearing failure are urgently needed. Traditional fault diagnosis methods have high uncertainty and complexity since they require manual extraction of features. Deep learning has shown good performance in electrical equipment fault detection, and it can directly complete end-to-end diagnosis of motor faults, avoiding human involvement. Here, a new fault diagnosis method is presented which combines Gramian angular field (GAF) image coding, extreme learning machine (ELM) and convolutional neural network (CNN). The method has three main stages: First of all, GAF is utilized to convert the acquired vibration break signals into 2-D pictures. Next, the enhanced CNN model is taken to identify the elements of the converted image quickly and accurately. Finally, the ELM is used as the final classifier to gain further accuracy and diagnostic speed of fault classification. Experiments were designed to validate the proposed method using two different motor bearing fault datasets at Case Western Reserve University and autonomous experiment and performance is compared with several commonly used intelligent diagnosis algorithms. The proposed method’s accuracy in the experiment designed in this paper can reach 99.2% at most, and it only takes 0.835s to complete the diagnosis, which outperforms traditional diagnostic methods on both datasets and improving the maximum diagnostic accuracy by 33.6%. The findings indicate that this method can classify various fault types efficaciously, and has the benefits of quick diagnosis, high accuracy, and good generalization ability.

PREVENTING AND MINIMIZING ARC FLASH RISK IN POWER SYSTEM NETWORK

Arc flash events have resulted in several accidents due to faults in electrical equipment that lead to a significant release of energy. This event is a hazard and threat to the Power System Security and due to the large energy release, plasma is generated, as pressure increases since it causes physical damage to equipment while life of system operators within the vicinity of its occurrence are at risk. Although arc flash is one of the electrical safety programs that have been in existence, arc flash hazard was not adequately addressed until recently. However, the Electric Arc phenomenon is relatively new in the Nigerian power industry, there are certain aspect that are yet to be treated by the available literature, hence it is the duty of this work to establish model for addressing the observed lapses. The design is adequately prepared for the power system security analysis using typical scenarios in industrial facilities that are prone to yield high incident energy levels. In line with the foregoing, the developed methodology is validated using a segment of the Nigerias power industry as case study.

Intelligent Fault Diagnosis Method for Industrial Processing Equipment by ICECNN-1D

Intelligent algorithm has been widely implemented to effectively diagnose faults in industrial instrument, electrical equipment and mechanical equipment. In addition, the rapid development of sensing technology generated enormous time series signal. Accordingly, diagnosing faults by analyzing time series signal has been widely developed. This paper aims to diagnose faults by applying improved Convolution Neural Network with Compression Enhancement (ICECNN-1D) to analyze time series signal, which effectively considers time series property of signal while diagnosing faults by artificial intelligence. Additionally, a large number of trend features and fluctuation features in high-frequency time series are also considered. the recognition rates of almost other machine learning algorithm are less than 90% in the experiments. Other methods may provide high rate of recognition, but their fluctuation of the recognition rate has varied obviously with different loads, and results provide undesirable ability of generalization under different working conditions. Comparatively, ICECNN-1D model provides high recognition rate and terrific ability of generation while processing time series with high frequency, and its accuracy of the recognition rate fluctuates inconspicuously with different loads.

Neural Network Based on Health Monitoring Electrical Equipment Fault and Biomedical Diagnosis.

In order to improve the accuracy of electrical equipment failure diagnosis and keep electrical equipment operating safely and efficiently, this paper proposes to design an electrical equipment failure diagnosis system based on a neural network, analyze the faults of electrical equipment and their causes, and establish knowledge base according to relevant data and expert judgment. The fault knowledge base was introduced into the neural network operation structure, and the fault diagnosis results were classified step by step through multiple subnetworks. In data preprocessing, in order to avoid the redundancy of primary fault information features, the principal component heuristic attribute reduction algorithm was used to select the fault data samples optimally. The neural network learning algorithm is used to calculate the forward direction and error rate of the initial error data, and the reliability function is used to optimize the initial weight threshold of the neural network, propagating the error backwards and high. Experimental results show that adding attribute reduction improves error classification performance, avoids the problem of local minima through neural network operation, and has fewer iteration steps, lower average error, and higher accuracy of fault diagnosis, reaching 95.6%.

Synthesis of sphere-like WO3 and their application to SO2 sensing

The detection of SO2, one of the main SF6 decomposition gases, can be applied to diagnose faults in gas-insulated electrical equipment. In this study, spherical WO3 nanoparticles were prepared by a simple hydrothermal method. Their physical phase, microstructure and ability to sense SO2 gas were investigated by various techniques. The experimental results show that the spherical gas sensors of WO3 have excellent performance for SO2 gas detection in terms of selectivity, response time and operating temperature, and can be used for effective detection of the major decomposition products of SF6.

Modernization of electromechanical transmission for dump trucks based on long-term operation data

In open pit mining, overburden and mineral haulage is carried out mostly by dump trucks. The number of high-capacity machines persistently grows. Such dump trucks mainly use electromechanical transmission systems. As a rule, dump trucks operate all day and all year round, with idle time for scheduled maintenance. The climatic service conditions assume variations in temperature, humidity and atmospheric pressure in wide ranges during a year, moreover, these physical quantities can fluctuate violently within a short time, for instance, within a day. The road conditions – road grade, hardness, roughness, length, altitude difference – differ greatly per open pit mines. Furthermore, air dustiness, including current-conducting coal- or metal-bearing dust should be taken into account. On the whole, these numerous and diverse factors are impossible to embrace in full at the stages of machine engineering and testing. Thus, during operation, it is necessary to accumulate and analyze the hand-on experience, and to improve all components of electromechanical transmission. This article gives data on four-year operation of BelAZ dump trucks with capacity of 90 and 240 t equipped with electromechanical transmission in open pit coal and ore mines. The traction electrical equipment faults are generalized, their causes are revealed, design modifications are described, as well as the processes of manufacturing and testing and the algorithm of diagnosis are reported. The low count of faults during operation and the high availability factor of the dump trucks equipped with electromechanical transmissions manufactured by RUSELPROM is reflective of the proficiency and competency of the machine engineering, design and testing. The modifications introduced into the electromechanical transmissions are mostly aimed at cost reduction and performance buildup, i.e. at competitive recovery of the product. The obtained results are used in engineering of traction electric equipment set for dump trucks of higher capacity (136, 180, 360 t).

Thermal Fault Diagnosis of Electrical Equipment in Substations Based on Image Fusion

Infrared thermal imaging can diagnose whether there are faults in electrical equipment during non-stop operation. However, the existing thermal fault diagnosis algorithms fail to consider an important fact: the infrared image of a single band cannot fully reflect the true temperature information of the target. As a result, these algorithms fail to achieve desired effects on target extraction from low-quality infrared images of electrical equipment. To solve the problem, this paper explores the thermal fault diagnosis of electrical equipment in substations based on image fusion. Specifically, a registration and fusion algorithm was proposed for infrared images of electrical equipment in substations; a segmentation and recognition model was established based on mask region-based convolutional neural network (R-CNN) for the said images; the steps of thermal fault diagnosis were detailed for electrical equipment in substations. The proposed model was proved effective through experiments.

Maintenance Automation Architecture and Electrical Equipment Fault Prediction Method in Tanzania Secondary Distribution Networks

Distribution networks remain the most maintenance-intensive parts of power systems. The implementation of maintenance automation and prediction of equipment fault can enhance system reliability while reducing the overall costs. In Tanzania, however, maintenance automation has not been deployed in secondary distribution networks (SDNs). Instead, traditional methods are used for condition prediction and fault identification of power assets (transformers and power lines). These (manual) methods are costly and time-consuming, and may introduce human-related errors. Motivated by these challenges, this work introduces maintenance automation into the network architecture by implementing effective maintenance and fault identification methods. The proposed method adopts machine learning techniques to develop a novel system architecture for maintenance automation in the SDN. Experimental results showed that different transformer prediction methods, namely support vector machine, kernel support vector machine, and multi-layer artificial neural network, give performance values of 96.72%, 97.50%, and 97.53%, respectively. Furthermore, oil based performance analysis was done to compare the existing methods with the proposed method. Simulation results showed that the proposed method can accurately identify up to ten transformer abnormalities. These results suggest that the proposed system may be integrated into a maintenance scheduling platform to reduce unplanned maintenance outages and human maintenance-related errors.
 Keywords: Predictive maintenance; fault identification; fault prediction; maintenance automation; secondary electrical distribution network

Infrared-Visual Image Fusion and CNN Model in Electrical Faults Diagnosis

In this paper, we proposed a new faults diagnosis method based on the fusion of visible and infrared images of electrical equipment. Firstly, the discrete wavelet transform method is used to fuse the visible and infrared images, which enables the accurate location of the electrical equipment. Then, a deep convolution neural network (CNN) model is employed to identify faults in electrical equipment. Three parameters of CNN including connection weight, convolution layer parameters and pooling layer strategy are designed in this paper. The inputs of CNN are the fused reconstructed images and the outputs are the classifications of faults. Finally, simulation experiments and analysis show that the algorithm proposed in this paper can effectively improve the contrast and clarity of the fused images. It can reduce noise interference, and improve the location accuracy of electrical equipment. More specifically, the faults diagnosis rate is improved by 2-6% with the proposed method.