Power transmission line easy-icing micro-terrain classification method

Abstract

The invention discloses a power transmission line easy-icing micro-terrain classification method. The method comprises the following steps: collecting a regional DEM, a power grid ice region distribution diagram and regional weather station wind direction observation data; carrying out crude extraction on ridge, valley and bealock terrains; dividing a threshold value according to a TPI index, determining a slope position type of the region, and carrying out accurate extraction on valley and ridge terrains; superposing the extracted upslope terrains of the valley, the ridge, the bealock and the windward slope with the power grid ice region distribution map, and extracting a terrain region within a heavy ice region range of 20 mm or above as an easy-icing micro-terrain; extracting topographic factors of each type of topographic region easy to be iced; taking the easy-icing micro-terrain type as model output, taking a terrain factor corresponding to the micro-terrain type as an input layer, performing model training by adopting an XGBoost algorithm, and establishing an easy-icing micro-terrain classification model; therefore, the winter icing inspection of the power transmission line and deployment of anti-icing and ice-melting facilities are effectively guided, and the risk of icing disasters of a power grid is reduced.

Description

technical field [0001] The invention belongs to the technical field of hydrometeorology in electric power engineering, and in particular relates to a method for classifying micro-topography prone to icing on transmission lines. Background technique [0002] In recent years, due to the increasingly obvious trend of global warming and the frequent occurrence of extreme weather events, the probability of ice covering transmission lines in some areas has gradually increased, which has had an extremely serious impact on the safe and stable operation of high-voltage transmission lines. At the same time, the impact of icing-prone micro-topography on the icing of transmission lines is often very significant, often causing various icing disasters such as ground wire disconnection, collapse, tower tilt, galloping, and insulator flashover, which have a great impact on the regional social economy. causing varying degrees of loss. [0003] Icing-prone micro-topography usually refers to ...

AI Technical Summary

Problems solved by technology

[0004] The current identification and division methods for the micro-topography of the transmission line area mainly rely on the contour topographic map for manual identification and vectorization and field verification. The identification accuracy is high, but the labor cost is high, and it is not suitable for large-scale and large-scale regional micro-topography division. With the popularity of geographic information technology in hydrometeorological applications, there have been micro-terrain classification algorithms based on digital terrain analysis, such as methods based on image processing, methods based on terrain geometry analysis, and methods based on physical simulation of surface water.

This type of method can identify terrain features such as ridges and mountain tops to a certain extent, but there are defects such as difficult threshold division and inability to identify ice-prone areas.

Images