巷道围岩变形的神经网络模型Model of Neural Network Forecasting the Deformation of Surrounding Rock in Tunnel
盛建龙,赵建海
摘要(Abstract)：
巷道围岩变形是巷道稳定性最直接判据,预测巷道围岩变形为选择支护方案提供有力的依据。巷道围岩变形的影响因素非常复杂,具有不确定性,而神经网络不仅能考虑定量因素,而且能考虑定性因素,因此神经网络适用于解决变形预测问题。系统分析了影响巷道围岩变形的因素,构建了巷道围岩变形预测的神经网络模型,经过改进的网络模型具有较好的收敛性和稳定性。
关键词(KeyWords)： 神经网络模型;巷道围岩变形;岩体工程;影响因素
基金项目(Foundation):
作者(Author): 盛建龙,赵建海
参考文献(References)：
- [1] 王同旭,秦忠诚,时连强.围岩变形的时间性与支护作用原理[J].矿山压力与顶板管理,2001,(4):6~7.
- [2] 汤劲松,乔春生.隧道锚喷支护设计的神经元网络方法[J].中国公路学报,2002,15(3):68~72.
- [3] 王德润,谢广祥,孟祥瑞,等.基于神经网络的综放回采巷道支护设计[J].矿业安全与环保,2003,30(2):15~17.
- [4] 葛宏伟,梁艳春,刘 玮,等.人工神经网络与遗传算法在岩石力学中的应用[J].岩石力学与工程学报,2004,23(9):1542~1550.
- [5] 邢福东,朱珍德,刘汉龙,等.高围压高水压作用下脆性岩石强度变形特性试验研究[J].河海大学学报,2004,32(2):184~187.
- [6] SimonHaykin.神经网络原理———AComprehensiveFoundation[M].北京:机械工业出版社,2004.
- [7] 彭苏萍,孙连英,马春丽.地下开采岩体变形综合分析方法及其应用[J].中国矿业大学学报,2002,31(1):80~83.
- [8] 汤连生,王思敬.水岩化学作用对岩体变形破坏力学效应研究进展[J].地球科学进展,1999,14(5):433~439.
- [9] 吴兴春,王思敬,丁恩保.岩体变形模量随深度的变化关系[J].岩石力学与工程学报,1998,17(5):487~492.
- [10] 沈明荣,石振明,张 雷.不同加载路径对岩石变形特性的影响[J].岩石力学与工程学报,2003,22(8):1234~1239.
- [11] 孙玉科.岩体结构力学———岩体工程地质力学的新发展[J].工程地质学报,1997,15(4):291~294.
- [12] 冯夏庭,张志强,盛 谦,等.三峡工程永久船闸三闸首区开挖变形特征的智能分析[J].岩石力学与工程学报,2001,20(5):633~637.
- [1] WANGTongxu,QINZhongcheng,ShiLianqiang.TheTime—DependentDeformationandSupportingPrincipleforSurroundingRock[J].GroundPressure&StrataControl,2001,(4):6~7.
- [2] TANGJinsong,QIAOChunsheng.MethodofArtificialNeuralNetworkforBolt shotcreteSupportDesigninTun nels[J].ChinaJournalofHighway&Transport,2002,15(3):68~72.
- [3] WANGRunde,XIEGuangxiang,MENGXiangrui,etal.SupportDesignofStopeRoadwayinFullyMechanizedCavingFaceBasedonNeuralNetwork[J].MiningSafety&EnvironmentalProtect,2003,30(2):15~17.
- [4] GEHongwei,LIANGChunyan,LIUWei.ApplicationsofArtificialNeuralNetworksandGeneticAlgorithmstoRockMechanics[J].ChineseJournalofRockMechanics&Engineering,2004,23(9):1542~1550.
- [5] XINGFudong,ZHUZhende,LIUHanlong, etal.Ex perimentalStudyonStrengthandDeformationCharacter isticsofBrittleRocksunderHighConfiningPressureandHydraulicPressure[J].JournalofHehaiUniversity(NaturalSciences),2004,32(2):184~187.
- [6] SimonHaykin.NeuralNetworkPrinciple———ACompre hensiveFoundation[M].Beijing:ChinaMachinePress,2004.
- [7] PENGSuping,SUNLianying,MAChunli.SyntheticalA nalysisMethodofRockMovementinUndergroundMiningandCaseStudy[J].JournalofChinaUniversityofMin ingandTechnology,2002,31(1):80~83.
- [8] TANGLiansheng,WANGSijing.ProgressintheStudyonMechanicalEffectoftheChemicalActionofWater rockonDeformationandFailureofRocks[J].AdvanceinEarthSciences,1999,14(5):433~439.
- [9] WUXingchun,WANGSijing,DINGEnbao.RelationshipBetweenRockMassDeformabilityModulusandtheDepth[J].ChineseJournalofRockMechanics&Engineering,1998,17(5):487~492.
- [10] SHENMinrong,SHIZhenming,ZHANGLei.Deforma tionPropertiesofSamplesunderDifferentLoadingPaths[J].ChineseJournalofRockMechanics&Engineer ing,2003,22(8):1234~1239.
- [11] SUNYuke.RockMassStructuralMechanism———ANewAdvanceinRockEngineeringGeologicalMechani cas[J].JournalofEngineeringGeology,1997,15(4):291~294.
- [12] FENGXiating,ZHANGZhiqiang,SHENGQian, etal.IntelligentAnalysisofDeformationBehaviorsofPerma nentShiplockoftheThreeGorgesProject[J].Chi neseJournalofRockMechanics&Engineering,2001,20(5):633~637.