Power transmission line icing thickness predicting method based on LSTM artificial neural network

Abstract

A power transmission line icing thickness predicting method based on an LSTM artificial neural network adopts historical icing thickness data of power transmission line poles and towers, data monitored by tensile force terminals arranged on the power transmission line poles and towers, data from real-time voltage monitoring terminal and data monitored by weather terminals, utilizes an LSTM artificial neural network algorithm technology to dynamically obtain the icing thickness on a power transmission line to be predicted according to real-time change of weather through data fusion, combines with designed borne icing thickness of the power transmission line to conduct early warning on the safety of iced poles and towers. Compared with a traditional artificial ice observing method, labor andmaterial resources are saved, better timeliness is also obtained, the fund input is smaller and the maintenance cost is lower compared with monitoring based on cameras, and power transmission line poles and towers having potential safety hazards can be found more timely.

Description

technical field [0001] The invention relates to a method for integrating transmission line conductors and ground wire ice thickness data, tension terminal monitoring data set on transmission towers, real-time voltage monitoring terminal data and meteorological terminal monitoring data in a power grid. Time series modeling of ice thickness data, and a machine learning method for predicting future ice thickness using the trained model. Background technique [0002] At present, there are very limited methods available for data collection of icing on transmission lines: artificial ice observation will consume a lot of manpower and material resources, and will cause hidden dangers to personnel safety, and the effectiveness of the data is not enough to achieve icing. Disaster prediction requirements; real-time cameras require a large amount of real-time monitoring equipment in the early stage. Since the power grid is an asset-intensive enterprise, there are too many transmission l...

AI Technical Summary

Problems solved by technology

[0002] At present, there are very limited methods available for data collection of icing on transmission lines: artificial ice observation will consume a lot of manpower and material resources, and will cause hidden dangers to personnel safety, and the effectiveness of the data is not enough to achieve icing. Disaster prediction requirements; real-time cameras require a large amount of real-time monitoring equipment in the early stage. Since the power grid is an asset-intensive enterprise, there are too many transmission lines and transmission towers, a large number of monitoring equipment will consume a lot of resources, and camera equipment is in reliability. Poor, the failure rate is high under severe weather conditions, and it will consume a lot of manpower and material resources in the later maintenance

Images