热力发电
熱力髮電
열력발전
THERMAL POWER GENERATION
2014年
10期
90-94
,共5页
汽轮机%排汽焓%在线计算%预测精度%Elman%GA
汽輪機%排汽焓%在線計算%預測精度%Elman%GA
기륜궤%배기함%재선계산%예측정도%Elman%GA
steam turbine%exhaust enthalpy%online calculation%prediction accuracy%Elman%GA
利用遗传算法(GA)的良好寻优能力对汽轮机排汽焓动态递归(Elman)神经网络进行了优化，建立了 GA-Elman 神经网络预测模型，并以某电厂350 MW 机组为例进行了汽轮机排汽焓的在线计算。结果表明：GA-Elman 神经网络预测模型克服了传统 Elman 神经网络利用梯度下降法进行训练所具有的易陷入局部极小值、收敛速度慢、精度低等缺点，提高了预测精度和收敛速度，较适合现场应用。
利用遺傳算法(GA)的良好尋優能力對汽輪機排汽焓動態遞歸(Elman)神經網絡進行瞭優化，建立瞭 GA-Elman 神經網絡預測模型，併以某電廠350 MW 機組為例進行瞭汽輪機排汽焓的在線計算。結果錶明：GA-Elman 神經網絡預測模型剋服瞭傳統 Elman 神經網絡利用梯度下降法進行訓練所具有的易陷入跼部極小值、收斂速度慢、精度低等缺點，提高瞭預測精度和收斂速度，較適閤現場應用。
이용유전산법(GA)적량호심우능력대기륜궤배기함동태체귀(Elman)신경망락진행료우화，건립료 GA-Elman 신경망락예측모형，병이모전엄350 MW 궤조위례진행료기륜궤배기함적재선계산。결과표명：GA-Elman 신경망락예측모형극복료전통 Elman 신경망락이용제도하강법진행훈련소구유적역함입국부겁소치、수렴속도만、정도저등결점，제고료예측정도화수렴속도，교괄합현장응용。
By taking use of good optimizing ability of the genetic algorithm (GA),the dynamic recurrent neural network (Elman)of steam turbine exhaust enthalpy was optimized and a GA-Elman neural network prediction model was established.Taking a 350 MW unit steam turbine as the example,online calculation for the turbine exhaust enthalpy was conducted by applying this model.The results show that:this GA-El-man neural network model overcomes such problems as easy to fall into local minimum,slow convergence speed and low precision that the conventional Elman neural network (which applies gradient descent meth-od to conduct training)has.So this model enhances the prediction accuracy and convergence speed,which is more suitable for field application.
