Arc Fault Detection Research Articles

A DC Series Arc Fault Detection Method Based on a Lightweight Convolutional Neural Network Used in Photovoltaic System

Although photovoltaic (PV) systems play an essential role in distributed generation systems, they also suffer from serious safety concerns due to DC series arc faults. This paper proposes a lightweight convolutional neural network-based method for detecting DC series arc fault in PV systems to solve this issue. An experimental platform according to UL1699B is built, and current data ranging from 3 A to 25 A is collected. Moreover, test conditions, including PV inverter startup and irradiance mutation, are also considered to evaluate the robustness of the proposed method. Before fault detection, the current data is preprocessed with power spectrum estimation. The lightweight convolutional neural network has a lower computational burden for its fewer parameters, which can be ready for embedded microprocessor-based edge applications. Compared to similar lightweight convolutional network models such as Efficientnet-B0, B2, and B3, the Efficientnet-B1 model shows the highest accuracy of 96.16% for arc fault detection. Furthermore, an attention mechanism is combined with the Efficientnet-B1 to make the algorithm more focused on arc features, which can help the algorithm reduce unnecessary computation. The test results show that the detection accuracy of the proposed method can be up to 98.81% under all test conditions, which is higher than that of general networks.

Series Dc arc fault detection and location in wind-solar-storage hybrid system based on variational mode decomposition

As the main new energy, the wind-solar-storage hybrid system is widely used because of its excellent complementarity. However, due to the complexity of the system, series DC arc faults are prone to occur. This paper presents a method for series DC arc fault detection and location in wind-solar-storage hybrid system, which works mainly on the principle of threshold comparison in the time-frequency domain. Therein, an algorithm called variational mode decomposition (VMD) is employed. The voltage signal of the identical DC load under different operating conditions is decomposed by VMD, and the time-frequency domain characteristics of the normal operating conditions are used as thresholds. The series DC arc faults in different subsystems are detected and located by comparing the time-frequency domain features under different operating conditions with the threshold features. Compared with classical decomposition algorithms, Empirical Mode Decomposition (EMD) and Wavelet Transform (WT), the results show that VMD can eliminate the influence of noise and extract the fault signals of different systems more accurately, ensuring the precise localization of series DC arc faults.

Unknown Input Observer-Based Series DC Arc Fault Detection in DC Microgrids

In this paper, a fault detection and isolation technique for series arc faults in dc microgrids with multiple power electronics loads is proposed using Unknown Input Observers (UIO). The dc microgrid is first modeled as a linear system using its corresponding graph information, including the oriented incidence matrix. The lines are assumed to be in Pi form (resistive, inductive, and capacitive) defining the dynamic states: line currents and node voltages. Sources and loads are considered inputs to the network and details are presented to include the case where these are not measured. DC series arc faults are then analyzed as disturbances affecting any line. An UIO framework is then presented to detect and identify the faulted line using the network model. Simulation and experimental results are then presented.

Arc fault detection devices efficiency in cooperation with switch-mode power supplies

The paper presents a special case of ineffective protection with Arc Fault Detection Device. The purpose of this article was to investigate why an AFDD does not detect sparking in a circuit supplying a switch-mode power supply. Therefore, laboratory tests according to IEC 62,606 and tests under real operating conditions were performed for this purpose. The devices of different manufacturers producers were compared with each other and it was checked if a similar problem is repeated with each AFDD. The tests conclude that switching-mode power supplies as capacitive loads negatively influence the spark detection efficiency, the selection of an AFDD should always be preceded by an analysis of the minimum operating currents (2.5 A) and there are differences in the detection sensitivity between devices of various manufactures.

Inception module and deep residual shrinkage network-based arc fault detection method for pantograph–catenary systems

Inception module and deep residual shrinkage network-based arc fault detection method for pantograph–catenary systems

Research on Low-Voltage AC Series Arc-Fault Detection Method Based on Electromagnetic Radiation Characteristics

Arc fault is an important cause of electrical fire. At present, the arc-fault detection method based on current and voltage is vulnerable to the influence of a nonlinear load and switching operation in the line, resulting in misjudgment and omission. Therefore, an arc-fault detection method based on the characteristics of electromagnetic radiation is proposed. A low-voltage AC series arc-fault simulation platform is built, and a simple annular antenna is designed to receive an electromagnetic radiation signal. It is proved by experiments that electromagnetic radiation signals have similar characteristic frequencies (13.6–14.2 MHz) under different currents, loads, arc positions and arc occurrence times. At the same time, the electromagnetic radiation signal of a low-voltage AC series arc and normal switching operations are compared. The pulse oscillation time of the radiation signals of the operating arc (2 μs) is far shorter than that of the faulty arc (4 μs), and the characteristic frequency of the radiation signal generated by the switching operation (9.35 MHz) is significantly lower than that of the series arc radiation signal (14 MHz). Compared with the existing methods, this method does not need to consider the influence of current, nonlinear load and other factors in the line, and can accurately distinguish the operating arc and faulty arc.

A novel series arc fault detection method for photovoltaic system based on multi-input neural network

There is a risk of fire caused by series arc failure in the operation of photovoltaic (PV) system. Therefore, it is required to discuss a solution for rapid arc fault detection. To address the series arc fault (SAF) detection under different working conditions, a method based on squeeze-and-excitation (SE)-inception multi-input convolutional neural network (MICNN) is proposed. Firstly, normalization and Hankel-singular value decomposition algorithm are used to denoise the current, which effectively avoid the influence of switching frequency on the subsequent diagnostic accuracy. Subsequently, the filtered time-domain signal and the frequency-domain signal after Fourier transform are input into a variant one-dimensional convolutional neural network (1D-CNN) model for training and testing. The proposed model is characterized by transforming the traditional CNN into MICNN, and introducing the inception network with spatial scaling function and the SE network structure with channel attention mechanism. Extensive simulations are performed to evaluate the efficacy with a desirable result of 97.48%, which is superior to traditional methods such as CNN, wavelet decomposition, and mathematical statistics. The proposed method can not only detect arc faults occurring in different locations, but also resist the disturbance of dynamic shading, maximum power point tracking (MPPT), strong wind, etc. In addition, this model achieved satisfactory results in three cases of long line fault, single series and array ageing.

Series Arc Fault Detection in a Low-Voltage Power System Based on CEEMDAN Decomposition and Sensitive IMF Selection

In the series arc fault detection of a low-voltage distribution network, the features of the fault current signal are easily submerged and arc fault features are difficult to be represented, which greatly increases the difficulty of fault arc detection based on current signals. To solve these problems, a series arc fault detection method combining CEEMDAN decomposition and sensitive IMF selection is proposed. In this paper, the CEEMDAN algorithm is first applied to complete decomposition of the arc current in series faults. Then, 12 feature indicators of the arc current are defined and the frequency band division of the IMF component is realized according to the kurtosis index and energy feature which are more sensitive. The time window-based feature calculation method is proposed to obtain the local features of the time scale of each high-frequency IMF component. Accurate selection of sensitive IMF components is realized by comparing feature indexes such as the variance and root mean square value. Finally, for the current feature set, the second dimension reduction is realized by the subspace transformation algorithm and the series arc fault detection is realized based on the SVM. The actual experiments show that the optimal detection accuracy of the proposed method is 91.67% and the average accuracy of 10 crossvalidation experiments is 88.33%. It shows that the proposed sensitive IMF selection method can effectively capture the fault component signals in the current and the proposed fault feature description method has good representation and discrimination ability.

TL–LEDarcNet: Transfer Learning Method for Low-Energy Series DC Arc-Fault Detection in Photovoltaic Systems

The arc-fault phenomenon in photovoltaic (PV) systems has emerged as a major problem in recent years. Existing studies on arc-fault detection in conventional PV systems primarily focus on detecting typical stable arc-faults. Low-energy arc-faults are more challenging to detect than stable arc-faults because of their low current distortions, short durations, and nonlinear properties. These low-energy arc-faults, which are precursors to stable arc-faults, could even inflict serious damage on the system components. Here, a transfer learning-based low-energy arc-fault detection network (TL–LEDarcNet) using a two-stage training method is proposed to proactively detect series DC arc-faults by considering low-energy arc-faults. A one-layer long short-term memory network combined with a lightweight one-dimensional convolutional neural network was developed to detect low-energy arc-faults by only using the sensed current information. The results of offline and online experiments conducted with a commercial grid-connected PV inverter indicate that the proposed method can perform real-time operations on a single-board computer and detect low-energy arc-faults with an accuracy of 95.8%, which is higher than previous methods considered in this study.

Series Arc Fault Detection Based on Wavelet Compression Reconstruction Data Enhancement and Deep Residual Network

Series arc fault is the main cause of electrical fire. Because of the complex load types and the randomness of arc fault in low-voltage distribution system, it is difficult to obtain fault data for data-driven machine learning algorithm to achieve higher accuracy. Therefore, an arc fault detection model based on residual network (ResNet) is proposed from the perspective of computer vision, and an appropriate data enhancement method is given. We first analyze the time-domain current signals of different load arc faults by multilayer discrete wavelet analysis. The obtained five-layer discrete wavelet detail values are fused into a matrix, and the coefficient matrix is then converted into a phase space image (RGB color space) using a colormap index. The phase space feature map is made into a classification dataset according to the load and fault type, which is input into ResNet in the form of three channels (RGB) for convolution and classification recognition. Then, aiming at the over-fitting phenomenon of neural network caused by small sample, a data enhancement method based on wavelet compression reconstruction is proposed. Finally, we set up different datasets to compare our method with typical neural network regularization methods. The results show that our method effectively solves the over-fitting phenomenon of deep network ResNet152 and improves the accuracy of ResNet 50/101/152 to 97.91%, 96.30%, and 97.69%, respectively.

Detection of AC Arc Faults of Aviation Cables Based on H-I-W Three-Dimensional Features and CNN-LSTM Neural Network

Aiming at the difficulty in identifying subtle AC arcs in aviation cables, this paper proposes an arc fault detection method based on the combination of three-dimensional features and convolutional neural network-long short term memory (CNN-LSTM). Firstly, based on the SAE AS5692A standard, the vibration series test, cutting parallel test, and wet arc trajectory parallel test were respectively conducted and the arc current signals under four types of loads were collected to analyze the arc faults under different incentives. Then, the three-dimensional features of arc current including Hurst exponent, inter-harmonic variance, and wavelet energy entropy (H-I-W) were extracted with an improved algorithm so as to enhance the fault identification capability and overcome the limitation of single-dimensional feature detection. Finally, a grid search algorithm was used to find out the optimal parameters, and a three-dimensional reference input CNN-LSTM neural network was designed to detect arc faults. The experimental results showed that the average detection accuracy of the proposed method for the three AC arc faults respectively reached 98.52%, 99.23%, and 98.51%. The real-time performance of the proposed method was better than the comparison methods, proving the feasibility and effectiveness of the proposed method.

Fast Detection of Weak Arc Faults Based on Progressive Singular-Value-Decomposition and Empirical Analyses

Fast Detection of Weak Arc Faults Based on Progressive Singular-Value-Decomposition and Empirical Analyses

Fast-Fourier-Transform Enhanced Progressive Singular-Value-Decomposition Algorithm in Double Diagnostic Window Frame for Weak Arc Fault Detection

In this study, a novel method that progressively applies the fastest form of singular-value decomposition (SVD) to extract nonperiodic arc-fault features is proposed in order to pursue a competent solution for AC weak arc fault detection. First, bus-current signals of the normal state and the arc-fault state are collected and normalized before being processed by progressive SVD (PSVD) to detect the discrepancy brought by comparatively stronger arc-fault nonperiodic components expressed in singular values. To provide a more comprehensive feature extraction for an enhanced accuracy, the fast Fourier transform (FFT) is incorporated for accumulating periodic variations caused by arc faults. Because weak arc faults are difficult to distinguish from normal signals when they start, a double diagnostic window frame (DDWF) is designed to reduce false negative errors. The effectiveness of each partial design of the method is verified by experiments with numerous load types and current amplitudes conducted on an industrial experimental platform. The proposed PSVD-FFT algorithm has achieved a satisfactory and consistent performance measured by both the detection accuracy and diagnosis time in all of the experiments. The proposed method is on average at least 10% more accurate than the selected methods for a parallel comparison (in total more than a thousand experimental cases), with a satisfactory range of execution time.

A Novel Series Arc Fault Detection Method Based on Mel-Frequency Cepstral Coefficients and Fully Connected Neural Network

Arc faults pose challenges to electric safety, which can cause serious fire hazards. However, the commonly used arc fault detection method is prone to nuisance tripping. This paper proposed a hybrid arc fault detection method based on the improved Mel-Frequency Ceptral Coefficients (MFCC) for preprocessing and a neural network model for arc identification called ARC_MFCC. As per the IEC 62606, twelve different loads/scenarios are considered for this research. An arc tangent-based core filter is employed to improve the MFCC to enhance the arc features within a bandwidth of 3 kHz to 7 kHz. A lightweight neural network model of fully connected cascaded with the MFCC-based preprocessing, which can distinguish the arc fault with normal operation under different test conditions. As a verification result, the ARC_ MFCC can achieve an accuracy of 99.34%. Moreover, the proposed method is implemented by Raspberry pie 4B. Test results show an average running time of about 4.2ms per sample, which Ensures that the tripping time can meet IEC 62606.

Parallel DC Arc Failure Detecting Methods Based on Artificial Intelligent Techniques

The unwanted electric discharge usually relates to arc phenomena between two connectors. The energy from an arc might fuse the electric wiring and be responsible for a fire. Various researches have been investigated for safety operations to improve detected techniques for arc diagnosis. There are two types of arc faults: parallel and series arcs. A parallel arc happens among two electrical lines, or line and ground, due to degrading insulation or contamination. On the other hand, a series arc might result from releasing connections in the wiring. The system’s current can be significantly increased by parallel arc fault compared with the series arc. In this work, the electrical behavior of the system is investigated during parallel arc faults to understand the arcing characteristics from different cases, identify electrical characteristics that are useful and reliable for the diagnosis process, and determine the location of the fault based on current or voltage of the faulted system. Eight learning techniques are adopted to detect arc fault in this study. Parallel arc signals were analyzed in the time and frequency domains, and unique characteristics of the current are extracted using Fourier analysis as an indicator for diagnosing an arc fault. This research can be used to improve arc-fault detector reliability and robustness.

Identifying DC Series and Parallel Arcs Based on Deep Learning Algorithms

Arc phenomena are usually related to the undesired disengagement of two electrical connections. The emission power discharge from the failure arc may damage wiring and can present a fire hazard. Numerous studies have been proposed to detect arc events and quickly isolate them from an electrical system. DC arc faults are often sorted into two types: series and parallel arcs. A series arc may be the outcome of discharging links in electrical wiring. By contrast, the parallel arc occurs between two electric wires, or between a link and a ground, owing to contamination or poor isolation. The currents in a system with an arc fault are considerably greater when the arc parallel in nature than when the arc is series in nature. In this paper, the electric activities of a network are investigated for the duration of series and parallel arc failures in both the time and frequency domains. The arcing behavior investigated is selected to allow for the identification of series and parallel arcs. The sorting of electrical arcs in an accurate and reliable manner is useful for electrical protection schemes. The identification process used here is based on data related to different domains, such as load current and voltage. In this study, eight learning techniques are investigated with the aim of detecting series and parallel arc faults. The arc behaviors were studied in the various domains. We used the load current and voltage characteristics as an statistic for categorizing a given arc failure. This study could be beneficial to enhance the stability and reliability of arc-fault detectors.

Series And Parallel Arc Fault Detection Based on Discrete Wavelet VS. FFT Techniques

Arc problems are most commonly caused by electrical difficulties such as worn cables and improper connections. Electrical fires are caused by arc faults, which generate tremendous temperatures and discharge molten metal. Every year, flames of this nature inflict a great lot of devastation and loss. A novel approach for identifying residential series and parallel arc faults is presented in this study. To begin, arc faults in series and parallel are simulated using a suitable simulation arc model. The fault characteristics are then recovered using a signal processing technique based on the fault detection technique called Discrete Wavelet Transform (DWT), which is built in MATLAB/Simulink. Then came db2, and one level was discovered for obtaining arc-fault features. The suitable mother and level of wavelet transform should be used, and try to compare results with conventional methods (FFT-Fast Fourier Transform). MATLAB was used to build and simulate arc-fault models with these techniques.

Research on the detection of arc fault in series connection of landscape power supply

Aiming at the series fault arc phenomenon in landscape lighting and the hidden dangers of electrical fires, in this paper, a landscape power supply series fault arc model is constructed and its model is simulated. The simulation results show that when a fault occurs, the arc current becomes smaller (almost zero) due to the increase in the impedance of the lighting circuit; this phenomenon is called the “current zero off” phenomenon of the fault arc current. The current zero off phenomenon of the fault arc current is the main fault feature in the landscape lighting circuit. In this paper, the wavelet algorithm is used to detect the fault current waveform. According to the fault characteristics, by judging whether the modulus maximum value of the wavelet coefficient has periodic characteristics with an interval of 100±15 sampling points, it is analyzed whether a series-type arc fault occurs. The built physical model verifies the feasibility and correctness of the arc detection algorithm. The research results of this paper have certain reference value for the detection and application of fault arc.

Series Arc Fault Detection of Grid-Connected PV System via SVD Denoising and IEWT-TWSVM

Series arc fault (SAF) is one of the most harmful faults during the operation of photovoltaic (PV) systems. It is a challenging task to find SAFs promptly for avoiding the PV fire. Aiming at the SAFs under different operating conditions, a novel detection algorithm by combining the Hankel singular value decomposition (Hankel-SVD) denoising method and the improved empirical wavelet transform–twin support vector machine (IEWT-TWSVM) is proposed. The Hankel-SVD algorithm is used to denoise the dc-bus current, which alleviates the influence of switching frequency and irrelevant background noise effectively. Then, the denoised current is decomposed by the IEWT, and the composite multiscale permutation entropy of each frequency band is input into the TWSVM classifier of the salp swarm optimization for completing the fault detection. The proposed algorithm not only can detect SAFs at various fault locations, but also resist dynamic shading, inverter startup, strong wind, and other interference phenomena. Moreover, the detection performance due to the arc transient process, a long-line fault, a single string array fault, a multiply string array fault, and different sampling rates of this model is verified in this study, and the corresponding results are relatively ideal. Experimental results show that the detection accuracy of the proposed method is as high as 98.10% for the measured data, which is more superior than other methods, such as wavelet decomposition, empirical mode decomposition, statistics methods including mean, standard deviation, and entropy.

Series arc fault detection based on current fluctuation and zero-current features

A series arc fault detection method based on current fluctuation features and zero-current feature fusion is proposed. In view of the problems of series arc faults, such as the strong concealment and high randomness, relatively small current amplitude easily annihilated by the load current when it occurs, and influence of the load properties, a low-voltage single-phase alternating-current (AC) series arc fault experiment platform is developed with reference to the UL1699 standard. The four-cycle current of the electric circuit is collected and the zero-current time proportional coefficient and normalized mean square error coefficient are calculated. A fuzzy logic device is then used to fuse the two coefficients to obtain the comprehensive feature identification coefficient of the series arc faults. The zero-current time proportional coefficient is combined and compared to the empirical threshold to determine whether there are series arc faults. This method has a high identification rate of 100% for series arc faults, without misjudgment or missed judgment when the GB14287.4 standard recommended load is used in the low-voltage single-phase AC power circuit.