An On-Line Detection Method and Device of Series Arc Fault Based on Lightweight CNN

Zhi-yong, Wang; Tian, Shigang; Gao, H.; Han, Congxin; Guo, Fengyi

doi:10.1109/tii.2023.3233967

Cited by 6 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…J. Yan et al [19] built a sequential convolutional network to extract DC arc current signal characteristics. A. Tang et al [20] and Z. Wang et al [21] use 1D convolution to extract arc features of the original current signal and a fully connected neural network to classify circuit states. Likewise, R. Jiang et al [22] also use a 1D convolution to extract features of high-frequency components in current signals to identify arc faults.…”

Section: Introductionmentioning

confidence: 99%

Explainability Approach-Based Series Arc Fault Detection Method for Photovoltaic Systems

Wang,

Zhou,

Paul

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Arc fault detection devices are mandatory worldwide for mitigating DC series arc faults in photovoltaic systems. However, they are prone to nuisance tripping. Artificial intelligence-based approaches can be a solution, but they are "black boxes" and challenging to modify. This paper proposes an explainability and attention-based method to investigate the intensive details of such an algorithm. The contributions of an arc feature to the proposed model can be visualized by the proposed interpretable methodology so that insensitive arc features can be removed to reduce the quantity of input data. Additionally, the structure of the proposed model can be optimized by cutting the redundant layers. Thus, an accuracy of 99.63% is achieved with only 48.48% of the parameters compared to the original model. Finally, the optimized model is implemented by a Cortex M7-based microprocessor with a runtime of only 7.8 ms, making it ready for industrial application.

show abstract