Modeling of boiler variable load combustion system based on gradient lifting decision tree and improved bidirectional threshold cycle unit

Guotian Yang, Yuchen He, Xin Li, Xinli Li

Article ID: 1528
Vol 5, Issue 1, 2022

VIEWS - 274 (Abstract) 337 (pdf)

Abstract


Boiler combustion system is a typical dynamic system with many variables, strong coupling, large-lag, and multiple input/output. It is very difficult to build a combustion system model that conforms to the actual working conditions. This paper presents a new modeling method of boiler combustion system based on bidirectional threshold cycle unit (Bi-GRU), and establishes the training model of combustion system under variable load (low, medium and high load)conditions. At the same time, gradient lifting decision tree (GBDT) is used to reduce the dimension of input characteristic matrix. GBDT model can evaluate the weight of input features under different loads and outputs, and can identify the feature with the largest weight proportion on the basis of retaining the original physical meaning of the feature. The feature selection model based on GBDT can not only reduce the original input dimension, but also provide theoretical guidance for the subsequent combustion control strategy. The calculation results of actual operation data show that the new combustion system model established by Bi-GRU and GBDT can accurately reflect the dynamic changes of main steam flow, main steam pressure and NOx emission under different loads. Compared with the traditional recurrent neural network (RNN) model, the accuracy and performance of the new model in this paper are significantly improved, and the structure is simple and the amount of calculation is small.

Keywords


Boiler Combustion System; Bidirectional Threshold Circulation Unit; Gradient Lifting Decision Tree; Output Characteristics

Full Text:

pdf


References


1. Wang Z, Liu H, Chen Y. Process control systems and instruments. Beijing: Machinery Industry Press; 2006. p. 1.

2. Pan H, Zhong W, Wang Z, et al. Optimization of industrial boiler combustion control system based on genetic algorithm. Computers and Electrical Engineering 2018; 70: 987-997.

3. Tang Z, Zhang Z. The multi-objective optimization of combustion system operations based on deep data-driven models. Energy 2019; 182: 37-47.

4. Zhao M, Wang P, Liang J, et al. Modeling of reference value of boiler operating parameters based on weighted fuzzy C-means clustering algorithm. Thermal Power Generation 2019; 48(1): 12-17.

5. Li C, Bai F, Hu S. Establishment of system model and parameters optimization of HRSG combined cycle units. Thermal Power Generation 2021; 50(2): 74-83.

6. Zhen C, Liu H. Prediction model of NOx emission from coal-fired boiler based on multi-model clustering ensemble. Thermal Power Generation 2019; 48(4): 33-40.

7. Niu Y, Du M, Ge W, et al. A dynamic nonlinear model for a once-through boiler-turbine unit in low load. Applied Thermal Engineering 2019; 161: 113880.

8. Xu L, Yuan J. Online identification of the lower heating value of the coal entering the furnace based on the boiler-side whole process models. Fuel 2015; 161: 68-77.

9. Henryk R, Wojciech S. Hybrid model of steam boiler. Energy 2009; 35(2): 1107-1113.

10. Eddy HC, Gao H. Estimation of NOx emissions from coal-fired utility boilers. Fuel 2010; 89(10): 2977-2984.

11. Sandro DS, Olivier J, Myriam LL, et al. Using a genetic algorithm and CFD to identify low NOx configurations in an industrial boiler. Fuel 2015; 158: 672-683.

12. Choi CR, Kim CN. Numerical investigation on the flow, combustion and NOx emission characteristics in a 500 MWe tangentially fired pulverized-coal boiler. Fuel 2009; 88(9): 1720-1731.

13. Dong X, Wang H, Zhao X. Model reference neural network control for boiler combustion system. Proceedings of 2005 International Conference on Machine Learning and Cybernetics; 2005 Aug 1821; Guangzhou, China: IEEE; 2005. p. 12.

14. Gu Y, Zhao W, Wu Z. Online adaptive least squares support vector machine and its application in util-ity boiler combustion optimization systems. Journal of Process Control 2011; 21(7): 1040-1048.

15. Chen J, Chan L, Cheng Y. Gaussian process re-gression based optimal design of combustion systems using flame images. Applied Energy 2013; 111: 153-160.

16. Xu X, Chen Q, Ren M, et al. Combustion optimization for coal fired power plant boilers based on improved distributed ELM and distributed PSO. Energies 2019; 12(6): 1036.

17. Rao H, Shi X, Rodrigue AK, et al. Feature selection based on artificial bee colony and gradient boosting decision tree. Applied Soft Compu-ting 2018; 74: 634-642.

18. Tian D, He G, Wu J, et al. An accurate eye pupil localization approach based on adaptive gradient boosting decision tree. 2016 Visual Communications and Image Processing; 2016 Nov 27-30; Chengdu, China: IEEE; 2016.

19. Xu Z X, Huang G, Weinberger KQ, et al. Gradient boosted feature selection. Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining; 2014 Aug 24; 2014. p. 522-531.

20. Gtanes A, Mohamed AR, Hinton G. Speech recognition with deep recurrent neural networks. IEEE International Conference on Acoustic; 2013 May 26-31; Vancouver, BC, Canada: IEEE; 2013.

21. Cho K, Merrienboer BV, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Naturel Language Precessing (EMNLP); 2014 Oct 25-29; Doha, Qatar; 2014. p. 1724-1734.

22. Jaihuni M, Basak JK, Khan F, et al. A partially amended hybrid Bi-GRU-ARIMA model (PAHM) for predicting solar irradiance in short and very-short terms. Energies 2020; 13: 435.




DOI: https://doi.org/10.24294/tse.v5i1.1528

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Creative Commons License

This site is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.