On-line-fault diagnostic analysis method for extra-high-voltage-converter-station alternating current filter

Abstract

The invention provides an on-line-fault diagnostic analysis method for an extra-high-voltage-converter-station alternating current filter, and belongs to the field of alternating current filter faultanalysis. The problems that a present fault diagnosis method is high in randomness and limited in application range and is not capable of discovering faults in time are solved. The method includes thesteps that according to historical waveform data recorded by a fault recorder of an extra-high-voltage converter station, a RBF neural network is trained with the net drawing algorithm to determine model parameters of the RBF neural network, wherein the model parameters include the center, the weight and the width of the RBF neural network; according to the data recorded by the fault recorder ofthe extra-high-voltage converter station, present waveform data of the extra-high-voltage converter station is obtained, and the characteristic quantities of the present waveform data is extracted, wherein the extracted characteristic quantities include the time-domain characteristic quantity and the frequency-domain characteristic quantity; the extracted characteristic quantities are subjected tonormalization processing; the characteristic quantities after normalization processing are input into the trained RBF neural network, and whether the alternating current filter faults or not is diagnosed according to the output result of the trained RBF neural network.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of an AC filter of an UHV converter station, in particular to an online fault diagnosis and analysis method for an AC filter of an UHV converter station. Background technique [0002] The UHV converter station is a system for mutual energy conversion between DC and AC in the DC transmission system. The power transmission principle of the converter station is very different from that of the conventional AC substation. In the DC transmission system, a large amount of reactive power needs to be consumed, and at the same time, there are a large number of harmonics in the waveform after conversion. Therefore, multiple AC filter banks need to be equipped in the converter station. Due to the characteristics of high heat generation and large size, AC filter banks are usually placed in outdoor venues and are exposed to wind and sun, so they are prone to defects. When the defect reaches a certain ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the technical problems of high randomness, limited scope of application and failure to detect faults in the current fault diagnosis method for the AC filter of the UHV converter station, and to provide an online AC filter for the UHV converter station. Fault diagnosis and analysis method

Images