Multi-objective prediction for denitration systems in cement: an approach combining process analysis and bi-directional long short-term memory network.

Abstract

Selective Non-Catalytic Reduction (SNCR) can improve the denitration process and reduce NOx emissions by accurizing prediction of NOx concentration and ammonia escape. However, there are inevitable time delays and nonlinearity problems in the prediction of NOx emission. To reduce NOx concentration quickly in SNCR, excessive ammonia spraying often causes a large amount of ammonia to escape, resulting in secondary pollution. Therefore, it is particularly important to monitor ammonia escape. To solve the above problems, this paper proposes a framework by specifically analyzing the cement denitration process and combining a multi-objective time series bi-directional long short-term memory network (MT-BiLSTM). Among them, the model achieves multi-objective prediction of NOx emission concentration and ammonia escape simultaneously. In addition, time series containing delay information are introduced in the input layer to eliminate the influence of delay. Based on the bi-directional LSTM model, the dropout strategy is adopted to improve the generalization of the model and the Adam optimizer is applied to improve the network performance. Besides, through the multi-step prediction of NOx emission at 3 time points, the dynamic nature of the data is preserved, which provides dynamic information support for realizing the automation of denitration system. The prediction performance of the MT-BiLSTM model is experimentally validated, and the results demonstrate that it can reliably predict both NOx and ammonia escape. The model achieves more accurate and reliable results for the prediction of flue gas concentrations compared with other methods such as SVR, DTR and LSTM. Therefore, the MT-BiLSTM model provides a basis for achieving NOx emission reduction and accurate ammonia injection.