Series Arc Fault Identification Method Based on Lightweight Convolutional Neural Network

Arc faults in electric circuits are recognized as an important cause of fire. The first Arc Fault Circuit Interrupter (AFCI) has been patented in 1980 in the United States. AFCI is a device designed to detect electric arc faults which was prescribed for use by the National Electric Code (NEC, US Wiring Regulation) in January 2008. The NEC describes it as ‘A device intended to provide protection from the effects of arc faults by recognizing characteristics unique to arcing and by functioning to de-energize the circuit when an arc fault is detected’. At the beginning of 2012 the Arc Fault Detection Device (AFDD) began to be introduced into the IEC world, culminating in the publication of Technical Product Standards IEC 62606 ' in August 2013, which sets out the requirements for arc fault protection devices. This paper underlines the importance of preventing electrical fires by using the new technology of AFDDs, which largely extend the protection offered by traditional circuit breakers like MCBs and RCDs. Product standard IEC 62606 and functional tests are reviewed, the functioning of AFDDs is explained and a method to design robust algorithms for arc fault detection is proposed.

Smart detection technology of serial arc fault on low-voltage indoor power lines

Arc fault detection and identification via non-intrusive current disaggregation

Arc faults can cause a severe electric fire, especially series arc faults. Artificial intelligence (AI)-based arc fault detection methods can have a boasted detection accuracy. However, the complexity and large parameter quantity of the AI-based algorithm will hinder its real-time performance for detecting series arc faults. This paper proposes a lightweight arc fault detection method based on the EffNet module, which can make the algorithm less complex with the same detection accuracy level. An arc fault test platform was constructed to collect arc current data, covering eight types of loads required by the IEC 62606 standard. The raw arc current data are used directly as an input for the proposed algorithm, reducing the module’s complexity. According to features of arc current mainly represented in the time domain, the first and last convolution layers of the EffNet module can be improved. Additionally, the spatially separable convolution is well-tuned and trimmed to achieve a more lightweight and better-performance architecture for arc fault detection called Arc_EffNet. Remarkably, this model achieves an impressive arc detection accuracy of 99.75%. An arc fault detection prototype was built using the Raspberry Pi 4B to evaluate the real-time detecting performance of the proposed method. The experimental results show that the prototype takes a time of about 72 ms to respond to a series arc fault, which can fulfill the requirement of real-time detection for arc faults.

Arc fault is one of the most critical reasons for electrical fires. Due to the diversity, randomness and concealment of arc faults in low-voltage circuits, it is difficult for general methods to protect all loads from series arc faults. From the analysis of many series arc faults, a large number of high frequency signals generated in circuits are found. These signals are easily affected by Gaussian noise which is difficult to be eliminated as a result of frequency aliasing. Thus, a novel detection algorithm is developed to accurately detect series arc faults in this paper. Initially, an autoregressive model of the mixed high frequency signals is modelled. Then, autoregressive bispectrum analysis is introduced to analyze common series arc fault features. The phase information of arc fault signal is preserved using this method. The influence of Gaussian noise is restrained effectively. Afterwards, several features including characteristic frequency, fluctuation of phase angles, diffused distribution and incremental numbers of bispectrum peaks are extracted for recognizing arc faults. Finally, least squares support vector machine is used to accurately identify series arc faults from the load states based on these frequency features of bispectrum. The validity of the algorithm is experimentally verified obtaining arc fault detection rate above 97%.

Convolutional neural networks (CNNs) have achieved significant accuracy improvement in many intelligent applications at the cost of intensive convolution operations and massive data movements. To efficiently deploy CNNs on low power embedded platforms in real time, the depthwise separable convolution has been proposed to replace the standard convolution, especially in lightweight CNNs, which remarkably reduces the computation complexity and model size. However, it is difficult for a general convolution engine to obtain the theoretical performance improvement as the decreased data dependency of depthwise convolution significantly reduces the data reuse opportunity. To address this issue, a flexible and highperformance accelerator based on FPGA is proposed to efficiently process the inference of both large-scale and lightweight CNNs. Firstly, by sharing the activation dataflow between the depthwise convolution and pooling layers, the control logic and data bus of the two layers are reused to maximize the data utilization and minimize the logic overhead. Furthermore, these two layers can be processed either directly after standard convolutions to eliminate the external memory accesses or independently to gain better flexibility. Thirdly, a performance model is proposed to automatically explore the optimal design options of the accelerator. The proposed hardware accelerator is evaluated on Intel Arria 10 SoC FPGA and demonstrates state-of-the-art performance on both large-scale CNNs, e.g., VGG, and lightweight ones, e.g., MobileNet.

Series Arc Fault (SAF) is the failure that occurs between any electrical contact and any electrical circuitry. However, it considered one of the common malfunctions that affect the operation of the PV system and causes serious problems such as fires and electrical shock hazards. Several reasons increase the possibility of this type of failures, such as incorrect installation, irregular maintenance, and some environmental effects. This paper presents a new intelligent and accurate detection method of SAF in the PV system. In this method, Convolutional neural networks (CNN) which is a discriminative (supervised) deep learning algorithm used for the process of fault detection. In typical cases, the signal consists of DC component, inverter component and noise of Network. In the case of SAF, a new part will add to the signal; therefore, CNN used to discriminate against the additional component to detect the SAF accurately. PSCAD is used to generate the Arc fault model; Performance evaluation and the results of the proposed method implemented using Python. The achieved accuracy of the proposed detection method is 98.9%.

Series Arc Fault (SAF) can be defined as the failure that occurs between any electrical contact and any electrical circuitry. However, it considered one of the common failures that affect the operation of the PV system and causes serious problems such as fires and electrical shock hazards. Several reasons increase the possibility of this type of failures such as incorrect installation, irregular maintenance, and some environmental effects. This paper presents a new intelligent and accurate detection method of SAF in the PV system. In this method, Convolutional neural networks (CNN) which is a discriminative (supervised) deep learning algorithm used for the process of fault detection. In normal cases, the signal consists of DC component, inverter component and noise of Network. In the case of SAF, a new component will add to the signal; therefore, CNN used to discriminate against the new component to accurately detect the SAF. PSCAD is used to generate the Arc fault model; Performance evaluation and the results of the proposed method implemented using Python. The achieved accuracy of the proposed detection method is 98.9%. .

This paper aims at providing a reliable algorithm to identify photovoltaic (PV) series arc faults regardless of complex fault-like interferences. Through conducting various arc fault experiments with different PV current levels, arc gap lengths, and load types, PV series arc fault features have been understood comprehensively. To avoid unwanted nuisance tripping, fault-like conditions are analyzed to confirm the unique arc fault features. Based on the loop current signature, a greater unstable fluctuation in the time domain and extra arc noises in the time-frequency domain are chosen as identification features. By quantificational evaluations, optimal detection variables with the Hamming window and the proper time resolution have been established to achieve the best identification results. By building fusion coefficients, two variables are arithmetically fused to achieve the arc fault discovery. The algorithm could also classify fault-like into normal and adjust the threshold value dynamically to fit different normal current levels. Its validity has been verified by experimental results on the simulated platform.

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

Arc fault is the arc that may cause damage to the society. Arc is with high temperature and massive heat. If arc fault appears in the low voltage supply environment, it will lead to fire or disaster. So detection and protection of arc fault is essential. In order to prevent the damage of fault arc, a new apparatus named Arc Fault Circuit Interrupter (AFCI) has been proposed. In the paper, arc fault features of the circuit with different load are studied. Then an arc fault detection method is proposed. Then a low cost AFCI is designed so as to promote AFCI. Experimental results show it has the ability to protect the arc fault.

A double ended AC series arc fault location algorithm for a low-voltage indoor power line using impedance parameters and a neural network

In order to improve the accuracy of series arc fault detection and prevent fire accidents caused by series arc fault, a series arc fault simulation experiment circuit was built to obtain the low-frequency and high-frequency current waveform of series arc fault under different loads. The kurtosis, waveform factor, crest factor, pulse factor, and margin factor of low-frequency current waveform are extracted in the time domain. In the frequency domain, a method based on variational mode decomposition and energy entropy is proposed to extract the characteristic quantity of series arc faults. It was found that the energy entropy of the intrinsic mode function component with the largest variance contribution ratio will increase when a series of arc faults occur, and it was used as a characteristic quantity. Characteristic vectors were constructed based on time–frequency characteristic quantities, and the characteristic vector was trained based on the random forest algorithm to obtain the diagnosis model and analyze the series arc fault diagnosis. The analysis showed that the diagnostic accuracy of the model trained by the proposed method was above 97%, and the fault recognition effect was remarkable, which provides an important reference for the improvement of the series arc fault detection technology.

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.

In this study, a lightweight convolutional neural network (CNN) is employed to identify Lamb modes. The proposed approach consists of five convolutional and pooling layers, then a fully-connected layer and a sigmoid layer. In which, the first convolutional layer is a wide-scale kernel. Lamb wave responses based on froward modelling are obtained for different plate materials (aluminium, steel and titanium), different excitation frequencies (250 kHz, 500 kHz), and different excitation cycles (4-cycle, 5-cycle). 16800 Lamb wave samples labelled by ‘A0 mode’ and ‘S0 mode’ are beforehand and hosted in a database, then trained via the lightweight CNN. In validation process, the lightweight CNN reaches 100% accuracy. The performance of light-weight CNN is also compared with some popular networks. Now, the well-trained network can be used to identify Lamb mode. Some responses are stimulated by ABAQUS under different excitation signal, different propagating distance, different plate material, and the predicted results via the lightweight CNN are all right. In addition, the extensibility of the network is validated by identifying new-converted Lamb mode correctly.