Page 133 - 《水资源与水工程学报》2025年第1期
P. 133

!36 "!1 #                         & ' ( ) & * + , -                               Vol.36No.1
               2025 $ 2 %               JournalofWaterResources&WaterEngineering                 Feb.,2025

            DOI:10.11705/j.issn.1672-643X.2025.01.14


                          '/ GNSS 0123456789:;


                                        <=>?@ABCDE


                                          1,2        1,2       1,2        1,2       1,2
                                  !"# , $%& , ' ( , )*+ , , -
                             (1. ?@VTL& WXWY&Z, >? ?@ 710048;2. ?@VTL& [\WT]
                                          E^_`N!-.abc, >? ?@ 710048;)

                 F G: defghijWXT]de@Nklm-I45QR, NnFopqrs(GNSS) UtdefgOim
                 -Iuvwx, yz{m|}~hi€‚ƒdem@N„…†-I。‡ GNSS z{ˆ‰ŠV‹fgŒŽ
                 €him, ‘’“x”'•fk–^k—(VMD)、 ˜™š›œ(CNN)、 žŸ ¡¢£¤œ(BiLSTM) ~
                 ¥¦§¨©(AM) mde GNSS fgz{ªˆShi–«。X¬ VMD­®fgŒ¯°±²ªˆŠV, ³´µ
                 ¶ˆ‰·¸, ‘Žz{|}; ¹¬ CNNJ›º VMDŠV3mŒ»‘¼½f¾¿, ÀÁ½ÂŒ»mÃÄ~NÃ
                 –Å; Ƭ BiLSTM–«ÇÈÉ CNN‘¼m½f¾¿, ʺžŸÀÁ½ÂŒ»mËÌ~ÍÎÏÐ, ђfgmÇ
                 ÈÒ。t“ÓÔՀ&֜m-I×z, ØÙ–ÇÚÛ(SA) Üݯ°ÞÓkl, Jß‘à–«máâ„ã~h
                 i€;BiLSTMђmäåʺ AMNæçè, äÈ¥¦§¨©¯x鑎hiäåmêë„, ÞìíîhiÒ。
                 ïðñȖ«ò¬•óWXT]dem GNSS Oiz{hi, äåôõ: S›öՀ&Ö÷Ȗ«øù, ‘’mñ
                 Ȗ«ú 3 ûüŸ(h、x、y) ýmhi€kþÿ!‘à“ 63.92%、62.06% ~ 89.10%, tWXT]de GNSS O
                 iz{kl‘"“#m$–üÝ。
                 HIJ: defg; hi–«;GNSS; ½Œhi; Հ&Ö
                 KLMNO:TU43   PQRST:A    PUVO:1672643X(2025)01012909

                      Deformationpredictionmethodsforhydraulicengineeringslopes
                             basedontheintegrationofGNSSanddeeplearning

                                                                                1,2
                                                                                             1,2
                                      1,2
                                                    1,2
                                                                 1,2
                          SONGJintao ,ANChence ,YANGJie ,MAChunhui ,TONGFei
             (1.InstituteofWaterResourcesandHydroElectricEngineering,Xi’anUniversityofTechnology,Xi’an710048,China;2.StateKey
              LaboratoryofWaterEngineeringEcologyandEnvironmentinAridArea ,Xi’anUniversityofTechnology,Xi’an710048,China)
                 Abstract:Slopedeformationpredictionisanimportantresearchfieldinslopesafetyanalysisofhydraulic
                 projects.TheGlobalNavigationSatelliteSystem(GNSS)technologyisoneofthemainapproachesfor
                 slopedeformationmonitoring,itsdataqualityandpredictionaccuracyarecrucialforslopesafetyevalua
                 tion.InresponsetotheissuesofnoiseprocessinginGNSSdataandhighprecisionpredictionofdeforma
                 tionsequences,adenoisingandpredictionmodelwasproposedbasedonvariationalmodedecomposition
                 (VMD),convolutionalneuralnetworks(CNN),bidirectionallongshorttermmemory(BiLSTM)net
                 worksandattentionmechanism(AM).Toimprovedataquality,VMDisemployedtofilteranddenoise
                 theoriginaldeformationsequence ;CNNisutilizedtoextracttimevaryingfeaturesfromtheprocessedda
                 ta,whichisthenfittedbyBiLSTMtoobtainthedeformationvaluesbasedonthehistoricalandfuturein
                 formationinofthetimeseries.Tooptimizethemodelparametersandtherebyimprovepredictionaccura
                 cy ,thesimulatedannealing(SA)optimizationalgorithmisintroducedfortheoptimalanalysisofimpor
                 tantparametersinthedeeplearningnetwork.Subsequently ,theoutputofBiLSTMmodelisprocessedin

                !"#$:20240913; %&#$:20241203
                '()*: !"#$%&'()*'(+,(52109166、52409173);!"#$%&'(-.+,(52039008);!"/0
                        123456789(GZC20232140)
                +,-.: :;<(1990—), =, >??@6, 12, ABC, D2EFG, HIJKLM@NOPQRB&S%4TU。
   128   129   130   131   132   133   134   135   136   137   138