Fast Breakdown Diagnosis in Vacuum Based on Zynq SoC With Softmax

Breakdown diagnosis has a guidance for conditioning design, which could improve the vacuum interrupter (VI) insulation ability. This article proposed a fast breakdown diagnosis in vacuum based on Zynq system-on-chip (SoC) with Softmax. The Softmax model is trained by prebreakdown current waveforms, and the weights of Softmax model for breakdown mechanism are obtained. The Zynq SoC with Softmax for fast breakdown diagnosis is designed based on the obtained weights. Three groups of prebreakdown current waveforms are obtained for breakdown diagnosis based on Zynq SoC with Softmax. The results show that the accuracies are 84%, 89.01%, and 89.72%, respectively. The precision, recall, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${F}1$ </tex-math></inline-formula>-score are higher than 84%, which verify the effectiveness. One breakdown diagnosis is within 1 ms by Zynq SoC with Softmax. The fast breakdown diagnosis based on Zynq SoC with Softmax is of high accuracy, high effectiveness, and high efficiency, which can have a promising application in engineering.