A multi-indicator prediction method for NOx emission concentration and ammonia escape value for cement calciner system

Abstract

It is particularly important to accurately predict NOx emission concentration in cement production. As the cement industry is a process industry, there are many chemical reactions, coupling of front and back processes, and large fluctuations in production, resulting in time-delayed denitration data, strong coupling, and uncertainty, which makes it difficult to adequately extract the characteristics of the denitration data to achieve accurate prediction of NOx concentration. At the same time, excessive ammonia is used in production to reduce NOx concentration, resulting in increased ammonia escape and secondary hazards to the environment, therefore it is necessary to perform accurate multi-step prediction of NOx concentration and ammonia escape. To address these issues, this paper presented a new multicriteria deep learning hybrid model MI-ITBA. The model is constructed by connecting an improved causal dilated temporal convolutional network (ITCN) with bidirectional gated recurrent units (BiGRU) and a special attention mechanism, which enhances the ability to extract features from denitration sequence, using the attention mechanism to weigh the importance of different time steps and highlight the influence of key features on the prediction results. In addition, the time series (TS) of denitration containing time-delay information is designed in the input of the model to minimize the influence of time delay. Dynamic information support for denitration control was provided by multi-step prediction of NOx concentration at seven moments and ammonia escape value at three moments to retain the dynamics of the data. Compared with TCN, BiGRU, and TCN-BiGRU, MI-ITBA has a high prediction accuracy, which can provide an effective guide to realizing NOx emission reduction and accurate ammonia injection.