燃煤电站锅炉性能智能优化研究

上海交通大学硕士学位论文燃煤电站锅炉性能智能优化研究姓名：马天星申请学位级别：硕士专业：热能工程指导教师：王恩禄200602181300MWe1.BP2.VC++BP3.2RESEARCHONTHEOPTIMIZATIONOFPULVERIZEDCOALFIREDUTILITYBOILERPERFORMANCEABSTRACTPulverizedcoalfiredutilityboilerhasmanyinputandoutputparameters,whicharemingledandpenetratedintoeachother.ByusingtheBPartificialneuralnetworkandgeneticalgorithm,amathematicalmodelwasbuiltupforgettingtherelationshipoftheinputparametersandoutputparameters,andtheinputandoutputparametersofthebestperformanceofthepulverizedcoalfiredutilityboiler.Themainideasoftheresearchareasfollows:Firstly,byanalyzingtherelationshipsoftheoperatingparametersofpulverizedcoalfiredutilityboiler,someofthemwereselectedtobeastheinputandoutputparametersoftheBPneuralnetworkmodel,whichwasbuiltupforforecastingandanti-forecastingtheperformanceandtheoperatingparametersofthepulverizedcoal-firedutilityboiler.AndtheoptimizemodelbasedontheGeneticAlgorithmwasbuiltupforgettingtheoperatingparameterswiththebestperformanceofthepulverizedcoal-firedutilityboiler;3Secondly,byusingthecomputerlanguageVC++,thesoftware,basedontheBPneuralnetworkandgeneticalgorithm,forforecastingandoptimizingtheperformanceofthepulverizedcoal-firedutilityboilerwaswritten.Therelationshipoftheoperationandperformanceparametersofa300MWeutilityboilerwasgottenbyrunningthesoftwarewithagreatdealofoperationdata,usedtobetrainedbyBPneuralnetworkanditwasusedtoforecastandanti-forecasttheoperatingandperformanceparameters,gettheparameterswiththebestperformancethroughGeneticAlgorithm,atdifferentloads,suchas300MWe,270MWe,240MWe,210MWe,180MWe;Thirdly,ithasbeenprovedthatthesoftwarehasmanymerits,suchasclearandswiftonitssurface,convenientinitsoperation,practicalandsafeinitsusage.Keywords:pulverizedcoalfiredutilityboiler,performanceoptimization,NeuralNetwork,GeneticAlgorithm4arnet,vQkJ/kgQ1kJ/kgQ2kJ/kgQ3kJ/kgQ4kJ/kgQ5kJ/kgQ6kJ/kgq1q2q3q4q5q6pyIkJ/kg0lkIkJ/kgpyahzGkgfhGkghzCfhC%Bkg5cph%apx,%bh,%ph,%eh,%ih,%mh,%gh,%BP(Back-PropagationNetwork)GA(GeneticAlgorithm)SGA(SimpleGeneticAlgorithm)12006218211.11.1.12002984453×106t106380114500×106t11.6520.6×106t[1]120008120102020203072.665.665.32030200015.71(106t)(106t)(%)200099852852.92005138870250.62010150082154.720201728105561.120301988135968.41.1.2500-800MWe40300MWe900MWe2““U”“W”RPHPMPSMBF1.1.3NOx[7][35]NOx1.21.2.1DCS[9][8]3DCS[2]NOxNOxNOxNOxNOxNOxNOx[3]NOx1.2.24[2][4][13]BP[14]10(DiagnosticOperationsCenterSystemHeatRateDegradationExpertSystemAdvisorSootblowerAdvisor)DCSDCS[6]PWIS(PLANTWIDEINFORMATIONSYSTEM)()[15][11][16][3]NOx[18]NOx[3]MAXFOXBOROABBSIEMENSGEDCSMIS5PEGASUPOWERPERFECTERPegasusNEUSIGHT1.3BP262.1()[22]()()(1)——(2)()2.22.2.17:(1)Q1(2)Q2(3)Q3(4)Q4Q4(5)Q5(6)Q6Q62.2.2arnet,vQ1kg:arnet,v123456QQQQQQQ=+++++2-1arnet,vQ——kJ/kgQ1——kJ/kgQ2——kJ/kgQ3——kJ/kgQ4——kJ/kg8Q5——kJ/kgQ6——kJ/kg(2-1)arnet,vQ100100%=q1+q2+q3+q4+q5+q62-2q1——q2——q3——q4——q5——q6——2.3.31q2042()(100),%lkpypyrIIqqQa--=(2-3)pyI——kJ/kg0lkI——tlk30kJ/kgpya——''1pyaaa=+∑V482222Table2ThethermallosingofQingDaopowerplant(%)(%)(%)(%)q27.234.4784.35.63q30.060.060.90.06q40.70.257.20.48q50.40.84100.67q60.040.040.60.049,,aÄá[23]2q30.5%3q4Q4hzQ4fh432700()100100hzhzfhfhrGCGCqQB+=×(2-4)GhzGfh——kg/hChzCfh——%B——kg/h2-44q55q62.3101%0.3%~0.4%3~4g/(kWh)300MWe[28][29][31][32]()2.3.12.3.211122.3.3;2-22.2.42-22.3.5NOx12()á=(2-5)ááá300MW270MW240MW210MW180MW1~51300MWeFig1Effectfromextra-oxygentotheboilerefficiencyin300MWe132270MWeFig2Effectfromextra-oxygentotheboilerefficiencyin270MWe3240MWeFig3Effectfromextra-oxygentotheboilerefficiencyin240MWe4210MWeFig4Effectfromextra-oxygentotheboilerefficiencyin210MWe145180MWeFig5Effectfromextra-oxygentotheboilerefficiencyin180MWe90%70%60%100%802.3.632300MWe270MWe240MWe210MWe180MWe6103Table3Effectfromthedistributionofsecond-windtotheboilerefficiency300MW270MW240MW210MW180MW12121212123.763.8444.24.494.584.184.184.874.8193.2992.6993.4392.2193.4292.5893.6893.1993.8392.535.796.245.656.665.506.185.235.754.985.98150.380.520.380.530.420.570.300.530.310.611381421361361331361231321191214.544.954.924.983.975.392.884.992.965.7316100100751001001001582581310010056100100100563405612426040664065303933411110010051515051505051511043504550395940503555950595050505050505050836564355485538423648640704050486035373048550605150515051515151454505550555050505050360505050504950505151266506050605760507060“”“”“”“”“”NOx(%)93.29(%)5.79(%)0.386654404342100100050100150246810121316(%)92.69(%)6.24(%)0.5250507050601001000501001502468101213166300MWeFig6Consractofeconomyindifferentsecond-windin300MWe(%)93.43(%)5.65(%)0.3860554045405675050100150246810121316(%)(%)92.21(%)6.66(%)0.535050505066100100050100150246810121316(%)167270MWeFig7Consractofeconomyindifferentsecond-windin270MWe(%)93.42(%)5.5(%)0.426055483940100100050100150246810121316(%)(%)92.58(%)6.18(%)0.575750605965100100050100150246810121316(%)8240MWeFig8Consractofeconomyindifferentsecond-windin240MWe(%)93.68(%)5.23(%)0.36050354030561050100150246810121316(%)(%)93.19(%)5.75(%)0.5350503750393458050100150246810121316(%)9210MWeFig9Consractofeconomyindifferentsecond-windin210MWe(%)93.83(%)4.98(%)0.31705