The accurate measurement of oxygen content in flue gases is significant for the improvement of the economic combustion. The soft-sensing technique and data fusion are used to measure oxygen content in flue gases in this thesis. Through mechanism analysis and the analysis of the history data of eDNA, dynamic and static soft-sensing models of oxygen content are set up. At same time, several software sensors of air flow and fuel flow are designed based on regression. Based on multisensor data fusion, more reliable and accurate values of air flow and fuel flow are obtained. At last, this soft-sensing model fit well with the practical oxygen content, which is illustrated by the simulations.
|