一种考虑高低空气象因子与地形条件影响的机器学习驱动电线覆冰预测方法、介质及程序产品
By fusing multi-source data to construct multi-dimensional feature vectors and performing spatiotemporal registration, and using machine learning models to predict icing levels, the problems of scarce samples, data source differences, and insufficient terrain effects in existing technologies have been solved, enabling reliable icing early warning and graded output for transmission line corridors.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- PUBLIC METEOROLOGICAL SERVICE CENT OF CHINA METEOROLOGICAL ADMINISTRATION
- Filing Date
- 2026-05-07
- Publication Date
- 2026-07-17
AI Technical Summary
Existing icing prediction technologies suffer from problems such as sample scarcity and imbalance, generalization instability caused by differences in data sources, insufficient representation of local topographic effects, and difficulty in balancing the operational constraints of multi-level early warning systems under the background of multi-source observation and reanalysis, making it difficult to achieve reliable prediction and representation of transmission line corridors.
By integrating ground-based low-altitude meteorological observations, multi-baric-layer reanalysis, and digital elevation model data, a multi-dimensional feature vector is constructed. Spatiotemporal registration and consistency processing are performed to establish a stable model and prediction of icing levels. Machine learning models are used for training and parameter tuning to output icing risk classification early warnings.
It improves the accuracy and stability of icing level prediction, reduces the risk of missed and false alarms, enhances cross-regional and cross-time period application capabilities, and meets the needs of power grid operation safety.
Smart Images
Figure CN122153660B_ABST