Multi-element conductor galloping early warning method based on deep learning and a related device

Abstract

The invention provides a multi-element conductor galloping early warning method based on deep learning and a related device. The method comprises the following steps: collecting related information ofa target coordinate point, wherein the related information of the target coordinate point comprises latitude and longitude, altitude, temperature, relative humidity and wind speed of the target coordinate point, sounding temperature in sounding data, and a difference value between the sounding temperature and dew point temperature; inputting the collected related information of the target coordinate points as input sample elements of a pre-trained model into the model; and obtaining a galloping early warning result which is output by the model and is used for representing whether the target coordinate point is a galloping point. According to the method, the influence of ground meteorological factors, high-altitude meteorological factors, terrains and geographic positions on power transmission line galloping is comprehensively considered, the universality and accuracy of wire icing galloping prediction are improved, and effective early warning information can be provided for power transmission line galloping under various terrain conditions of various regions in China.

Description

technical field [0001] The invention relates to the interdisciplinary technical field of electric power production and meteorological forecasting, in particular to a deep learning-based multi-element wire galloping early warning method and related devices. Background technique [0002] With global climate change, extreme weather events are showing a trend of increasing frequency and intensity, and various meteorological disasters caused by this have posed a great threat to the safety of power grid operation. Among them, galloping of transmission lines is a special meteorological disaster, which will cause line tripping, damage power equipment, cause large-scale power outages, and bring great losses to society and economy. Therefore, establishing an effective and widely applicable transmission line galloping warning and forecasting system has great practical significance to ensure the safety of power grid operation and the normal operation of society. [0003] Galloping of t...

AI Technical Summary

Problems solved by technology

In recent years, many scholars have carried out research on the prediction model of wire icing. The existing models include generalized regression neural network (GRNN), BP neural network, radial basis function (RBF) neural network, etc., but these models are only for Icing thickness is predicted without considering whether the wire gallops after icing

Images