配电网维护方法、装置、计算机设备、可读存储介质和程序产品
By using voltage sensors to calculate potential differences in the power distribution network and employing the K-nearest neighbor model to identify faults, and by adjusting the potential difference range in conjunction with load and environmental factors, rapid and accurate fault location and emergency response are achieved, thereby improving power supply quality and reducing operation and maintenance costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA SOUTHERN POWER GRID ARTIFICIAL INTELLIGENCE TECHNOLOGY CO LTD
- Filing Date
- 2024-08-16
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies make it difficult to quickly and accurately locate abnormal voltage fluctuations in the distribution network and take effective countermeasures, which affects power supply quality and increases system operation and maintenance risks and costs.
The potential difference is calculated by acquiring voltage values from voltage sensors. The trained K-nearest neighbor model is used to identify abnormal state categories, determine fault categories and locations, and perform maintenance based on fault categories and locations. The potential difference range is adjusted in combination with load conditions, network topology and environmental factors. Voltage data is transmitted using radio signals to build a communication network, automatically classify abnormal types and trigger emergency plans.
It improves the power supply quality of the distribution network, reduces the risks and costs of system operation and maintenance, and ensures the stability of the power grid and the reliability of power supply.
Smart Images
Figure CN119151712B_ABST