一种供电网络跳闸故障定位方法及系统
By combining discrete wavelet transform and neural networks, the problems of accuracy and real-time performance in fault location in complex power grid environments have been solved, achieving high-precision and fast-response fault location and improving the reliability and efficiency of power grid operation and maintenance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING QIANGZE ELECTRIC CO LTD
- Filing Date
- 2025-06-11
- Publication Date
- 2026-07-17
AI Technical Summary
Existing fault location technologies lack accuracy and real-time performance in complex power grid environments, and have excessively high requirements for time synchronization and data quality, making it difficult to achieve efficient fault location in high-noise and asynchronous data environments.
Discrete wavelet transform is used to extract high-frequency transient components, combined with cubic spline interpolation to calibrate timestamps, and fused with traveling wave analysis and fully connected neural networks. Through wavelet packet decomposition and least squares optimization methods, a comprehensive fault location report is generated and scheduling instructions are generated.
It significantly improves the accuracy and robustness of fault location, enabling rapid response and high-precision fault location in high-noise, multi-branch power grid environments, meeting the reliability and efficiency requirements of modern smart grids.
Smart Images
Figure CN120559386B_ABST