热力发电
熱力髮電
열력발전
THERMAL POWER GENERATION
2014年
9期
39-42,47
,共5页
谢诞梅%陈畅%熊扬恒%高尚%王纯
謝誕梅%陳暢%熊颺恆%高尚%王純
사탄매%진창%웅양항%고상%왕순
汽轮机%排汽干度%BP神经网络%在线计算
汽輪機%排汽榦度%BP神經網絡%在線計算
기륜궤%배기간도%BP신경망락%재선계산
exhaust dryness%BP neural network%online prediction
对于大型凝汽式汽轮机,其汽轮机末级的排汽状态点处于湿蒸汽区,由于缺乏实时有效的测量手段,汽轮机末级排汽干度难以直接确定,其计算取值一直是火电机组热力系统热经济性在线分析的难点.利用 BP 神经网络的非线性映射能力,以某台 N1000-25/600/600型汽轮机为研究对象,建立了汽轮机末级排汽干度(排汽干度)与机组负荷和汽轮机末级排汽压力(排汽压力)的BP神经网络关系模型.将该模型通过典型工况的学习训练及校验后,用于排汽干度的全工况在线计算.结果表明,所建模型最大训练误差和最大校验误差分别为-0.0061和-0.0010,满足工程计算的精度要求,可用于排汽干度在线计算和预测.
對于大型凝汽式汽輪機,其汽輪機末級的排汽狀態點處于濕蒸汽區,由于缺乏實時有效的測量手段,汽輪機末級排汽榦度難以直接確定,其計算取值一直是火電機組熱力繫統熱經濟性在線分析的難點.利用 BP 神經網絡的非線性映射能力,以某檯 N1000-25/600/600型汽輪機為研究對象,建立瞭汽輪機末級排汽榦度(排汽榦度)與機組負荷和汽輪機末級排汽壓力(排汽壓力)的BP神經網絡關繫模型.將該模型通過典型工況的學習訓練及校驗後,用于排汽榦度的全工況在線計算.結果錶明,所建模型最大訓練誤差和最大校驗誤差分彆為-0.0061和-0.0010,滿足工程計算的精度要求,可用于排汽榦度在線計算和預測.
대우대형응기식기륜궤,기기륜궤말급적배기상태점처우습증기구,유우결핍실시유효적측량수단,기륜궤말급배기간도난이직접학정,기계산취치일직시화전궤조열력계통열경제성재선분석적난점.이용 BP 신경망락적비선성영사능력,이모태 N1000-25/600/600형기륜궤위연구대상,건립료기륜궤말급배기간도(배기간도)여궤조부하화기륜궤말급배기압력(배기압력)적BP신경망락관계모형.장해모형통과전형공황적학습훈련급교험후,용우배기간도적전공황재선계산.결과표명,소건모형최대훈련오차화최대교험오차분별위-0.0061화-0.0010,만족공정계산적정도요구,가용우배기간도재선계산화예측.
In large scale condensing turbine unit,the exhaust status always lies in wet steam area.Due to the lack of effective measuring method,the exhaust dryness of the steam turbine is difficult to obtain directly, which has been the difficult problem in online economic analysis for thermal power units.By taking an N1000-25/600/600 ultra-supercritical steam turbine as an example,the nonlinear mapping ability of BP neural network was used to establish a model which can reflect the relationship between exhaust dryness and unit load and exhaust pressure.After learning and training under some typical conditions,this model was used for exhaust dryness online calculation under full condition.The results show the final error of the training samples and verifying samples were controlled within -0.006 1 and -0.001 0,which satisfies the accuracy requirement for engineering calculation,indicating the established BP neural network can be used in exhaust dryness prediction.