Machine Learning Approach to Detect Arc Faults Based on Regular Coupling Features
Machine Learning Approach to Detect Arc Faults Based on Regular Coupling Features
复制标题
DOI：
10.1109/tii.2022.3153333
复制
发表时间：
2023-03
影响因子：
12.3
通讯作者：
Run Jiang;Guanghai Bao;Q. Hong;C. Booth
中科院分区：
文献类型：
--
作者：
Run Jiang;Guanghai Bao;Q. Hong;C. Booth
在交流串联电弧故障（SAF）期间，在不同的负载组合模式和故障起始点下，电弧电流特征可能会显着变化或迅速消失。这些现象使得特征提取算法检测 SAF 变得非常具有挑战性。为了解决这些问题，本文提出了一种基于规则耦合特征（RCF）的检测模型。该模型仅通过单负载电路中的样本进行训练后，就可以检测未知多负载电路下的SAF。为了提取 RCF，通过将火线和中性线穿过电流互感器来耦合不对称磁通量。耦合信号不受多负载电路的影响。根据独特的信号，提取两个时域特征和一个频域特征来表示RCF，包括脉冲因子分析、协方差矩阵分析和多频带分析。然后，利用脉冲因子及其阈值对信号进行预处理，降低分类器的分析复杂度。最后，实验结果表明，该方法在SAF检测中的泛化能力和检测精度都有显着提高。
During ac series arc faults (SAFs), arcing current features can change significantly or vanish rapidly under different load-combination modes and fault inception points. The phenomena make it very challenging for feature-extracting algorithms to detect SAFs. To address the issues, this article presents a detection model based on regular coupling features (RCFs). After the model is only trained by the samples in single-load circuits, it can detect SAFs under unknown multiload circuits. To extract the RCFs, asymmetric magnetic flux is coupled by passing the live line and the neutral line through the current transformer. The coupling signals are not influenced by the multiload circuits. According to the unique signals, two time-domain features and one frequency-domain feature are extracted to represent the RCFs, including impulse-factor analysis, covariance-matrix analysis, and multiple frequency-band analysis. Then, the impulse factor and its threshold are used to preprocess the signals and decrease analysis complexity for the classifier. Finally, the experimental results show that the proposed method has significantly improved generalization ability and detection accuracy in SAF detection.