A fault area diagnosis method and system for AC/DC hybrid power grid based on LSTM

Abstract

The invention belongs to the technical field of electric power system transmission safety, and discloses an LSTM-based method and system for diagnosing a fault area of ​​an AC / DC hybrid power grid. Including: building a power system time-domain simulation model to simulate various working conditions to obtain the voltage amplitude of the entire network node and the corresponding label to obtain the basic sample set; using the sliding window method to intercept the basic sample to obtain the sample set for training the fault time judgment model and the fault area judgment model Carry out training and properly adjust the relevant parameters of the model; input the samples at the current sliding window time, the fault time judgment model judges whether a fault occurs, and if a fault is confirmed, input the samples into the fault area judgment model to obtain the fault location; finally output the current fault diagnosis information. The invention uses a deep neural network to quickly and effectively determine the time of fault occurrence in the power grid and determine the fault area, has better performance under different operating conditions and certain noise conditions, and can meet the needs of fault diagnosis in complex power systems.

Description

technical field [0001] The invention belongs to the technical field of electric power system transmission safety, and more specifically relates to an LSTM-based method and system for diagnosing a fault region of an AC / DC hybrid power grid. Background technique [0002] Fast and accurate fault diagnosis of power system after a fault occurs is of great significance for clearing faults, restoring power supply and maintaining system stability. With the large-scale access of the DC system, the AC-DC coupling of my country's power grid is becoming increasingly tight, and the failure of the AC system can easily cause commutation failure or even blockage of the DC system, thereby affecting the stability of the power system. The traditional diagnosis method based on the relay protection of AC system is difficult to be directly applied to the AC-DC hybrid power grid for effective fault diagnosis. Due to the nonlinearity of the DC system and the complexity of DC control in the AC-DC h...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the defects of the prior art, the purpose of the present invention is to provide an LSTM-based method and system for diagnosing fault areas of AC / DC hybrid power grids, aiming to solve the problem that existing power system fault diagnosis methods rely on expert knowledge and experience and require manual screening It is difficult to set the effective characteristics and model parameters, and it cannot be effectively applied to the AC-DC hybrid power grid, thus affecting the technical problems of the accuracy of fault diagnosis

Images