Adaptive Critical Cost-Sensitive Detection of High-Impedance Faults Based on Impedance Criticality

High-impedance fault (HIF) in distribution networks is notoriously difficult to detect, as its high impedance results in weak fault currents that evade conventional protection schemes. In addition, for both HIF and non-HIF samples, the impact of critical samples on the detection rules is regarded as more important than that of non-critical samples. Therefore, a critical cost-sensitive factor distribution (CCFD) method based on impedance criticality is proposed in this study. A higher cost factor is assigned to critical samples than to non-critical samples. To better learn from the misclassified samples and reduce the interference of anomalous samples, an adaptive critical cost-sensitivity factor distribution (ACCFD) method is further proposed. During model training, the distribution factors of consecutively misclassified and correctly classified samples within the critical sample set are adaptively adjusted to optimize the detection rules. Experiments are conducted on a 10 kV distribution network simulation model and a field experiment platform. The results demonstrate that the proposed ACCFD method exhibits high classification accuracy and excellent generalization ability, effectively enhancing the reliability and security of power grids.