ARTIFICIAL INTELLIGENCE TREATMENT OF NOx EMISSIONS FROM CFBC IN AIR AND OXY-FUEL CONDITIONS
The present work introduces a way of predicting the NOx (i.e.NO + NO2) emissions from coal combustion in circulating fluidized bed combustors (CFBC) by Artificial Neural Network (ANN) approach.The purpose of the study is to perform a simple model to predict the NOx emissions from circulating fluidized bed (CFB) facilities in different scales and under wide range of operating conditions, both for air-fired and oxy-fuel conditions.The neurocomputing approach constitute a novel and powerful tool to examine the NOx emissions from CFB units.It has been shown, that the modeling using artificial neural network approach gives simple way to obtain the gas emissions.The ANN model give quick and accurate results for both large and pilot-scale CFB combustors as an answer to the input pattern, i.e.under different conditions and geometry parameters of the combustion chambers.The validity of the model was verified by measurements on the data obtained from the existing units.Among them are 0.1MWth OxyFuel-CFB Test Rig operated in oxy-fuel mode and the worlds largest once through supercritical 966 MWth, circulating fluidized bed boiler, operated in air-fired conditions, installed in the Tauron Generation Lagisza Power Plant, Poland.The NOx emissions evaluated using the developed ANN model are in a good agreement with experimental results.
Jaroslaw Krzywanski Artur Blaszczuk Tomasz Czakiert Rafal Rajczyk Wojciech Nowak
Institute of Advanced Energy Technologies,Czestochowa University of Technology Dabrowskiego 73,42-200 Czestochowa,Poland
国际会议
The 11th International Conference on Fluidized Bed Technology(CFB-11)(第十一届流化床技术国际会议)
北京
英文
619-624
2014-05-14（万方平台首次上网日期，不代表论文的发表时间）