History

A general study on genetic fuzzy systems

Description
A general study on genetic fuzzy systems
Categories
Published
of 26
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Related Documents
Share
Transcript
  See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/2703492 A General Study on Genetic Fuzzy Systems  Article  · October 1997 Source: CiteSeer CITATIONS 48 READS 19 1 author:Some of the authors of this publication are also working on these related projects: FUZZ-IEEE 2017   View projectFuzz-IEEE 2017 Special Session on Fuzzy Models for Big Data (SS - 11)   View projectFrancisco HerreraUniversity of Granada 864   PUBLICATIONS   36,766   CITATIONS   SEE PROFILE All content following this page was uploaded by Francisco Herrera on 07 September 2013. The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the srcinal documentand are linked to publications on ResearchGate, letting you access and read them immediately.  3  AGeneralStudyonGeneticFuzzy Systems  OSCARCORD  ON,FRANCISCOHERRERA  3.1INTRODUCTION  Asitisknown,arulebasedsystem(productionrulesystem)hasbeensuccessfullyused tomodelhumanproblem-solvingactivityandadaptivebehavior,whereaclassicway torepresentthehumanknowledgeistheuseofIF/THENrules.Thesatisfactionoftheruleantecedentsgivesrisetotheexecutionoftheconsequent,oneactionisperformed.Theconventionalapproachestoknowledgerepresentationarebasedonbivalentlogic.Aseriousshortcomingofsuchapproachesistheirinabilitytocometogripswiththeissueofuncertaintyandimprecision.Asaconsequence,theconventionalapproachesdo notprovideanadequatemodelformodesofreasoningandallcommonsensereasoning fallintothiscategory.FuzzyLogic(FL)maybeviewedasanextensionofclassicallogicalsystems,providesaneectiveconceptualframeworkfordealingwiththeproblemofknowledgerepresentationinanenvironmentofuncertaintyandimprecision.FL,asitsnamesuggests,isthelogicunderlyingmodesofreasoningwhichareapproximateratherthan exact.TheimportanceofFLderivesfromthefactthatmostmodesofhumanreasoning -andespeciallycommonsensereasoning-areapproximateinnature.FLisconcerned inthemainwithimprecisionandapproximatereasoning.TheapplicationsofFLtorulebasedsystemshavebeenwidelydevelopped.From averybroadpointofviewaFuzzySystem(FS)isanyFuzzyLogicBasedSytems,whereFLcanbeusedeitherasthebasisfortherepresentationofdierentformsofknowledgesystems,ortomodeltheinteractionsandrelationshipsamongthesystem variables.FShavebeenshowntobeanimportanttoolformodellingcomplexsystems,inwhich,duetothecomplexityortheimprecision,classicaltoolsareunsuccessful. SampleContributedBook EditorJennySmithc   1993JohnWiley&SonsLtd. cbook2/9/199717:36|PAGEPROOFSforJohnWiley&SonsLtd(jwbook.styv3.0,12-1-1995)  2OSCARCORD ON,FRANCISCOHERRERA  DESIGN PROCESSLearning ProcessInput InterfaceOutput InterfaceKnowledge BaseComputation with Fuzzy SystemsFuzzy SystemGenetic Algorithm BasedEnvironmentEnvironment Figure3.1 GeneticFuzzySysems AmongthemostsuccessfulapplicationsofthissystemshasbeentheareaofFuzzy logiccontrollers(FLCs).FLCsarerulebasedsystemsusefulinthecontextofcomplex ill-denedprocesses,especiallythosewhichcanbecontrolledbyaskilledhuman operatorwithoutknowledgeoftheirunderlyingdynamics.Recentelyfuzzycontroltechniqueshavebeenappliedtomanyindustrialprocesses,FLCshavebeenwidthly usedinautomationandengineering.Theexperienceofskilledoperatorsandtheknowledgeofcontrolengineersareexpressedqualitetivelybyasetoffuzzycontrolrules.Infact,oneofthefeaturesoftheFLCsisthatthe IF-THEN  rulesaredescribed onthebaseoftheconventionalcontrolstrategyandtheexperts'knowledge.Eachfuzzy rulehasanantecedent,or IF  ,partcontainingseveralpreconditions,andaconsequent,or THEN  ,partwhichprescribesthevalue.Recentely,numerouspapersandapplicationscombiningfuzzyconceptsandgeneticalgorithms(GAs)havebecomeknown,andthereisanincreasingconcernintheintegrationofthesetwotopics.Inparticular,thereareagreatnumberofpublicationsexploringtheuseofGAsfordeveloppingfuzzysystems,thecalledgeneticfuzzysystems(GFSs).Figure1showsthisidea.ThispaperpresentsanoverviewoftheGFSs,showingtheuseoftheGAsintheconstructionofthefuzzylogiccontrollersknowledgebasescomprisingtheknown knowledgeaboutthecontrolledsystem.Toachievethat,thispaperisdividedinto4sectionstherstbeingthisintroduction.Thesection2introducesthefuzzysystemswithaspecialattentiontoFLCs,whilesection3presentstheGFSs.Somenalremarksaremadeinsection4.cbook2/9/199717:36|PAGEPROOFSforJohnWiley&SonsLtd(jwbook.styv3.0,12-1-1995)  AGENERALSTUDYONGENETICFUZZYSYSTEMS3 3.2FUZZYSYSTEMS  FuzzylogicandfuzzysetsinawideinterpretationofFL(intermsofwhichfuzzylogiciscoextensivewiththetheoryoffuzzysets,thatis,classesofobjectsinwhichthetransitionfrommembershiptononmembershipisgradualratherthanabrupt)haveplacedmodelingintoanewandbroaderperspectivebyprovidinginnovativetoolsto copewithcomplexandill-denedsystems.Theareaoffuzzysetshasemergedfollowing somepioneeringworksofZadehZad65,Zad73]wheretherstfundamentalsoffuzzy systemswereestablished.Asweaforesaid,arulebasedsystemhasbeensuccessfullyusedtomodelhuman problem-solvingactivityandadaptivebehavior.Theconventionalapproachesto knowledgerepresentation,arebasedonbivalentlogic.Aseriousshortcomingofsuch approachesistheirinabilitytocometogripswiththeissueofuncertaintyand imprecision.Asaconsequence,theconventionalapproachesdonotprovideanadequatemodelformodesofreasoning.Unfortunatelly,allcommonsensereasoningfallintothiscategory.TheapplicationofFLtorulebasedsystemsleadsustothefuzzysystems.Themainroleoffuzzysetsisrepresentingknowledgeabouttheproblem,ortomodeltheinteractionsandrelationshipsamongthesystemvariables.Therearetwoessentialadvantagesforthedesignofrule-basedsystemswithfuzzysetsandlogic:  thekeyfeaturesofknowledgecapturedbyfuzzysetsinvolvehandling uncertainty,and   inferencemethodsbecomemorerobustandexiblewithapproximatereasoningmethodsoffuzzylogic.Knowledgerepresentationisenhancedwiththeuseoflinguisticvariablesandtheirlinguisticvaluesthataredenedbycontext-dependentfuzzysetswhosemeaningsarespeciedbygradedmembershipfunctions.Onotherhand,inferencemethodssuch asgeneralizedmodusponens,tollens,etc.,whicharebasedonfuzzylogicformthebasesofapproximatereasoningwithpatternmatchingscoresofsimilarity.Fuzzylogicprovidesanuniquecomputationalbaseforinferenceinrulebasedsystems.Unliketraditionallogicalsystems,fuzzylogicisaimedatprovidingmodesofreasoningwhich areapproximateandanalogicalratherthanexact.Abordingthefuzzysystemmodelingissue,itisessentiallydevelopedintotwo dierenttypesofsystemmodelsidentiedasacquisitionofrulesandtheirparameters:i)fuzzyexpertsystemmodels,andii)fuzzylogiccontrollers.Fuzzyexpertsystemmodelsaredesigned,developedandimplementedwithadirectparticipationofasystem'sexpertwhoisthroughlyfamiliarwiththecharacteristicbehaviourofthesystemunderinvestigation.Theknowledgeoftheexpertisextracted fromtheexpertthroughexperimentalmethodsofquestionnaires,protocolsand interviewswhichmaybeconductedbypeopleorbycomputersforthepurposeofidentifyingtheformandthestructureoftherules,i.e.,structureidenticationaswellasthemembershipfunctionsofthelinguisticvaluesoflinguisticvariables,i.e.,parameteridentication.Ontheotherhand,fuzzycontrolmodeldesign,developmentandimplementation aredependentontheavailabilityofinput-outputdatasets.Thesystemstructureidenticationintermsofrulesandspecicationofmembershipfunctionsthatdenecbook2/9/199717:36|PAGEPROOFSforJohnWiley&SonsLtd(jwbook.styv3.0,12-1-1995)  4OSCARCORD ON,FRANCISCOHERRERA  FuzzificationInterfaceInterfaceControlled SystemKnowledge Base Control VariablesState Variables Inference SystemDefuzzification Figure3.2  Genericstructureofafuzzylogiccontroller themeaningrepresentationoflinguisticvaluesoflinguisticvariablesaredetermined bylearningtechniques.Alsothereisathirdkindthatisthecombinationoftheotherstwothatmaybecalled  fuzzyexpert-control .Here,wewillcenterinthesecondfuzzysystemmodel,theFLCs,wheretheGAshavebeenusedfordesignthestructureidenticationofthesystem.FLCs,initiatedbyMamdaniandAssilianintheworkMA75],arenowconsidered asoneofthemostimportantapplicationsofthefuzzysettheory.FLCsareknowledgebasedcontrollersthatmakeuseoftheknownknowledgeoftheprocess,expressedin formoffuzzylinguisticcontrolrulescollectedinaknowledgebase(KB),tocontrolit.Theadvantageofthisapproachwithrespecttotheclassical ControlTheory  isthatithasnotnecessityofexpressingtherelationshipsexistinginthesystemby meansofamathematicalmodel,whatconstitutesaverydiculttaskinmanyrealsituationspresentingnonlinearcharacteristicsorcomplexdynamic.Inthefollowing twosubsectionswepresentanintroductiontoFLCsandtotheFLCKBs. 3.2.1FuzzyLogicControllers AnFLCiscomposedbya  KnowledgeBase  ,thatcomprisestheinformationgivenby theprocessoperatorinformoflinguisticcontrolrules,a  FuzzicationInterface  ,which hastheeectoftransformingcrispdataintofuzzysets,an  InferenceSystem  ,thatusesthemjoinedwiththeKnowledgeBasetomakeinferencebymeansofareasoning method,anda  DefuzzicationInterface  ,thattranslatesthefuzzycontrolactionso obtainedtoarealcontrolactionusingadefuzzicationmethod.ThegenericstructureofanFLCisshowningure2Lee90].Severalfactorswithasignicantinuencehavetobeanalyzedinordertodesignan FLCforaconcreteprocess.Concretely,therearetwomaindecisionstomakeinordertodesignaFLC,toderiveaKBforthesystemandtodecidethereasoningmethodto use.Ascanbeviewed,onlytherstonedependsdirectlyontheconcreteapplication altoughseveralreasoningmethodswillperformbetterwithsomekindofsystemsthan others.cbook2/9/199717:36|PAGEPROOFSforJohnWiley&SonsLtd(jwbook.styv3.0,12-1-1995)
Search
Tags
Related Search
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks