資源描述:
《模糊神經(jīng)網(wǎng)絡(luò)及其在熱工建模與控制中的應(yīng)用研究》由會(huì)員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)。
1、東南大學(xué)碩士學(xué)位論文模糊神經(jīng)網(wǎng)絡(luò)及其在熱工建模與控制中的應(yīng)用研究姓名:楊世忠申請(qǐng)學(xué)位級(jí)別:碩士專業(yè):熱能工程指導(dǎo)教師:呂劍虹20070601摘要AbstractWiththeapplicationofDesinautomaticcontrolsystemforthermalpowerplant,advancedcontrolstrategieshavebeenadoptedintIlerTnalprocessescontr01.But∞whatCallbeseerli11manythermalpowerplant,weyetcanno
2、tobtaingoodperformanceinthermalprocessescon訂ol,becausethetraditionalPIDcontrolsystemshavebeenwidelyusedinalmosta11thethelTnalpowerplants,whichhasabadeffectonthesafetyandeconomicalefficiencyofpowerplants.111emainrel舶onsare∞follows.First,whenthethermalsystems’statechange,
3、thedynamicperfommceofcontrolledplantsoftenvariedgreatly,whichmeansthatthereisseriousnonlinearityincontrolledplants.SothetraditionalPIDcontrolsystem,whichisdesignedonthebasisofplantscharaeteristieonterrainloadpoint,cannotbeusedtorealizeprocessoptimaleontrolinwholeloadran
4、ge.Inaddition.onthecontrarytothelinearityofPIDeontr01systems,therearenonlinearresponsesincontrolledplants.Asweallknow,nomatterhowweimprovetheeapabilityoflinearPDcontrolsystems.theremustbealimitationintheimprovementofcontroleffects.Soweshouldadoptnewoptimalcontrolsystems
5、whicharebasedonwholenonJinearmodelsforthermalprocessestoimprovethecontrolperformance.Obviously,thewholenonlinearmodelingforthermalprocessesisthebasistooptimalcontrolinwholeloadrage.Thefuzzysystemhasseveraladvantages:itcalldepicttheuncertaintyofplantswell;ithasacapabilit
6、yofuniversalapproximation;itssinglerulecanapproachthelocaldynamicscharacterizationofthenonlinearsystem;itsmodelingresultisrelativelytransparent.AUofthesevirtuesareinfavorofthedesignandapplicationofhi曲.performancemodelcontroller.What’smore,duetothepowerfulabilityofnonlin
7、earfunctionsapproximation,andwiththecharacteristicsofadaptivelearning,parallelanddistributedprocessing,strongrobustnessandfaulttolerance,ArtificialNeuralNetwork(ANN)hasbeenaneriectiveapproachtomodelandcontr01theunknownanduncertainoontrolsysreins.Justonthebasisof出eseappl
8、icailonbackground.thispapercombinesANNwithfuzzysystem,andstudiestouscFuzzyNenralNetwork(FNN)tosolvethecorrelat