Page 94 - 《水资源与水工程学报》2023年第1期
P. 94
9 0 & ' ( ) & * + , - 2023 $
2 VMD§<>X»/«T»Ú, ¾ô72Þ osciencesandEngineering ,2022,19(2):1633-1648.
Èi4Fô7, ¥¦)¹uÈÉ56 [12]DRAGOMIRETSKIYK,ZOSSOD.Variationalmodede
[¿, ab, ·§ª|S>X·¸ VMD»$P。 composition [J].IEEETransactionsonSignalProcessing,
2013,62(3):531-544.
( 3) »K56Þë·ßàÈÉ5Ê[¿, OP
[13]DINGJiakai,XIAODongming,LIXuejun.Gearfaultdi
È$±P¯{G
øðT»Ú56。U
agnosisbasedongeneticmutationparticleswarmoptimiza
U2 ELMAN¯ CNN-LSTMÌÎ
tionVMDandprobabilisticneuralnetworkalgorithm [J].
K»Ú56, <+[¿)³ÈÉ, ßÅ EL
IEEEAccess ,2020,8:18456-18474.
AMNÍ CNN-LSTM¢ûG
ÎK [14]ZHANGFangqim,KANGYan,CHENGXiao,etal.A
»Ú56。 hybridmodelintegratingElmanneuralnetworkwithvaria
tionalmodedecompositionandBox-Coxtransformation
©ªKL:
formonthlyrunofftimeseriesprediction [J].WaterRe
[1]Ëáá, ³ ?, !)·, ].
G_÷»¼ - E"
sourcesManagement ,2022,36:3673-3697.
- =!fÚêéMê'c_Nª|S56
[15]SIBTAINM,LIXianshan,NABIG,etal.Development
[J]. ?@3#X,2020,35(2):355-364.
ofathreestagehybridmodelbyutilizingatwostagesig
[2]l Ô,
.
c%gùeVösU|SmM
naldecompositionmethodologyandmachinelearningap
56[J]. 1Ä<ÄeÊ,2018,37(8):20-28.
proachtopredictmonthlyrunoffatSwatRiverBasin ,Pa
[3]BAJIRAOTS,KUMARP,KUMARM,etal.Potentialof
kistan[J].DiscreteDynamicsinNatureandSociety,
hybridwaveletcoupleddatadrivenbasedalgorithmsfordaily
2020,2020:7345676.
runoffpredictionincomplexriverbasins [J].Theoreticaland
[16]LIUHongchi,LIPeng,LIMeng,etal.Loadprediction
AppliedClimatology ,2021,145:1207-1231.
basedonhybridmodelofVMD-mRMR-BPNN-LSS
[4]FRAMEJ,KRATZERTF,KLOTZD,etal.Deeplearn
VM[J].Complexity,2020,2020:6940786.
ingrainfall-runoffpredictionsofextremeevents [J].Hy
[17]ZHANGGang,LIUHongchi,ZHANGJiangbin,etal.Wind
drologyandEarthSystemSciencesDiscussions ,2022,26
powerpredictionbasedonvariationalmodedecomposition
(13):3377-3392.
multifrequencycombinations[J].JournalofModernPower
[5]HEXinxin,LUOJungang,LIPeng,etal.Ahybridmodel
SystemsandCleanEnergy ,2019,7:281-288.
basedonvariationalmodedecompositionandgradientboos
[18]LIUWei,CAOSiyuan,CHENYangkang.Applicationsof
tingregressiontreeformonthlyrunoffforecasting[J].Wa
variationalmodedecompositioninseismictimefrequencya
terResourcesManagement,2020,34:865-884.
nalysis[J].Geophysics,2016,81(5):V365-V378.
[6]KUMARS,TIWARIMK,CHATTERJEEC,etal.Reservoir
[19]KIM T-Y,CHO S-B.Predictingresidentialenergy
inflowforecastingusingensemblemodelsbasedonneuralnet
consumptionusingCNN-LSTMneuralnetworks[J].En
works ,waveletanalysisandbootstrapmethod[J].WaterRe
ergy,2019,182:72-81.
sourcesManagement ,2015,29:4863-4883.
[20] HOCHREITER S,SCHMIDHUBER J.Longshortterm
[7]CHENShu,RENMiaomiao,SUNWei.Combiningtwo
memory [J].NeuralComputation,1997,9(8):1735-1780.
stagedecompositionbasedmachinelearningmethodsfor
[21]ELMANJL.Findingstructureintime[J].CognitiveSci
annualrunoffforecasting [J].JournalofHydrology,2021,
ence ,1990,14(2):179-211.
603:126945.
[22]Æ#X, $, Kä.
VMD-CNN-LSTM
[8]SAMANTARAYS,SAHOOA.Estimationofrunoffthrough
ô'Sqª|S56[J]. õ1\%ieeÊ,
BPNNandSVM inAgalpurWatershed [M]//DITZINGER
2021,37(1):1-8.
T.AdvancesinIntelligentSystemsandComputing.Berlin :
[23]LIVIERISIE,PINTELASE,PINTELASP.ACNN-LSTM
Springer,2020.
modelforgoldpricetimeseriesforecasting[J].NeuralCom
[9]HINTONGE,OSINDEROS,TEHY-W.Afastlearning
putingandApplications,2020,32:17351-17360.
algorithmfordeepbeliefnets [J].NeuralComputation,
[24]LUWenjie,LIJiazheng,LIYifan,etal.ACNN-LSTM
2006,18(7):1527-1554.
basedmodeltoforecaststockprices[J].Complexity,
[10]©2, êVs, ³ÿ4, ].
CNN-LSTMõ¬
2020,2020:6622927.
öĶÐ56[J]. Þ³,2020,41(5):37-41.
[25]MUZAFFARS,AFSHARIA.Shorttermloadforecastsu
[11]JINGXin,LUOJungang,ZHANGShangyao,etal.Run
singLSTM networks [J].EnergyProcedia,2019,158:
offforecastingmodelbasedonvariationalmodedecompo
2922-2927.
sitionandartificialneuralnetworks[J].MathematicalBi