Intelligent prediction model of CFB boiler bed temperature based on parallel control theory

doi:10.3969/j.issn.2097-0706.2022.03.008

Abstract

Abstract:

To pursue the carbon peaking and carbon neutrality,with the accelerating development of renewable energy oriented power system and rising of environment protection awareness, thermal power units have to operate under extreme operating conditions. But the traditional mechanism modelling can hardly realize the accurate prediction on CFB boiler bed temperature. Based on parallel control theory,a real system can operate following the guidance of its virtual counterpart based on computational experiments. The virtual system takes Temporal Pattern Attention for Multivariate Time Series Forecasting （TPA-LSTM）model which can improve the traditional LSTM model's recognition ability of the temporal segments in industrial process by introducing temporal attention as the attention mechanism. Taking gray correlation analysis method to screen the data of the real system can improve the accuracy of the computational experiments of the virtual system. The analysis results show that the mean absolute deviation and mean absolute percent error of the predicted bed temperature can be reduced to 0.131 7 ℃ and 0.014 29%. The model realizes the accurate prediction on CFB boiler bed temperature.

Key words: carbon neutrality, parallel control system, LSTM neural network, attention mechanism, grey correlation degree analysis, virtual system, circulating fluidized bed, bed temperature

CLC Number:

TK229.6⁺6：TP273

LIU Wenhui, YAN Bowen, WU Jiang, REN Yijun, KONG Weizheng, CHEN Jiyu. Intelligent prediction model of CFB boiler bed temperature based on parallel control theory[J]. Integrated Intelligent Energy, 2022, 44(3): 50-57.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Table 1

Fig.6

Table 2

Fig.7

Fig.8

Table 3

References 19

[1]	姚禹歌, 黄中, 张缦, 等. 中国循环流化床燃烧技术的发展与展望[J]. 热力发电, 2021, 50(11):13-19.
	YAO Yuge, HUANG Zhong, ZHANG Man, et al. Development and prospect of circulating fluidized bed combustion technology in China[J]. Thermal Power Generation, 2021, 50(11):13-19.
[2]	LYU J, YANG H, LING W, et al. Development of a supercritical and an ultra-supercritical circulating fluidized bed boiler[J]. Frontiers in Energy, 2019, 13(1):114-119. doi: 10.1007/s11708-017-0512-4
[3]	KE X, LI D, LI Y, et al. 1-Dimensional modelling of in-situ desulphurization performance of a 550 MWe ultra-supercritical CFB boiler[J]. Fuel, 2021, 290:120088.
[4]	郭伟, 乔东东, 李涛, 等. CFBB床温LMPC-PID控制[J]. 控制工程, 2019, 26(9):1648-1654.
	GUO Wei, QIAO Dongdong, LI Tao, et al. LMPC-PID control of CFBB bed temperature[J]. Control Engineering, 2019, 26(9):1648-1654.
[5]	GUNGOR A, ESKIN N. Hydrodynamic modeling of a circulating fluidized bed[J]. Powder Technology, 2007, 172(1):1-13. doi: 10.1016/j.powtec.2006.10.035
[6]	PALLARES D, JOHNSSON F. Macroscopic modelling of fluid dynamics in large-scale circulating fluidized beds[J]. Progress in Energy & Combustion Science, 2006, 32(5/6):539-569.
[7]	王飞跃. 平行系统方法与复杂系统的管理和控制[J]. 控制与决策, 2004(5):485-489,514.
	WANG Feiyue. Parallel systems approach and management and control of complex systems[J]. Control and Decision-Making, 2004(5):485-489,514.
[8]	YUE H, TURTON R, PARK J, et al. Dynamic model of the riser in circulating fluidized bed[J]. Powder Technology, 2006, 163(1/2):23-31. doi: 10.1016/j.powtec.2006.01.003
[9]	曹建宗, 林宸雨, 陈文通, 等. 现代预测和优化算法在脱硫系统运行中的应用[J]. 华电技术, 2020, 42(3):59-66.
	CAO Jianzong, LIN Chenyu, CHEN Wentong, et al. Application of modern prediction and optimization algorithms in FGD systems[J]. Huadian Technology, 2020, 42(3):59-66.
[10]	倪绍佑. 基于大数据的CFB燃煤锅炉脱硫系统建模研究[D]. 杭州:浙江大学, 2021.
[11]	张媛媛, 曲江源, 王鹏程, 等. 超低负荷循环流化床机组NO_x超低排放的GA-BP算法优化模型[J]. 热力发电, 2021, 50(12):35-42.
	ZHANG Yuanyuan, QU Jiangyuan, WANG Pengcheng, et al. GA-BP algorithm optimization model for ultra-low NO_x emission of ultra-low load circulating fluidized bed units[J]. Thermal Power Generation, 2021, 50(12):35-42.
[12]	韩义, 张奇月, 王研凯, 等. 基于BP神经网络的300 MW循环流化床机组出力预测[J]. 华电技术, 2020, 42(12):1-6.
	HAN Yi, ZHANG Qiyue, WANG Yankai, et al. Performance prediction on a 300 MW CFB based on BP neural network[J]. Huadian Technology, 2020, 42(12):1-6.
[13]	崔博洋, 王永林, 王云, 等. 基于长短期记忆神经网络的吸收塔pH值预测模型[J]. 华电技术, 2020, 42(9):32-36.
	CUI Boyang, WANG Yonglin, WANG Yun, et al. Prediction model for the pH value of absorption tower slurry based on LSTM neural networks[J]. Huadian Technology, 2020, 42(9):32-36.
[14]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Compution, 1997, 9(8):1735-1780.
[15]	GERS F A, SCHMIDHUBER J, CUMMINS F. Learning to forget: Continual prediction with LSTM[J]. Neural Computation, 2000, 12(10):2451-2471 doi: 10.1162/089976600300015015
[16]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Conference on Neural Information Processing Systems (NIPS 2017). Long Beach, 2017.
[17]	SHIH S Y, SUN F K, LEE H Y. Temporal pattern attention for multivariate time series forecasting[J]. Machine Learning, 2019, 108(8):1421-1441. doi: 10.1007/s10994-019-05815-0
[18]	DENG J L. Introduction to grey system theory[J]. Journal of Grey System, 1989, 1(1):1-24.
[19]	KINGMA D P, BA J L. Adam: A method for stochastic optimization[C]//Proceedings of the 3rd International Conference for Learning Representations—ICLR 2015. San Diego, 2015.

编号	输入变量	编号	输入变量
0	AGC负荷指令	10	左侧下部二次风风量
1	燃料量	11	右侧下部二次风风量
2	^#4给煤机转速	12	左侧上部二次风风量
3	^#3给煤机转速	13	右侧上部二次风风量
4	^#2给煤机转速	14	左侧一次风风量
5	^#1给煤机转速	15	右侧一次风风量
6	冷渣器A转速	16	左侧床温
7	冷渣器C转速	17	右侧床温
8	左侧回料阀阀门开度	18	左侧床压
9	右侧回料阀阀门开度	19	右侧床压

超参数	值
时间步长	150
LSTM层神经元数量	32
LSTM模型层数	4
卷积核大小	40
批训练的数据集容量	100
学习率	0.001
卷积核数量	32