A method for fault identification of distribution network based on improved multi-class support vector machine

Abstract

A method for identifying faults of distribution network based on improved multi-class support vector machine includes such steps as collecting three-phase current and bus zero-sequence voltage simulation waveform data of main transformer low-voltage side one cycle aft fault as input signal, 2, performing wavelet decomposition processing on that input signal, and reconstructing a low-frequency component to obtain a reconstructed signal; 3, extracting the characteristic vector of the reconstructed signal by the method of obtaining the root mean square distance and the Euclidean distance; 4, constructing a multi-level support vector model, and searching the optimal parameters based on the radial basis function to obtain the trained multi-level support vector machine model; 5: inputting the feature vector of the reconstructed signal to the trained multi-level support vector machine model to obtain the fault classification. The invention is based on the improved multi-classification supportvector machine, and greatly improves the accuracy rate and the fault recognition rate of the fault classification.

Description

technical field [0001] The invention relates to the field of distribution networks, in particular to a distribution network fault identification method based on an improved multi-classification support vector machine. Background technique [0002] With the development of modern electric power, the scale of distribution network continues to expand and its structure becomes more and more complex, so various faults will inevitably occur. Accurately identifying and locating faults can effectively reduce the scope of accidental power outages and improve system operation stability. Usually, after a fault is detected, it is first necessary to identify the fault type, then select the faulty line, and then locate the faulty section. Different fault types use different fault location methods. Therefore, accurate fault identification is one of the decisive prerequisites for distribution network fault location research. Fault identification can be based on steady-state or transient el...

AI Technical Summary

Problems solved by technology

The existing multi-level support vector machines for fault identification in distribution networks are mostly built using the decision tree method, which is prone to error accumulation and is greatly affected by different decision paths, which may lead to a decrease in the recognition rate

Images