부산대학교 도서관

This paper investigates the real-time prediction of nitrogen oxides (NO x) emission by using around 17000 samples involved in a collection of three-day real data from a waste incineration power plant. To disclose the relationship between the ammonia (NH 3) ejection and NO x emission, we choose the NO x reduction from inlet to outlet rather than the NO x concentration monitored by continuous emission monitoring system (CEMS). A hybrid procedure is developed to select appropriate features from the large and unsynchronized data, with which we establish a model based on the gradient boosting decision tree (GBDT) for the prediction. Computational experiments demonstrate that, with root mean square error (RMSE) values being 1.851 and 3.593 for training and test data, respectively, GBDT outperforms its two popular counterparts, supporting vector regression (SVR) and long short-term memory (LSTM). Shapley additive explanations (SHAP) is also conducted for analysis. • NOx reduction as a proxy to disclose true relationship between NOx emission and NH 3. • The maximal information coefficient is used to eliminate redundant features. • The differential evolution is used to determine the lag-periods of selected feature. • GBDT is verified to outperform SVR and LSTM in predicting NOx emission. • SHAP is conducted to analyze the mechanism of GBDT in depth. [ABSTRACT FROM AUTHOR]