简介:ThedesignofanOLAPsystemforsupportingreal-timequeriesisoneofthemajorresearchissues.Oneapproachistousedatacubes,whicharepre-computedmultidimensionalviewsofdatainthedatawarehouse.Aninitialsetofdatacubescanbederived.fromwhichtheanswertoeachfrequentlyaskedquerycanberetrieveddirectly.However,therearetwopracticalproblemsconcerningthedesignofacubebasedsystem:1)themaintenancecostofthedatacubes,and2)thequerycosttoansweraselectedsetoffrequentlyaskedqueries.MaintainingadatacuberequiresdiskstorageandCPUcomputation,Sothemaintenancecostisrelatedtothetotalsizeofthedatacubesmaterialized,andthuskeepingalldatacubesisimpractical.Thetotalsizeofcubesmaybereducedbymergingsomecubes.However,theresultinglargercubeswillincreasethequerycostofansweringsomequeries.Iftheboundsonmaintenancecostandquerycostarestrict.someofthequeriesneedtobesacrificed.Anoptimizationproblemindatacubesystemdesignhasbeendefined.Withamaintenance-costboundandaquery-costboundgivenbytheuser,itisnecessarytoopti-mizetheinitialsetofdatacubessuchthatthesystemcanansweramaximumnumberofqueriesandsatisfythebounds.ThisisanNP-completeproblem.ApproximatealgorithmsGreedyRemoving(GR)and2-GreedyMergingwithMultiplepaths(2GGM)areproposed.Experimentshavebeendoneonacensusdatabaseandtheresultsshowthatourapproachinbotheffbctiveandefficient.
简介:这份报纸的目的是在设计下面并且离开设计条件改进最后阶段汽轮机和一台600MW蒸气汽轮机的exhaust兜帽的空气动力学的表演。在操作期间,在汽轮机和exhaust兜帽之间的强壮的流动相互作用在兜帽在流动行为上强加影响并且导致汽轮机的不能令人满意的空气动力学的表演并且用尽兜帽。exhaust兜帽因此有潜力以空气动力学的效率被改善。就在汽轮机和exhaust兜帽之间的流动相互作用而言,更弥漫的结束墙的侧面被优化。联合模型汽轮机和模型用尽兜帽计算和实验被执行验证优化的效果。模型实验证明设计修正导致了全面压力恢复系数的实质的增加。流动和空气动力学的表演照原尺寸最后一台阶段汽轮机并且照原尺寸用尽兜帽被模仿探索流动物理改变到更弥漫的几何学的修正。湿蒸气作为流动媒介被选择。在不同操作条件下面的实际流动地被分析。
简介:Thispaperpresentsthedesignandsimulationofseveralfixed-tunedsub-harmonicmixerscoverfrequenciesfrom110GHto130GHz,215GHto235GHz,310GHto350GHz,and400GHto440GHz.Amongthem,120GHz,225GHz,330GHzsubharmonicmixersaredesignedwithflip-chippedplanarschottkydiodemountedontoasuspendedquartz-basedsubstrate,the225GHzand425GHzsubharmonicmixersareGaAsmembraneintegrated,andthe115GHzsubharmonicmixerhasbeenfabricatedandtestedalready.
简介:Abroadbandreflectivepolarizationconverterisproposed.Theunitcellofpolarizationconverteriscomposedofasingle-splitresonantring,adouble-splitresonantring,adielectricsubstrateandametallicground.Thesimulatedresultsshowthatthepolarizationconvertercanconvertx-polarizedwavesintoy-polarizedwavesandobtainabroadbandpolarizationconversionfrom0.5010THzto1.3900THzwiththepolarizationconversionratio(PCR)beyond80%atnormalincidence.Moreover,thesurfacecurrentdistributionsareinvestigatedtoexplainthepolarizationconversionmechanism.Finally,agoodagreementisachievedbetweensimulatedandmeasuredresults.Thepolarizationconvertercanbeappliedinterahertzimaging,communicationandstealthytechnology.
简介:我们在场为电可擦可编程只读存储器记忆的一个新感觉放大器电路。感觉放大器的拓扑学使用察觉到方法的电压,有象高可靠性一样的低成本和低动力消耗量。感觉放大器在与嵌入的电可擦可编程只读存储器处理的一个SMIC0.35-μm2P3M互补金属氧化物半导体认识到的一个电可擦可编程只读存储器被实现。在电力供应是3.3V的条件下面,模拟结果证明费用时间是在建议感觉放大器的35ns,并且最大值在read时期期间平均当前的消费,这是40μA。新奇拓扑学允许电路与象1.4V一样低的电力供应工作。感觉放大器为RFID标签IC应用在2-kb电可擦可编程只读存储器记忆被实现了,并且有240仅仅μm2的一个硅区域。
简介:TherelationshipsbetweenthepropertiesofPVC-MBSpolyblendandoftheMBSmultiphasestructureandbetweentheMBSstructureandpolymerizationparametersarestudiedtheoreticallyandexperimentally.MBSresinsynthesizedfromthemoleculedesignprincipleissuitabletopreparePVC-MBSpolyblendwithgoodtransparencyandhighimpactstrength.
简介:TheRFsystemforTESLArequiresacomprehensiveinterlocksystem.Usuallyinterlocksystemsareorganizedinahierarchicalway,Inordertoreacttodifferentfaultconditionsinafastandflexiblemanneranonhierarchicalorganizationseemstobethebettersolution,AttheTESLATestFacility(TTF)atDESYwewillinstallanonhierarchicalinterlocksystemthatisbasedonuserdesgnedreprogrammablegate-arrays(FPGA's)whichincorporateanembeddedmicrocontrollersystem.ThissystemcouldbeusedlaterfortheTESLAlinearcolliderreplacingastrictlyhierarchicaldesign.
简介:<正>From10-19OctobertheBritishDesignCouncil’sinternationaltouringexhibitionGreatExpectationswillvisitOrientalPlazainBeijing.GreatExpectationsshowcasesover100examplesofworld-leadingtechnologyanddesignfromtheUK.Theconceptoftheexhibitionechoestheinnovationitprojects.GreatExpectationshasbeendesignedaroundtheideaofafeast,whereiconsofinnovationaresetoutonavastglowingtablearoundwhichguestscanwanderortakeaseat.
简介:Controlinvariantsetsplayakeyroleinmodelpredictivecontrol.UsingLyapunovfunction,atechniqueisproposedtodesigncontrolinvariantsetsofplanarsystemsinapreciseform.First,itisdesignedforalinearsysteminBrunovskycanonicalform.Then,theresultisextendedtogenerallinearsystems.Finally,thenonlinearcontrolsystemsareconsidered,andsomesufficientconditionsanddesigntechniquesarealsoobtained.Numericalexamplesarepresentedtoillustratetheproposeddesignmethods.
简介:基于传统的弄平的粒子水动力学(SPH)算法,连接表搜索算法与可变变光滑长度结合了,方形的支持领域被提出改进计算效率并且保证计算精确性。一个舷侧液体舱上的高速度碎片影响的物理过程为模拟被规划。数字结果一般软件ANSYSAUTODYN与那些同意了很好,它验证数字方法的有效性和可行性。从液体舱,液体舱的宽度,和碎片的事件角度的外部板厚度的观点,保护的机制上的这些参数的影响被分析为一个舷侧液体舱的保护的设计提供一个基础。结果证明外部板厚度的影响不是明显的;因此,常规设计能在外部板的设计被采用。液体舱的宽度在碎片和液体舱的宽度的剩余速度上有大影响应该被设计在满足另外的要求的房屋下面尽可能宽。有碎片的速度变细是很明显的某个事件在角度,并且内部板附近的高压的地区是不对称的。液体舱的内部板应该根据壳形式,主要尺寸,和脆弱的点被加强。
简介:Wehavedevelopedafuzzyneuralexpertsystemthathastheprecisionandlearningabilityofaneuralnetwork.Knowledgeisacquiredfromdomainexpertsasfuzzyrulesandmembershipfunctions.Then,theyareconvertedintoaneuralnetworkwhichimplementsfuzzyinferencewithoutrulematching.Theneuralnetworkisappliedtoproblem-solvingandlearnsfromthedataobtainedduringoperationtoenhancetheaccuracy.Thelearningabilityoftheneuralnetworkmakesiteasytomodifythemembershipfunctionsdefinedbydomainexperts.Also,bymodifyingtheweightsofneuralnetworksadaptively,theproblemofbeliefpropagationinconventionalexpertsystemscanbesolvedeasily.Convertingtheneuralnetworkbackintofuzzyrulesandmembershipfunctionshelpsexplaintheinnerrepresentationandoperationoftheneuralnetwork.
简介:ManytaskstypicalforHighEnergyPhysicssuchassimulation,eventdisplay,maintenanceofthegeometrydatabaseofanexperiment,requireinputofgeometricaldata.TosimplifytheprocessofpreparationofsuchkindsofdataaninteractivegraphicatoolGBuilderisbeingdevelogped.DefinitionofthegeometrymodelinGBuilderisbasedontheConstructiveSolidGeometryapproachwhereobjectsaredefinedusingbooleanoperationsonbasicshapes.Toprovidsparameterizationofthemodelarithmeticexpressionsmaybeusedinplaceofnumbers,Awidelistofpredefinedmaterialsisalsoavailable.Differentdriversallowtooutputthegeometrymodelinaformsuitableforspecificsimulationofvisualanalysistools.