Real-time dynamic prediction model of NOx emission of coal-fired boilers under variable load conditions

This study focuses on the problem of predicting nitrogen oxide (NOx) concentration at the inlet of selective catalytic reduction (SCR) reactors under variable load conditions of thermal power units. Some variables with strong correlation with NOx concentration at the SCR inlet were selected as auxiliary variables and the delay time between NOx concentration and auxiliary variables was determined by the mutual information method. Taking the delay time, dynamic time and prediction error into account, a real-time dynamic prediction model of NOx concentration based on the least square support vector machine was proposed. The model was tested using the actual historical data under variable load operating conditions of two thermal power units. Test results show that the proposed dynamic prediction model has high real-time prediction accuracy and satisfactory generalization ability.