摘要
锅炉受热面积灰和结渣会导致锅炉运行的安全性和经济性下降。定义了新的受热面清洁因子,考虑了锅炉各受热面清洁时与灰污平衡时工质进出口焓升的变化,该清洁因子能够更显著地反映出受热面的灰污程度。应用BP神经网络预测不同工况下锅炉各受热面的工质焓升极大值与极小值,实时计算出锅炉各受热面的灰污状况,可指导和优化锅炉吹灰操作,并以屏式过热器为例进行了验证。
Fouling and slagging on boiler heating surface can reduce its safety and economy.A new cleaning factor was defined by considering inlet and output enthalpy increment of working substance when the surfaces were clean and fouling balancing.The cleaning factor can reflect the fouling degree of heating surfaces observably.BP neural network was used to predict the maximum enthalpy increment and minimum enthalpy increment of working substance under different operating conditions.The fouling degree of boiler heating surfaces can be calculated to instruct and optimize sootblowing operation in real time.The method was verified by an example of a platen superheater of a boiler.
出处
《节能》
2009年第4期19-20,共2页
Energy Conservation
关键词
锅炉
灰污监测
BP神经网络
清洁因子
boiler
fouling monitoring
BP neural network
cleaning factor
