Power transmission line fault type identification method based on deep learning LSTM model

Abstract

The invention discloses a power transmission line fault type identification method based on a deep learning LSTM model. The method specifically comprises the steps: obtaining a three-phase fault current sampling sequence after a power transmission line has a fault; making a data set containing a plurality of samples, wherein each sample contains a three-phase current sampling sequence and a faulttype label corresponding to a power transmission line fault; establishing a power transmission line fault classification model based on a deep learning LSTM network, and performing forward propagationoutput; performing back propagation training on the model through a loss function; verifying, testing and storing the power transmission line fault classification model obtained by training; and taking the three-phase fault current sampling sequence of the power transmission line to be subjected to fault classification as the input of the model so as to obtain the fault type. According to the method, the limitation that features are difficult to extract in the conventional power transmission line fault classification algorithm can be overcome, and the method has better performance and is notaffected by factors such as fault positions, fault resistance and initial phases.

Description

technical field [0001] The invention relates to the field of transmission line fault identification, in particular to a transmission line fault type identification method based on a deep learning LSTM model. Background technique [0002] The rapid development of the power system has led to the fact that the number and total length of transmission lines are now increasing to a large extent. Due to the characteristics of large spans, long distances, and strong influences from harsh environments and weather, transmission lines play an important role in the stability of the entire power system. However, during the operation of the power system, some transmission lines will inevitably appear Various glitches. If the transmission line fails and cannot be eliminated in time and effectively, it will have a great impact on the entire power system. At the least, it will reduce the reliability of the power supply of the power grid, cause power plants to freeze, cause local power sup...

AI Technical Summary

Problems solved by technology

[0004] However, in practical applications, due to the interference of various factors, it is difficult for these traditional feature extraction algorithms to extract the features of complex transmission line faults, and the feature extraction of transmission line faults not only depends on various forms of mathematical models, but also with It is related to the corresponding professional experience of the analyst, so there are problems of cumbersome process and low recognition accuracy in application

Images