Abstract
Accurately predicting NOx emissions during boiler combustion is of significance for the operation and control of the boiler combustion systems in coal-fired power plants. According to the characteristics of the boiler combustion process with strong disturbances, highly nonlinear and multivariate coupling, a fusion model based on mutual information variable selection and Hyperopt optimized GRU neural network (MI-HGRU) is proposed. The method can accurately select the parameters of boiler combustion process base on mutual information feature selection algorithm. A GRU neural network prediction model with Hyperopt optimization is established to achieve accurate prediction of NOx emission during boiler combustion. The modeling experiment was using a NOx emission dataset from a power plant boiler in Guangdong. The experimental results show that the MI-HGRU method has higher generalization ability and prediction accuracy than the RBF, LSSVM, RNN and LSTM neural networks, with an average accuracy of 99.4%.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Xue, W.B., Xu, Y.L., Wang, J.N., et al.: Ambient air quality impact of emissions from thermal power industry. China Environ. Sci. 36(05), 1281–1288 (2016)
GB 13271–2014 Emission standard of air pollutants for boiler. China Environmental Science Press (2014)
Li, J.J.: Experimental and Modeling Study on NOx Generation Mechanism in Circulating Fluidized Bed Boiler. Tsinghua University (2016)
Gao, M.M., Yu, H.Y., Lyu, J.F., et al.: Study on prediction model and optimal control of nitrogen oxides emission of circulating fluidized bed. Clean Coal Technol. 26(03), 46–51 (2020)
Zhang, H., Zhe, C.C., Ren, P.: Model for predicting boiler nitrogen oxide emissions based on least squares support vector machine. Jilin Electric Power 47(03), 18–20 (2019)
Yang, Q.: Study on NOx emission prediction of coal - fired boiler based on LSTM. Mech. Electr. Inf. 2019(05), 21–22 (2019)
Hong, C.S., Huang, J., Guan, Y.Y., et al.: Combustion control of power station boiler by coupling BP/RBF neural network and fuzzy rules. J. Eng. Thermal Energy Power 36(04), 142–148 (2021)
Peng, H., Long, F., Ding, C.: Feature selection based on mutual information criteria of max-dependency, max-relevance, and Min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1226–1238 (2005)
Vergara, J.R., Estévez, P.A.: A review of feature selection methods based on mutual information. Neural Comput. Appl. 24(1), 175–186 (2014)
He, F., Xiao, H.: Information entropy feature selection method to locate the cause of head narrowing of hot rolled strip. J. Eng. Sci. 37(S1), 45–50 (2015)
Tao, Z., Huiling, L., Wenwen, W., et al.: GA-SVM based feature selection and parameter optimization in hospitalization expense modeling. Appl. Soft Comput. 75, 323–332 (2019)
Nikbakht, S., Anitescu, C., Rabczuk, T.: Optimizing the neural network hyperparamters utilizing genetic algorithm. J. Zhejiang Univ. Sci. A (Appl. Phys. Eng.) 22(06), 407–426 (2021)
Ghawi, R., Pfeffer, J.: Efficient hyperparameter tuning with grid search for text categorization using kNN approach with BM25 similarity. Open Comput. Sci. 9(1), 160–180 (2019)
Xu, C., Li, S.Q., Li, Z.F., et al.; Application of reliefF-SVM with hyperparameter optimization in fault diagnosis of refrigerant charge. Chin. J. Refrigeration Technol. 41(01), 17–22+34 (2021)
Torres, J.F., Gutiérrez-Avilés, D., Troncoso, A., et al.: Random hyper-parameter search-based deep neural network for power consumption forecasting[C]//International Work-Conference on Artificial Neural Networks, pp. 259–269. Springer, Cham (2019)
Andonie, R., Florea, A.C.: Weighted random search for CNN hyperparameter optimization. Int. J. Comput. Commun. Control 15(2) (2020)
Acknowledgment
This paper is supported by the Key Technology Project of Foshan City in 2019 (1920001001367), National Natural Science and Guangdong Joint Fund Project (U2001201), Guangdong Natural Science Fund Project (2018A030313061, 2021A1515011243), Research and Development Projects of National Key fields (2018YFB1004202), Guangdong Science and Technology Plan Project (2019B010139001) and Guangzhou Science and Technology Plan Project (201902020016).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lin, K., Xiao, H., Jiang, W., Yang, J., Zhao, C., Lu, J. (2021). MI-HGRU: A Combine Method of Mutual Information and HGRU Neural Network for Boiler NOx Emission Prediction. In: Tan, Y., Shi, Y., Zomaya, A., Yan, H., Cai, J. (eds) Data Mining and Big Data. DMBD 2021. Communications in Computer and Information Science, vol 1453. Springer, Singapore. https://doi.org/10.1007/978-981-16-7476-1_39
Download citation
DOI: https://doi.org/10.1007/978-981-16-7476-1_39
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7475-4
Online ISBN: 978-981-16-7476-1
eBook Packages: Computer ScienceComputer Science (R0)