Transmission line traveling wave velocity prediction model correction method and traveling wave velocity prediction method

CN120804549APending Publication Date: 2025-10-17GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD
View PDF 0 Cites -1 Cited by

Patent Information

Application Number
CN202510626087.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-15
Publication Date
2025-10-17

AI Technical Summary

Technical Problem

In existing technologies, the estimation of traveling wave velocity in transmission lines is inaccurate, resulting in insufficient fault location accuracy, which is particularly difficult to meet engineering requirements in complex terrain or extreme working conditions.

Method used

By acquiring multi-dimensional historical data of transmission lines, extracting line feature data, constructing training and validation sets, and using the mirage algorithm to optimize the hyperparameters of the initial traveling wave velocity prediction model, the model is updated to improve prediction accuracy.

Benefits of technology

It improves the accuracy and adaptability of traveling wave velocity prediction, enhances the accuracy and adaptability of fault location, and overcomes the problems of low parameter tuning efficiency and easy getting trapped in local optima in traditional optimization methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120804549A_ABST
    Figure CN120804549A_ABST
Patent Text Reader

Abstract

The invention relates to a power transmission line traveling wave velocity prediction model correction method and a traveling wave velocity prediction method. The method comprises the following steps: acquiring historical multi-source line data of a power transmission line; performing feature extraction on the historical multi-source line data to obtain historical line feature data; constructing a training set and a verification set based on the historical line feature data; obtaining an initial traveling wave velocity prediction model, and optimizing a plurality of hyper-parameters of the initial traveling wave velocity prediction model based on a preset mirage algorithm to obtain a plurality of optimized target hyper-parameters; and updating hyper-parameters of the initial traveling wave velocity prediction model based on the plurality of target hyper-parameters, and training the updated initial traveling wave velocity prediction model based on the training set and the verification set to obtain a trained traveling wave velocity prediction model. The method is beneficial to improving the traveling wave velocity prediction accuracy.
Need to check novelty before this filing date? Find Prior Art