Prediction of NOX emission for coal-fired boilers based on deep belief network. (November 2018)

• Record Type: Journal Article
• Authors: Wang, Fang; Ma, Suxia; Wang, He; Li, Yaodong; Zhang, Junjie
• Is Part Of: Control engineering practice. Volume 80(2018)
• Page Start: 26
• Page End: 35
• Publication Date: 2018-11
• Subjects: Coal combustion simulation -- NOX emission prediction -- Deep belief network -- Mutual information-based variable selection; Automatic control -- Periodicals; 629.89
• DOI: 10.1016/j.conengprac.2018.08.003
• Languages: English
• ISSNs: 0967-0661

Abstract

Abstract: This study developed three types of deep belief network (DBN)-based models to estimate NO X emission in coal-fired power plants by a new data acquisition method. Based on the experimental data obtained by field experiments, the validated Fluent-based simulation results and the historical operating data from a database are used in the model calculations. Using mutual information, the model input set is optimized by the feature selection method. With the optimal inputs, three types of DBN-based NO X prediction models are constructed, in which the extreme learning machine, back propagation network, and radial basis function network are below the top layer of the DBN to serve as the regression model. The results indicate that the DBN-based models have a greater prediction accuracy with 0.93, 0.9, and 0.89 coefficients of determination and greater robustness compared to the three other NO X prediction models. Graphical abstract: Highlights: Historical operating data are validated by Fluent-based combustion simulation. Mutual information-based feature selection is used for selecting optimal inputs. Deep belief network(DBN) is applied to the NO X emission prediction of power plants. The effectiveness of DBN is validated by three kinds of DBN-based models.