基于GRNN的特高壓直流輸電線路故障識(shí)別方法

打開文本圖片集

關(guān)鍵詞：廣義回歸神經(jīng)網(wǎng)絡(luò)；特高壓直流輸電線路；繼電保護(hù)；廣義S變換；故障識(shí)別DOI：10.15938/j. jhust.2025.02.014中圖分類號(hào)：TM723 文獻(xiàn)標(biāo)志碼：A 文章編號(hào)：1007-2683（2025）02-0131-09

Abstract：Aprotection methodforultra-highvoltage directcurenttransmisson linesbasedongeneralizedregressonneural network（GRNN）isproposedtoaddresstheisuesofeasyrejectionandlongfault detectiontimeinultra-highvoltagedirectcurrent protection.FirstlyasedonthegneralizedStransfo，thefaultcharacterisiciformationintefrequencydomainistaindto constructhe input data for GRNN.Secondly，thechaosquantum particleswarm optimization（CQPSO）algorithm isused tooptimize theparametersofthegeneralizedregressonneuralnetwork，foranidealnetworkmodelbasedontheprincipleofthelowestfinss function，andbeterlathultcharacterissofthulra-hghvageDCtrasmssonlne.TeSofaxlasifierisuiledto clasifydep-levelfeatures，dentifingfaultsasexteal，us，orlinefults，andpolarizingtemintopositive，negative，orbipolar faults，thenoutpuigrecogitioesultsinally，heultra-higagediecturnt tasmissnodelbuiltineCA/C simulatioenvronmentisvalidated，andtevadationresultsshowedthattheproposedmethodhasgoodpeformanceinfaultetection andfaultpoleselectionofultra-highvoltagedirectcurenttransmissionlinerelaprotectionComparedtotradionalonolutional neuralnetwoks，generalizedregressionneuralnetworks，upportvectormacines，andotermethods，thefultrecognitionacyof the proposed method in this paper has been improved by 6.6% ， 0.65% ，and 7.69% ，respectively，meeting the requirements of protection speed and reliability.

Keywords：generalizedregressonneuralnetwork；UHVDCtransmissionline；relayprotection；generalizedS-transform；faulti dentification

0 引言

隨著新型電力系統(tǒng)建設(shè)的推進(jìn)，特高壓直流輸電由于其傳輸容量大、傳輸距離遠(yuǎn)、線路損耗少等顯著優(yōu)勢(shì)，可以很好地接入分布式電源和儲(chǔ)能裝置，進(jìn)而推進(jìn)我國“雙碳”目標(biāo)，故研究特高壓直流輸電技術(shù)已經(jīng)成為熱點(diǎn)。（剩余13451字）