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.

Low-voltage arc fault detection can effectively prevent fires, electric shocks, and other accidents, reducing potential risks to human life and property. The research on arc fault circuit interrupters (AFCIs) is of great significance for both safety in production scenarios and daily living disaster prevention. Considering the diverse characteristics of loads between the normal operational state and the arc fault condition, a parallel neural network structure is proposed for arc fault recognition, which is based on a convolutional neural network (CNN) and a Transformer. The network uses convolutional layers and Transformer encoders to process the low-frequency current and high-frequency components, respectively. Then, it uses Softmax classification to perform supervised learning on the concatenated features. The method combines the advantages of both networks and effectively reduces the required depth and computational complexity. The experimental results show that the accuracy of this method can reach 99.74%, and with the threshold-moving method, the erroneous judgment rate can be lower. These results indicate that the parallel neural network can definitely detect arc faults and also improve recognition efficiency due to its lean structure.

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%.

Low-voltage AC power lines are prone to arc faults, and an arc current presents as a random and complicated signal. The amplitude of the line current remains relatively unchanged during the occurrence of series arcs, hence complicating the detection of series arc faults. In this work, we developed a low-voltage series arc fault test platform to analyze the digital features of low-voltage series arc currents and the morphology of arc combustion, as the current model fails to capture the high-frequency and randomness of arc currents. An analysis of the physical causes and influencing factors of the random distribution of AC arc zero-crossing times was conducted. A time-domain simulation model for arc fault currents was developed by enhancing the time constant of the Cassie arc model, while the high-frequency features of arc currents were simulated using a segmented noise model. The measured arc current data were utilized to validate the model through the analysis of the zero-crossing time distribution of arc current, the correlation coefficient of the arc current frequency-domain signal, and the similarity of the time-domain waveforms. When comparing the similarity of the simulated waveforms of the arc model presented in this research and those of other traditional arc models, it was found that the suggested model effectively characterizes the time-/frequency-domain features of low-voltage AC series arc fault currents. The suggested model enhances the features of randomness in low-voltage AC series arc faults and is important in extracting essential aspects and reliably recognizing low-voltage series arc faults.

An arc fault is a potential hazard in power systems, capable of causing serious safety accidents such as fires. Therefore, the timely detection of arc faults and implementation of circuit-breaking measures are crucial for ensuring safety, preventing fires, and maintaining the stable operation of power systems. Although existing studies have made progress in improving the accuracy of their detection, most methods have not proposed effective solutions that address the cost-sensitive problem of feature selection. Thus, a multi-feature method is proposed by combining time-domain, frequency-domain, energy, and spatial features, which are integrated into a CBN (conditional batch normalization) convolutional neural network for detection. The experimental results show that the proposed method outperforms traditional models in terms of its accuracy and misjudgment rate while maintaining a lower computational cost, demonstrating its superior detection performance. This provides an effective improvement for arc fault detection.