As the main energy source for thermal power generation, coal generates a large amount of NOx during its incineration in boilers, and excessive NOx emissions can cause serious pollution to the air environment. Selective catalytic reduction denitrification (SCR) selects the optimal amount of ammonia to be injected for denitrification based on the measurement of NOX concentration by the automatic flue gas monitoring system. Since the automatic flue gas monitoring system has a large delay in measurement, it cannot accurately reflect the real-time changes of NOx concentration at the SCR inlet when the unit load fluctuates, leading to problems such as ammonia escape and NOX emission exceeding the standard. In response to these problems, this paper proposes an SCR inlet NOx concentration prediction algorithm based on BMIFS-LSTM. An improved mutual information feature selection algorithm (BMIFS) is used to filter out the auxiliary variables with maximum correlation and minimum redundancy with NOx concentration, and reduce the coupling and dimensionality among the variables in the data set. The dominant and auxiliary variables are then fed together into a long short-term memory neural network (LSTM) to build a prognostic model. Simulation experiments are conducted using historical operation data of a 300 MW thermal power unit. The experimental results show that the algorithm in this paper reduces the average relative error by 3.45% and the root mean square error by 1.50 compared with the algorithm without auxiliary variable extraction, which can accurately reflect the real-time changes of NOx concentration at the SCR inlet, solve the problem of delay in NOx concentration measurement, and reduce the occurrence of atmospheric pollution caused by excessive NOx emissions.

In order to reduce the nitrogen oxides (NOx) emission of flue gas, a selective catalytic reduction (SCR) system must be installed. In general, the lag of the inlet NOx analyzer, the action of the NH3 injection valve and the feedforward signal are seriously delayed. Therefore, it is necessary to consider the measurement lag of inlet NOx on the NH3 injection flowrate control system. In this paper, the data-driven model of inlet NOx is proposed to improve control system, so as to avoid excessive or insufficient NH3 injection. First, the measurement lag time of inlet NOx is estimated by the blowback signal of a CEMS and the change process of the inlet O2 content. Then, an exponential model is used to predict the inlet NOx in advance, and recursive LSSVM is proposed to revise the output of the exponential model. Finally, the output of the final model is used as the feedforward signal for improved feedforward (IF) control. Based on IF control and PID control, the IF-PID control strategy for NH3 injection is proposed. The results show that the outlet NOx are close to the set value and meet the national environmental regulation. Furthermore, the average value of the NH3 injection flowrate remains unchanged. It shows that a better control effect and environmental sustainability are achieved without increasing the cost of NH3 injection.