BP neural network-based power transmission line leakage current prediction method and system, and storage medium

Abstract

The invention discloses a BP neural network-based power transmission line leakage current prediction method and system, and a storage medium. The method comprises the steps that the air relative humidity, the temperature difference and whether rainfall exists in the current environment of a line to be predicted or not are acquired to serve as feature input quantity, the feature input quantity is input into a trained BP neural network model in the corresponding time period according to the current prediction time, and a leakage current predicted value is output. The operation data obtained by different lines are classified according to seasons and are respectively used for the training process of the neural network model, so that the influence caused by pollution changes of different regions and different seasons in the prediction process is eliminated.

Description

technical field [0001] The present invention relates to the technical field of leakage current prediction of transmission lines, in particular to a method, system and storage medium for prediction of leakage current of transmission lines based on BP neural network. Background technique [0002] The pollution accumulated on the surface of insulators may cause flashover under wet conditions, and then cause pollution flashover accidents. Due to the low success rate of accident reclosing caused by pollution flashover, it is easy to cause the system to lose stability, and then cause large-scale power outages, which have a significant impact on the safety of people's lives and properties. At present, the problem of atmospheric environmental pollution in my country is still very serious, and with the continuous improvement of the voltage level of transmission lines, pollution flashover accidents are still a problem that cannot be ignored in maintaining the safe and stable operation...

AI Technical Summary

Problems solved by technology

[0008] (1) The leakage current value measured by the existing leakage current prediction method is easily affected by factors such as region and environment. On the one hand, the measurement test is often not repeatable; The conclusions obtained from the data are difficult to apply in other regions, and the reference is not good

[0009] (2) The existing leakage current prediction methods consider the factors that affect the leakage current relatively single, but the factors that affect the leakage current of transmission lines are various, and changes in temperature, humidity, air pressure and other factors will cause a large leakage current Variety

Images