Wang Ningfang, Wang Yujia, Zhang Yifei, Tang Ci, Sun Chenhao
School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha 410114, China.
International College of Engineering, Changsha University of Science & Technology, Changsha 410114, China.
Sensors (Basel). 2025 Jun 25;25(13):3960. doi: 10.3390/s25133960.
With the rapid advancement of digitalization and intelligence in power systems, SF high-voltage circuit breakers, as the core switching devices in power grid protection systems, have become critical components in high-voltage networks of 110 kV and above due to their superior insulation performance and exceptional arc-quenching capability. Their operational status directly impacts the reliability of power system protection. Therefore, real-time condition monitoring and accurate assessment of SF circuit breakers along with science-based maintenance strategies derived from evaluation results hold significant engineering value for ensuring secure and stable grid operation and preventing major failures. In recent years, the frequency of extreme weather events has been increasing, necessitating a comprehensive consideration of both internal and external factors in the operational status prediction of SF high-voltage circuit breakers. To address this, we propose an operational status assessment model for SF high-voltage circuit breakers based on an Integrated Attribute-Weighted Risk Model Based on the Branch-Trunk Rule (IAR-BTR), which integrates internal and environmental influences. Firstly, to tackle the issues of incomplete data and feature imbalance caused by irrelevant attributes, this study employs missing value elimination (Drop method) on the fault record database. The selected dataset is then normalized according to the input feature matrix. Secondly, conventional risk factors are extracted using traditional association rule mining techniques. To improve the accuracy of these rules, the filtering thresholds and association metrics are refined based on seasonal distribution and the importance of time periods. This allows for the identification of spatiotemporally non-stationary factors that are strongly correlated with circuit breaker failures in low-probability seasonal conditions. Finally, a quantitative weighting method is developed for analyzing branch-trunk rules to accurately assess the impact of various factors on the overall stability of the circuit breaker. The DFP-Growth algorithm is applied to enhance the computational efficiency of the model. The case study results demonstrate that the proposed method achieves exceptional accuracy (95.78%) and precision (97.22%) and significantly improves the predictive performance of SF high-voltage circuit breaker operational condition assessments.
随着电力系统数字化和智能化的快速发展，SF高压断路器作为电网保护系统中的核心开关设备，凭借其卓越的绝缘性能和出色的灭弧能力，已成为110 kV及以上高压电网中的关键部件。其运行状态直接影响电力系统保护的可靠性。因此，对SF断路器进行实时状态监测、准确评估，并根据评估结果制定科学的维护策略，对于确保电网安全稳定运行、预防重大故障具有重要的工程价值。近年来，极端天气事件的发生频率不断增加，在SF高压断路器运行状态预测中需要综合考虑内部和外部因素。为此，我们提出了一种基于基于分支-主干规则的综合属性加权风险模型（IAR-BTR）的SF高压断路器运行状态评估模型，该模型整合了内部和环境影响因素。首先，为解决由无关属性导致的数据不完整和特征不平衡问题，本研究对故障记录数据库采用缺失值消除（删除法）。然后根据输入特征矩阵对所选数据集进行归一化处理。其次，使用传统关联规则挖掘技术提取常规风险因素。为提高这些规则的准确性，基于季节分布和时间段的重要性对过滤阈值和关联度量进行优化。这使得能够识别在低概率季节条件下与断路器故障密切相关的时空非平稳因素。最后，开发了一种定量加权方法来分析分支-主干规则，以准确评估各种因素对断路器整体稳定性的影响。应用DFP-Growth算法提高模型的计算效率。案例研究结果表明，所提出的方法具有出色的准确率（95.78%）和精确率（97.22%），并显著提高了SF高压断路器运行状态评估的预测性能。
