计量学报
計量學報
계량학보
ACTA METROLOGICA SINICA
2014年
6期
622-626
,共5页
计量学%遗传算法%GA-BP神经网络%PM2. 5监测%软测量
計量學%遺傳算法%GA-BP神經網絡%PM2. 5鑑測%軟測量
계량학%유전산법%GA-BP신경망락%PM2. 5감측%연측량
MetrOIOgy%Genetic aIgOrithm%GA-BP neuraI netwOrk%PM2. 5 mOnitOring%SOft sensOr
大气中PM2.5质量浓度变化具有较强的非线性特性,传统的软测量方法很难对其做出准确的计量监测。针对传统BP神经网络易陷入局部最小值的缺陷,将遗传算法和BP神经网络相结合建立了GA-BP神经网络软测量模型,将该模型应用到大气PM2.5质量浓度的计量监测中,并与传统BP神经网络模型的监测结果进行对比,结果表明经过遗传算法优化后的模型具有更好的非线性拟合能力和更高的监测精度。
大氣中PM2.5質量濃度變化具有較彊的非線性特性,傳統的軟測量方法很難對其做齣準確的計量鑑測。針對傳統BP神經網絡易陷入跼部最小值的缺陷,將遺傳算法和BP神經網絡相結閤建立瞭GA-BP神經網絡軟測量模型,將該模型應用到大氣PM2.5質量濃度的計量鑑測中,併與傳統BP神經網絡模型的鑑測結果進行對比,結果錶明經過遺傳算法優化後的模型具有更好的非線性擬閤能力和更高的鑑測精度。
대기중PM2.5질량농도변화구유교강적비선성특성,전통적연측량방법흔난대기주출준학적계량감측。침대전통BP신경망락역함입국부최소치적결함,장유전산법화BP신경망락상결합건립료GA-BP신경망락연측량모형,장해모형응용도대기PM2.5질량농도적계량감측중,병여전통BP신경망락모형적감측결과진행대비,결과표명경과유전산법우화후적모형구유경호적비선성의합능력화경고적감측정도。
Because Of the varying cOncentratiOn Of atmOspheric PM2. 5 have strOng nOnIinear characteristics,traditiOnaI sOft sensOr methOds are difficuIt tO make accurate measuring and mOnitOring. AccOrding tO traditiOnaI BP neuraI netwOrk is easy tO faII intO IOcaI minimum,BP neuraI netwOrk is cOmbined with genetic aIgOrithm tO estabIish the GA-BP neuraI netwOrk sOft sensOr mOdeI. The mOdeI is appIied tO the mOnitOring Of the atmOspheric cOncentratiOn Of PM2. 5,and cOmpared with the resuIts Of the mOnitOring Of the traditiOnaI BP neuraI netwOrk mOdeI,the resuIts shOw that the genetic aIgOrithm OptimizatiOn mOdeI has a better nOn-Iinear fitting abiIity and higher mOnitOring accuracy.