Abstract
In order to control NH3 injection for the selective catalytic reduction of nitrogen oxide (NOx) denitration (SCR de-NOx) process, a model that can accurately and quickly predict outlet NOx emissions is required. This paper presents a dynamic kernel partial least squares (KPLS) model incorporated with delay estimation and variable selection for outlet NOx emission and investigated control strategy for NH3 injection. First, k-nearest neighbor mutual information (KNN_MI) was used for delay estimation, and the effect of historical data lengths on KNN_MI was taken into account. Bidirectional search based on the change rate of KNN_MI (KNN_MI_CR) was used for variable selection. Delay–time difference update algorithm and feedback correction strategy were proposed. Second, the NH3 injection compensator (NIC) and the outlet NOx emission model constituted a correction controller. Then, its output and the output of the existing controller are added up to suitable NH3 injection. Finally, the KNN_MI_CR method was compared with different algorithms by benchmark dataset. The field data results showed that the KNN_MI_CR method could improve model accuracy for reconstructed samples. The final model can predict outlet NOx emissions in different operating states accurately. The control result not only meets the NOx emissions standard (50 mg/m3) but also keeps high de-NOx efficiency (80%). NH3 injection and NH3 escape are reduced by 11% and 39%.
Highlights
How to reduce nitrogen oxide (NOx ) emissions from coal-fired power plants has become an important task of environmental treatment
The deviation ∆ ỹ(t) between the corrected delay–time difference (DTD)–kernel partial least squares (KPLS) model output ỹ(t) and the set value of outlet NOx mission yset is used as the input variables, and the compensation amount of NH3 injection ∆yNH3 (t) is used as the output variable
Aiming at nonlinearity and large lag in SCR de-NOx process, this paper proposes the k-nearest neighbor Mutual information (MI)(KNN_MI) method to estimate the time-delay of the input variable and the effect of the historical data lengths on k-nearest neighbor mutual information (KNN_MI) was taken into account
Summary
How to reduce nitrogen oxide (NOx ) emissions from coal-fired power plants has become an important task of environmental treatment. When the operating state changes, the SCR system cannot adjust NH3 injection in time based on the sampling inlet NOx concentration, which can make the outlet NOx emission deviate from the set value. How to select an evaluation strategy and how to estimate the MI value accurately are two main difficulties in variable selection by the MI method. It is necessary to determine the historical data length of each input variable when the time-delay is estimated. The objective of this paper is to model outlet NOx emissions under the different operating state, thereby to facilitate controller design. The field data experiment for the SCR de-NOx process is investigated, and the predictive accuracy of the outlet NOx emission model and the control effect of the proposed control strategy are analyzed.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
