Deep Learning Modeling for the NOx Emissions of Coal-fired Boiler Considering Time-delay Characteristics

被引：0

作者：

Tang Z. ^{[1
]}

Chai X. ^{[1
]}

Cao S. ^{[1
]}

Mu Z. ^{[2
]}

Pang X. ^{[2
]}

机构：

[1] School of Automation Engineering, Northeast Electric Power University, Jilin

[2] Electric Power Research Institute, State Grid Gansu Electric Power Corporation, Lanzhou

来源：

| 1600年 / Chinese Society for Electrical Engineering卷 / 40期

基金：

中国国家自然科学基金;

关键词：

Coal-fired boiler; Deep learning; Empirical mode decomposition; NO[!sub]x[!/sub] emission; Time delay;

D O I：

10.13334/j.0258-8013.pcsee.200573

中图分类号：

学科分类号：

摘要：

In order to establish a high precision NOx emission prediction model for coal-fired boilers, a deep learning-based NOx emission modeling algorithm considering the time-delay characteristics was proposed. First, the importance of characteristic variables was analyzed by combining mechanism analysis and lasso algorithm, and the variables most related to NOx emissions were selected. Furthermore, the time-delay correlation between the selected variables and NOx information and time domain information, and construct the modeling database. Finally, the deep neural network structure and parameters were designed to build a NOx emission prediction model. The experimental results based on the actual operation data of the thermal power plant show that the prediction error of the proposed algorithm is less than 2% under various working conditions, which can meet the requirements of actual production on the prediction accuracy. © 2020 Chin. Soc. for Elec. Eng.

引用

页码：6633 / 6643

页数：10

共 34 条

[11]

Gu Lijing, Li Yonghua, Li Lu, Hybrid model prediction of utility boiler combustion optimization, Proceedings of the CSEE, 35, 9, pp. 2231-2237, (2015)

[12]

Zheng Ligang, Zhou Hao, Wang Chunlin, Et al., Combining support vector regression and ant colony optimization to reduce NOx emissions in coal-fired utility boilers, Energy & Fuel, 22, 2, pp. 1034-1040, (2008)

[13]

Xu Chang, Lv Jianhong, Artificial neural networks model for NOx emissions in a pulverized-coal power station boiler on generation mechanism, Proceeding of the CSEE, 24, 10, pp. 233-237, (2004)

[14]

Bengio Y., Deep learning of representations for unsupervised and transfer learning, Workshop on Unsupervised and Transfer Learning Challenge and Workshop, 7, pp. 1-20, (2012)

[15]

Zeng Wenhao, Zhu Xiaohua, Li Hongtao, Et al., Subarray reconstruction 2D-DOA estimation algorithm based on matrix completion, Journal of Nanjing University of Science and Technology, 41, 3, pp. 337-343, (2017)

[16]

Li Hongtao, He Yapeng, Zhu Xiaohua, Et al., Eigenvector-based linearly constrained minimum variance adaptive pattern control algorithm, Journal of Nanjing University of Science and Technology, 35, 4, pp. 529-533, (2011)

[17]

Li Jian, Stoica P, Wang Zhisong, On robust capon beamforming and diagonal loading, IEEE Transactions on Signal Processing, 51, 7, pp. 1702-1715, (2003)

[18]

Wang Fang, Ma Suxia, Wang He, Et al., Prediction of NOx emission for coal-fired boilers based on deep belief network, Control Engineering Practice, 80, pp. 26-35, (2018)

[19]

Tang Zhenhao, Zhang Zijun, The multi-objective optimization of combustion system operations based on deep data-driven models, Energy, 182, pp. 37-47, (2019)

[20]

Yang Yang, Zhao Jiwen, Song Juncai, Et al., Structural optimization of air-core permanent magnet synchronous linear motors based on deep neural network models, Proceedings of the CSEE, 39, 20, pp. 6085-6094, (2019)

← 1 2 3 4 →