|
OALib Journal期刊
ISSN: 2333-9721
费用：99美元
|
|
|
|
基于wls？svm？sfs模型的电站锅炉燃烧优化
, PP. 7-12
Keywords: nox排放量,锅炉效率,wls？svm,sfs,燃烧优化
Abstract:
nox排放量和锅炉效率模型是电站锅炉燃烧优化的基础。采用抗干扰能力更强的加权最小二乘支持向量机（wls？svm）建立了nox排放模型。将序列前向选择（sfs）与wls？svm相结合建立了锅炉效率模型，在不影响模型精度前提下去除了模型中的冗余成分，精简了模型结构，提高了模型计算速度。采用遗传算法，以所建模型为基础，提出了一种可兼顾锅炉效率和nox排放量的优化燃烧方案。实际应用结果表明，该优化方案使锅炉效率平均提高0.386%，nox排放量平均降低99.147mg/m3。
| [1] | 吴碧君.燃烧过程中氮氧化物的生成机理[j].电力环境保护,2004,19(4):9�12.wubijun.thecomposingmechanismofnoxincombustion[j].electricpowertechnologyandenvironmentalprotection,2004,19(4):9�12.
|
| [2] | 孔亮,张毅,丁艳军,等.电站锅炉燃烧优化控制技术综述[j].电力设备,2006,7(2):19�22.kongliang,zhangyi,dingyanjun,etal.areviewofcontroltechnologiesofcombustionoptimizationinutilityboilers[j].electricalequipment,2006,7(2):19�22.
|
| [3] | 顾燕萍,赵文杰,吴占松.基于最小二乘支持向量机的电站锅炉燃烧优化[j].中国电机工程学报,2010,30(17):91�97.guyanping,zhaowenjie,wuzhansong.combustionoptimizationforutilityboilerbasedonleastsquare�supportvectormachine[j].proceedingsofthecsee,2010,30(17):91�97.
|
| [4] | 许昌,吕剑虹.基于生成机理的燃煤电站锅炉nox排放量神经网络模型[j].中国电机工程学报,2005,24(10):233�237.xuchang,lujianhong.artifcialneuralnetworksmodelfornoxemissionsinapulverized�coalpowerstationboilerongenerationmechanism[j].proceedingsofthecsee,2005,24(10):233�237.
|
| [5] | 周昊,朱洪波,岑可法.基于人工神经网络和遗传算法的火电厂锅炉实时燃烧优化系统[j].动力工程,2003,23(5):2665�2669.zhouhao,zhuhongbo,cenkefa.anon�lineboileroperatingoptimizationsystembasedontheneuralnetworkandthegeneticalgorithms[j].powerengineering,2003,23(5):2665�2669.
|
| [6] | zhouh,peizhaoj,gangzhengl,etal.modelingnoxemissionsfromcoal�firedutilityboilersusingsupportvectorregressionwithantcolonyoptimization[j].engineeringapplicationsofartificialintelligence,2012,25(1):147�158.
|
| [7] | wahabnia,mohameda,hussaina.comparingleastsquaressupportvectormachineandprobabilisticneuralnetworkintransientstabilityassessmentofalarge�scalepowersystem[c]//proceedingsofieee2ndinternationalpowerandenergyconference.2008:485�489.
|
| [8] | guy,zhaow,wuz.onlineadaptiveleastsquaressupportvectormachineanditsapplicationinutilityboilercombustionoptimizationsystems[j].journalofprocesscontrol,2011,21(7):1040�1048.
|
| [9] | suykensjak,debrabanterj,lukasl,etal.weightedleastsquaressupportvectormachines:robustnessandsparseapproximation[j].neurocomputing,2002,48(1):85�105.
|
| [10] | xiej.fuzzyleastsquaresupportvectormachineappliedtodetectdamageforfibersmartstructures[c]//proceedingoftheinternationalsymposiumonintelligentinformationtechnologyapplicationworkshops.2008:383�386.
|
| [11] | suykensjak,vandewallej.leastsquaressupportvectormachineclassifiers[j].neuralprocessingletters,1999,9(3):293�300.
|
| [12] | guyoni,elisseeffa.anintroductiontovariableandfeatureselection[j].thejournalofmachinelearningresearch,2003,3:1157�1182.
|
| [13] | liuh,motodah.computationalmethodsoffeatureselection[m].chapman&hall/crc,2007.
|
| [14] | 张毅.电站锅炉燃烧优化控制理论[d].北京:清华大学,2006.zhangyi.researchontheoryandapplicationofcombustionoptimizationcontrolofutilityboilers[d].beijing:tsinghuauniversity,2006(inchinese).
|
| [15] | 张小桃,王培红.一种新的锅炉效率的计算模型[j].电站系统工程,1999,15(4):16�17.zhangxiaotao,wangpeihong.newcomputingmodelforboilerefficiency[j].powersystemengineering,1999,15(4):16�17.
|
Full-Text
|
|
Contact Us
service@oalib.com QQ:3279437679 
WhatsApp +8615387084133
|
|
