一种风电智能电缆故障精确定位方法及系统
By employing methods such as multi-source data synchronous acquisition, temperature compensation, and multi-dimensional feature fusion, combined with wavelet packet decomposition and fuzzy neural networks, the system achieves accurate location and type identification of cable faults in wind farms. This solves the problems of large location errors, missed detections, and false detections in existing technologies and provides early warning functionality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- LIAONING XINLIAOBEI CABLE CO LTD
- Filing Date
- 2026-05-11
- Publication Date
- 2026-07-17
AI Technical Summary
Existing cable fault location technologies in wind farms suffer from large location errors, are prone to missed or misjudged faults, lack comprehensive monitoring and early warning functions for multiple physical quantities, and cannot adapt to complex environments, especially in high-resistance fault and intermittent fault scenarios where detection sensitivity is insufficient.
Multi-source data synchronous acquisition and time synchronization are adopted, and the traveling wave velocity is corrected by a second-order temperature compensation model. A multi-dimensional fault feature vector is constructed, and wavelet packet decomposition and Teager energy operator are used to identify the wavefront. Fault classification is performed by combining fuzzy neural network, and early warning function is provided through confidence assessment.
It improves the accuracy and reliability of fault location, can accurately identify different types of faults in complex environments, reduces the false judgment rate, has early warning capabilities, and adapts to the stability of different voltage levels and line lengths.
Smart Images
Figure CN122150754B_ABST