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.