Series Arc Fault Research Articles

DC Series Arc Fault Detection Method With Resonant Filter Design for PV Systems

DC Series Arc Fault Detection Method With Resonant Filter Design for PV Systems

AC Series Arc Fault Detection for Wind Power Systems Based on Phase Lock Loop With Time and Frequency Domain Analyses

AC Series Arc Fault Detection for Wind Power Systems Based on Phase Lock Loop With Time and Frequency Domain Analyses

Intelligent Identification Method of Low Voltage AC Series Arc Fault Based on Using Residual Model and Rime Optimization Algorithm

Intelligent Identification Method of Low Voltage AC Series Arc Fault Based on Using Residual Model and Rime Optimization Algorithm

Experimental and model analysis of the thermoelectric characteristics of serial arc in prismatic lithium‐ion batteries

AbstractAiming at the electrical safety problems of lithium‐ion battery system due to series arc fault, a finite element simulation model of square battery under series arc fault is established based on the magnetohydro‐dynamic equations. The arc voltages at different electrode spacings are analysed, and the electric field distribution, magnetic field distribution, arc temperature and flow velocity around the arc are investigated to determine the maximum values and locations of the electric field strength, magnetic density, arc temperature and flow velocity at the time of the arc fault. Then, on the basis of the series arc experimental platform, determine the value of the arc starting voltage and the critical power supply voltage that produces a stable arc, analyse the evolution of the arc burning time with different loop currents, the evolution of the arc of the separation gap, and then summarise the effect of the disaster on the battery. Finally, the errors of simulation and experimental arc voltage and battery surface temperature are analysed to verify the accuracy of the model.

Lightweight Low-Voltage AC Arc-Fault Detection Method Based on the Interpretability Method

Electrical fires are frequently caused by low-voltage AC series arc faults, which can result in significant injuries and property damage. The installation of arc-fault detection devices is mandated or recommended in many regions and countries across the world, yet the current devices’ detection accuracy is insufficient to completely eliminate the risk posed by arc faults. The method based on artificial intelligence is a solution with high detection accuracy, but the AI model is a ‘black box’. When a misjudgment occurs, the cause of the model error cannot be found fundamentally, and the modification and light weight of the model also presents significant difficulties when using the approach. Given the aforementioned issues, this research proposes a novel lightweight low-voltage AC arc-fault detection method based on the explainability approach. By applying the attention mechanism approach and performing a visual analysis, the contribution of arc features to model detection is determined. Model input data optimization and model structure simplification are achieved at the same time as increased model detection accuracy. Ultimately, an experimental prototype for arc-fault detection is designed and validated. Test results demonstrate the effectiveness of the method by demonstrating that the lightweight model maintains 99.69% detection accuracy, even after optimizing the input data by 80% and reducing the model parameters by 51.52%.

AI-enhanced time–frequency domain reflectometry for robust series arc fault detection in DC grids

The generation of series arc fault (SAF) within DC grids poses a significant hazard, potentially leading to electrical fires. However, developing a diagnostic method that is robust to the external environment and noise remains challenging. Conventional reflectometry methods are unable to discern minute impedance fluctuations at cable joint, as they analyze reflected signals generated at points of impedance mismatch to locate faults.This paper presents a new version of reflectometry, which merges artificial intelligence (AI) with the time–frequency domain reflectometry (TFDR) technique. In this study, we designed a structure that combines denoising autoencoders (DAE) with autoencoders (AE) to secure robust SAF detection performance against noise such as ambient environmental changes and weather fluctuations. Furthermore, the time-series generative adversarial network (TimeGAN) was utilized to generate synthetic data. Three experiments were conducted to verify the performance of the proposed method. (1) According to the UL1699B safety standard, an experiment was conducted under laboratory conditions to check whether a SAF could be detected within a maximum of 2.5s immediately after a SAF occurred. (2) To simulate external environmental conditions, a system connected to an inverter and a photovoltaic (PV) simulator was utilized to emulate the occurrence of SAFs. The manipulation of the PV simulator allowed for the simulation of solar irradiance changes due to weather variations and power fluctuations occurring immediately after the system’s power was turned on. This created an experimental setup that closely resembled actual PV systems, where the performance of the proposed algorithm was validated. (3) Finally, a 1kW capacity PV system was constructed, and SAF was simulated within it. The system was tested using four SAF detection methods, and the experimental results were compared and validated.

Multi-classification fault diagnosis of AC series arc based on wavelet decomposition and probabilistic neural network

Abstract AC series arc is difficult to detect because of its complex characteristics, and it can easily cause electrical fire or explosion and other accidents. In order to solve the problem that multi-class loads can not be easily recognized when an arc fault occurs, this paper presents a method for AC series arc multi-classification fault diagnosis based on wavelet decomposition and probabilistic neural network (PNN). According to the standard, the experiment platform of fault arc is designed in this paper, and the current waveform data of fault arc and normal operation under different load types are collected. The multi-dimensional characteristics of the high-frequency current waveform are extracted by processing the detail coefficients obtained by wavelet decomposition. According to the load type and working state, multi-classification data sets are built and input into PNN to train and test the fault diagnosis model. The proposed method can not only accurately detect the fault arc, but also effectively identify the fault load line, which has important reference significance for AC series arc fault diagnosis.

DC Series Arc Fault Detector With Differential DWT and Variable Threshold Method for Photovoltaic Systems

DC Series Arc Fault Detector With Differential DWT and Variable Threshold Method for Photovoltaic Systems

Series alternating current arc fault detection method based on relative position matrix and deep convolutional neural network

The detection of series arc faults is crucial due to the potential safety hazards caused by cable aging and breakage. This paper proposes an arc fault detection framework that utilizes the relative position matrix and deep convolutional network to accurately detect alternating current series arc faults. In this framework, the time series data is first converted into a relative position matrix and then visualized as a two-dimension image. This enables the characterization of singular values and flat shoulders in the arc current, making it easier to extract significant features for the models. Next, a Residual Network with hybrid attention mechanisms model is constructed and the images are fed into the model to determine whether an arc fault has occurred in the current signal. Finally, the data is collected using the experimental platform, and the relative position matrix is constructed with different dimensionality reduction factor. The appropriate dimensionality reduction factor is selected through experimental comparisons. In addition, the effectiveness of the proposed method is verified by measured data, and the proposed model is compared with four other commonly used network models, which demonstrates the superiority of the proposed model in terms of detection performance. The proposed method achieves a detection accuracy of 98.74%.

Series‐arc‐fault diagnosis using feature fusion‐based deep learning model

AbstractThis paper describes the detection of series arc faults, which constitute the major cause of electrical fires, in a power distribution system. Because the characteristics of series arc faults change considerably depending on the load type, their accurate detection and analysis are difficult. We propose a series‐arc‐fault detector that uses a transfer learning (TL)‐based feature fusion model. The model is trained stagewise for various features in the time and frequency domains using a one‐dimensional convolutional neural network combined with a long short‐term memory model that uses an attention mechanism to accurately detect arc‐fault features. To enhance the reliability of the proposed model, we implement an arc‐fault generator compliant with the UL1699 standard and acquire high‐quality data that suitably reflect the real environment. Experimental results show that the proposed model achieves an accuracy of 99.99% in classifying series arc faults for five different loads. Hence, a performance improvement of approximately 1.7% in classification accuracy is reached compared with a feature fusion model that does not incorporate TL‐based model transfer and the attention mechanism.

Integration of wavelet packet transform, residual convolution neural network, and support vector machine for series arc fault detection

Series arc fault (SAF) poses a great challenge to the safe and stable operation of civil low-voltage distribution systems. For the accurate and rapid detection of SAF, this article proposes an SAF detection method using wavelet packet transform (WPT), residual convolution neural network (RCNN), and support vector machine (SVM). First, the raw current signal is decomposed into four wavelet components based on WPT. Then, the 1-D wavelet components are converted into 2-D matrices. Afterward, the matrices are input into RCNN through different channels. Finally, the detection results can be yielded by SVM. The effectiveness of the proposed method is verified based on offline experiments. The average detection accuracy of the proposed method is 99.72%, which is higher than that of the eight comparison methods. Moreover, the results of online experiments indicate that the detection time of the proposed method is less than 100 ms and can satisfy the requirement of standard 1699.

A Method for Recognizing a Series Arc Fault in a Low-voltage Network

A Method for Recognizing a Series Arc Fault in a Low-voltage Network

Series arc fault detection based on multi-domain depth feature association

Series arc fault detection based on multi-domain depth feature association

Arc-1DCNN: An enhanced model for series arc fault detection

Series Arc Faults (SAFs) represent a prominent cause of electrical fires in low-voltage distribution systems, often arising from faulty connections or deteriorated insulation. These SAFs occurrences generate high-temperature arcs that endanger electrical system safety. As a result, detecting and accurately identifying SAFs have become crucial concerns. However, the line noise interference and the complexity of the electrical environment make SAFs detection challenging. In this paper, we propose a novel method that combines Wiener filtering with the Arc-1DCNN model to enhance SAFs detection. The method leverages Wiener filtering to enhance current signal, effectively reducing noise interference and providing a more robust dataset for training. To fully exploit the rich high-frequency characteristics of SAFs, Arc-1DCNN incorporates a High-Frequency-Feature-Attention module, enabling the model to capture subtle SAFs anomalies and significantly improving detection accuracy. Experimental validation demonstrates Arc-1DCNN's exceptional performance with 99.94% detection accuracy for SAFs, showcasing its potential for addressing SAFs detection challenges.

Modelling Inductive Sensors for Arc Fault Detection in Aviation.

Modern aircraft are being equipped with high-voltage and direct current (HVDC) architectures to address the increase in electrical power. Unfortunately, the rise of voltage in low pressure environments brings about a problem with unexpected ionisation phenomena such as arcing. Series arcs in HVDC cannot be detected with conventional means, and finding methods to avoid the potentially catastrophic hazards of these events becomes critical to assure further development of more electric and all electric aviation. Inductive sensors are one of the most promising detectors in terms of sensitivity, cost, weight and adaptability to the circuit wiring in aircraft electric systems. In particular, the solutions based on the detection of the high-frequency (HF) pulses created by the arc have been found to be good candidates in practical applications. This paper proposes a method for designing series arc fault inductive sensors able to capture the aforementioned HF pulses. The methodology relies on modelling the parameters of the sensor based on the physics that intervenes in the HF pulses interaction with the sensor itself. To this end, a comparative analysis with different topologies is carried out. For every approach, the key parameters influencing the HF pulses detection are studied theoretically, modelled with a finite elements method and tested in the laboratory in terms of frequency response. The final validation tests were conducted using the prototypes in real cases of detection of DC series arcs.

Series arc fault detection method based on a residual deformable convolutional network for complex branch circuit

Series arc fault detection method based on a residual deformable convolutional network for complex branch circuit

Research on the Identification Method of Series Arc Fault Based on the Feature Sensitivity Analysis and the TVA Coefficient Optimized Random Forest

Research on the Identification Method of Series Arc Fault Based on the Feature Sensitivity Analysis and the TVA Coefficient Optimized Random Forest

A Novel Series Arc Fault Detection Method Based on CEEMDAN and IFAW-1DCNN

A Novel Series Arc Fault Detection Method Based on CEEMDAN and IFAW-1DCNN

A series fault arc detection method based on denoising autoencoder and deep residual network

Given the problem that the existing series arc fault identification methods use existing features such as the time-frequency domain of the current signal as the basis for identification, resulting in relatively limited arc detection solutions, and that the methods of directly extracting current signal features using deep learning algorithms have insufficient feature extraction, a new series arc fault detection method based on denoising autoencoder (DAE) and deep residual network (ResNet) is proposed. First, a large number of training samples are obtained through sliding window and data normalization methods, and then high-dimensional abstract feature data are obtained from the fault and normal samples collected in the experiment through denoising autoencoders, converted into grayscale images, and processed in pseudo-color. The single-channel grayscale images are mapped into three-channel color values, and finally, the three-channel values are input into the constructed deep residual network for deep learning training. In the 152 super high-level ResNet, the arc fault recognition rate can reach 99.7%. For loads that have not participated in ResNet network training, the recognition rate can also reach 97.6%.

Detection and localization of fault in DC microgrid using discrete Teager energy and generalized least square method

PurposeThis paper aims to introduce a new fault protection scheme for microgrid DC networks with ring buses.Design/methodology/approachIt is well recognized that the protection scheme in a DC ring bus microgrid becomes very complicated due to the bidirectional power flow. To provide reliable protection, the differential current signal is decomposed into several basic modes using adaptive variational mode decomposition (VMD). In this method, the mode number and the penalty factor are chosen optimally by using arithmetic optimization algorithm, yielding satisfactory decomposition results than the conventional VMD. Weighted Kurtosis index is used as the measurement index to select the sensitive mode, which is used to evaluate the discrete Teager energy (DTE) that indicates the occurrence of DC faults. For localizing cable faults, the current signals from the two ends are used on a sample-to-sample basis to formulate the state space matrix, which is solved by using generalized least squares approach. The proposed protection method is validated in MATLAB/SIMULINK by considering various test cases.FindingsDTE is used to detect pole-pole and pole-ground fault and other disturbances such as high-impedance faults and series arc faults with a reduced detection time (10 ms) compared to some existing techniques.Originality/valueVerification of this method is performed considering various test cases in MATLAB/SIMULINK platform yielding fast detection timings and accurate fault location.