基于混合建模的水泥生料分解过程动态特性研究

doi:10.11949/0438-1157.20211646

摘要/Abstract

摘要：

为掌握水泥分解炉运行过程的动态特性，采用机理建模与神经网络相结合的方法构建了水泥分解炉一维特性模型，并结合工业数据对该方法的可行性进行验证。结果表明，模型能够准确地计算炉内温度、气体浓度等参数，具有良好的泛化性能。基于所提出的模型，研究了炉内各状态参数的稳态分布特性。此外，对喷煤量、生料下料量、喷氨量以及高温风机转速等操作变量进行阶跃实验，分析上述操作变量改变时分解炉出口温度及出口NO _x 含量的动态响应情况。研究所得相关动态特性规律可以为控制系统的分析、设计和优化提供参考与依据。

关键词: 水泥分解炉, 混合模型, 动态仿真, 神经网络, 多相反应器

Abstract:

In order to understand the dynamic characteristics of cement precalciner, a one-dimensional hybrid model combined of reaction mechanism and neural network was constructed. Feasibility of this method was verified by comparison with industrial data. The results show that the hybrid model can accurately calculate temperature, gas concentration and other parameters in the furnace. Distribution of each parameter along the direction of flue gas flow is consistent with the actual situation. Based on the proposed model, the steady-state distribution characteristics of various state parameters in the furnace were studied. Furthermore, step response tests were carried out. Dynamic responses of temperature and NO _x concentration at furnace outlet were researched when the coal feeding rate, limestone feeding rate, ammonia injection rate and other manipulated parameters were changed respectively. The relevant dynamic characteristics obtained from the research can provide reference for the analysis, design and optimization of the control system.

Key words: cement precalciner, hybrid model, dynamic simulation, neural networks, multiphase reactor

中图分类号:

TQ 172

戚子豪, 钟文琪, 陈曦, 周冠文, 赵小亮, 辛美静, 陈翼, 朱永长. 基于混合建模的水泥生料分解过程动态特性研究[J]. 化工学报, 2022, 73(5): 2039-2051.

Zihao QI, Wenqi ZHONG, Xi CHEN, Guanwen ZHOU, Xiaoliang ZHAO, Meijing XIN, Yi CHEN, Yongchang ZHU. Research on dynamic characteristics of cement raw meal decomposition process based on hybrid modeling[J]. CIESC Journal, 2022, 73(5): 2039-2051.

图/表 17

图1 分解炉模型及控制体划分

Fig.1 Precalciner model and division of control volume

表1 分解炉参数

Table 1 Parameters of calciner

名称	数值
分解炉高度/mm	78
分解炉主体直径/m	8.4
轴向长度/m	98.6
气体停留时间/s	7~8
进料量/(t/h)	360
生料温度/℃	800
分解炉喂煤量/(t/h)	11
投煤温度/℃	60
喷氨量/(kg/吨熟料)	3
氨水浓度/%	20
排烟温度/℃	880

表2 燃料特性参数

Table 2 Parameters of fuel characteristic

元素分析/%						工业分析/%					低位发热量/(MJ/kg)
C_ad	H_ad	O_ad	S_ad	N_ad		A_ad	FC_ad	V_ad	M_ad		低位发热量/(MJ/kg)
67.73	3.89	3.59	1.03	1.41		22.34	54.32	20.21	2.11		23.93

图2 混合模型框架

Fig.2 Framework of hybrid model

图3 神经网络参数更新过程

Fig.3 Update process of neural network parameter

图4 固气停留时间比的影响

Fig.4 Effect of solid-gas residence time ratio

表3 计算结果

Table 3 Calculation result

预测对象	计算值	实际值
出口温度/K	1164	1160
出口压力/Pa	-900	-851
碳酸钙分解率/%	96	95
煤炭燃尽率/%	98	—
O₂含量/%	2.43	2.27
CO含量/%	0.0195	0.0217
NO _x 含量/（mg/m³）	75	66

图5 温度及NO x 浓度的模型预测值与真实值对比

Fig.5 Comparison of model predicted value and real value of temperature and NO x concentration

图6 计算误差分布

Fig.6 Error distribution

表4 训练集与测试集误差对比

Table 4 Comparison of training error and test error

项目	训练集		测试集
项目	RMSE	MAPE	RMSE	MAPE
温度	4.06 K	0.34%	6.72 K	0.50%
NO _x 浓度	6.22 mg/m³	7.27%	7.35 mg/m³	9.01%

图7 模型预测值与真实值对比

Fig.7 Comparison of model predicted value and real value

图8 给煤量阶跃变化

Fig.8 Step change of coal feed

图9 生料量阶跃变化

Fig.9 Step change of limestone

图10 喷氨量阶跃变化

Fig.10 Step change of ammonia injection

图11 高温风机转速阶跃变化

Fig.11 Step change of high temperature fan speed

附表1 炉内挥发分、焦炭燃烧与碳酸钙分解计算公式

Appendix 1　Calculation formulas for volatile matter， coke combustion and calcium carbonate decomposition

	变量名称	方程		变量名称	方程
挥发分析出	挥发分析出量	$V v o l = X V M - A - B A = e x p (26.41 - 3.691 l n T + 1.15 X V M) B = 0.2 (X V M - 10.9)$	焦炭燃烧	氧气扩散系数	$D g T, P = D g T 0, P 0 T T 0 1.75 P 0 P$
				Reynolds 数	$R e T = A r ε 4.75 18 + 0.61 A r ε 4.74 0.5$
				Schmidt 数	$S c = μ g ρ g D g$
	挥发分含量	$Y C H 4 = 0.201 - 0.469 X V M + 0.241 X V M 2 Y H 2 = 0.157 - 0.868 X V M + 1.388 X V M 2 Y C O 2 = 0.135 - 0.900 X V M + 1.906 X V M 2 Y C O = 0.428 - 2.653 X V M + 4.845 X V M 2 Y H 2 O = 0.409 - 2.389 X V M + 4.554 X V M 2 Y t a r = - 0.325 + 7.279 X V M - 12.880 X V M 2$		Schmidt 数	$S c = μ g ρ g D g$
				Archimedes 数	$A r = g d p 3 ρ g ρ p - ρ g μ$
			碳酸钙分解	分解速率	$k C a C O 3 = 1 k p h + 1 η k c h - 1$
焦炭燃烧	焦炭燃烧化学机械因子	$? = 2 K r + 2 K r + 2 d p < 0.05 m m 2 K r + 2 - K r 0.095 d p - 0.005 0.05 m m < d p ≤ 1 m m K r + 2 d p > 1.0 m m$		孔隙效率因子	$η = t a n h d 6 k ? c h ? D / d 6 k ? c h ? D$
	焦炭燃烧化学机械因子			分子扩散系数	$D = 1 D b i n + 1 D k n u - 1$
	CO/CO₂浓度生成比	$K r = 2515 e x p - 5.19 × 104 R g T c$			$D b i n = 0.0266 T 1.5 p M A B 0.5 σ A B 2 ω d$
	颗粒表面温度	$T c = T + 6.6 × 104 C O 2$			$D k n u = d p o r e 3 8 R C O 2 T π 0.5$
	单个焦炭颗粒反应速率	$r c = π d c 2 k c C O 2$		扩散系数校正因子	$? = ε p τ p 2$
	焦炭燃烧反应速率	$k c = 1 / 1 ? k c d + 1 k c s$		CO₂平衡分压	$p e q = 4.137 × 1012 e x p - 20474 T$
	化学反应速率	$k c s = 8710 e x p - - 1.4947 × 108 R T c$		化学反应速率	$k c h = k D p e q - p C O 2 M C a C O 3 1000$ $k D = 1.22 × 10 - 5 e x p - 4026 T$
	扩散反应速率	$k c d = S h D g d c$		扩散反应速率	$k p h = 12 D S h R C O 2 d C a C O 3 T p r e f$
	Sherwood 数	$S h = 2 + 0.6 R e T 0.5 S c 0.33$		碳酸钙质量变化速率	$d m C a C O 3 d t = - k C a C O 3 π d C a C O 3 2$

附表1 炉内挥发分、焦炭燃烧与碳酸钙分解计算公式

Appendix 1　Calculation formulas for volatile matter， coke combustion and calcium carbonate decomposition

	变量名称	方程		变量名称	方程
挥发分析出	挥发分析出量	$V v o l = X V M - A - B A = e x p (26.41 - 3.691 l n T + 1.15 X V M) B = 0.2 (X V M - 10.9)$	焦炭燃烧	氧气扩散系数	$D g T, P = D g T 0, P 0 T T 0 1.75 P 0 P$
				Reynolds 数	$R e T = A r ε 4.75 18 + 0.61 A r ε 4.74 0.5$
				Schmidt 数	$S c = μ g ρ g D g$
	挥发分含量	$Y C H 4 = 0.201 - 0.469 X V M + 0.241 X V M 2 Y H 2 = 0.157 - 0.868 X V M + 1.388 X V M 2 Y C O 2 = 0.135 - 0.900 X V M + 1.906 X V M 2 Y C O = 0.428 - 2.653 X V M + 4.845 X V M 2 Y H 2 O = 0.409 - 2.389 X V M + 4.554 X V M 2 Y t a r = - 0.325 + 7.279 X V M - 12.880 X V M 2$		Schmidt 数	$S c = μ g ρ g D g$
				Archimedes 数	$A r = g d p 3 ρ g ρ p - ρ g μ$
			碳酸钙分解	分解速率	$k C a C O 3 = 1 k p h + 1 η k c h - 1$
焦炭燃烧	焦炭燃烧化学机械因子	$? = 2 K r + 2 K r + 2 d p < 0.05 m m 2 K r + 2 - K r 0.095 d p - 0.005 0.05 m m < d p ≤ 1 m m K r + 2 d p > 1.0 m m$		孔隙效率因子	$η = t a n h d 6 k ? c h ? D / d 6 k ? c h ? D$
	焦炭燃烧化学机械因子			分子扩散系数	$D = 1 D b i n + 1 D k n u - 1$
	CO/CO₂浓度生成比	$K r = 2515 e x p - 5.19 × 104 R g T c$			$D b i n = 0.0266 T 1.5 p M A B 0.5 σ A B 2 ω d$
	颗粒表面温度	$T c = T + 6.6 × 104 C O 2$			$D k n u = d p o r e 3 8 R C O 2 T π 0.5$
	单个焦炭颗粒反应速率	$r c = π d c 2 k c C O 2$		扩散系数校正因子	$? = ε p τ p 2$
	焦炭燃烧反应速率	$k c = 1 / 1 ? k c d + 1 k c s$		CO₂平衡分压	$p e q = 4.137 × 1012 e x p - 20474 T$
	化学反应速率	$k c s = 8710 e x p - - 1.4947 × 108 R T c$		化学反应速率	$k c h = k D p e q - p C O 2 M C a C O 3 1000$ $k D = 1.22 × 10 - 5 e x p - 4026 T$
	扩散反应速率	$k c d = S h D g d c$		扩散反应速率	$k p h = 12 D S h R C O 2 d C a C O 3 T p r e f$
	Sherwood 数	$S h = 2 + 0.6 R e T 0.5 S c 0.33$		碳酸钙质量变化速率	$d m C a C O 3 d t = - k C a C O 3 π d C a C O 3 2$

附表2 炉内均相反应速率

Appendix 2　Homogeneous reaction rate in the furnace

化学反应	催化剂	反应速率
（1） $2 H 2 + O 2 → 2 H 2 O$	—	$r 1 = k 1 C H 2 1.5 C O 2$	$k 1 = 1.63 × 109 T 1.5 e x p - 3420 T$
（2） $C H 4 + 32 O 2 → C O + H 2 O$	—	$r 2 = k 2 C C H 4 0.7 C O 2 0.8$	$k 2 = 1.585 × 1010 e x p - 24157 T$
（3） $C O + 12 O 2 → C O 2$	—	$r 3 = k 3 C C O C H 2 O 0.5 C O 2 0.3$	$k 3 = 1.9 × 106 e x p - 8050 T$
（4） $t a r + 7.5 O 2 → 6 C O 2 + H 2 O$	—	$r 4 = k 4 C t a r C O 2$	$k 4 = 3.8 × 107 e x p - 0.555 × 108 T$
（5） $N H 3 + N O + 14 O 2 → N 2 + 32 H 2 O$	—	$r 5 = k 5 C N H 3 C N O$	$k 5 = 2.45 × 1017 e x p - 29400 T$
	CaO	$r 5' = k 5' C N H 3$	$k 5' = 0.73 × 106 e x p - 7000 T$
（6） $N H 3 + 54 O 2 → N O + 32 H 2 O$	—	$r 6 = k 6 C N H 3$	$k 6 = 2.21 × 1014 e x p - 38160 T$
	char	$r 6' = k 6' C N H 3 C O 2$	$k 6' = 4.95 × 1012 e x p - 15000 T$
	CaO	$r 6 ″ = k 6 ″ C N H 3 C O 2$	$k 6 ″ = 2.67 × 1010 e x p - 10000 T$
（7） $2 N H 3 + 32 O 2 → N 2 + 3 H 2 O$	char	$r 7 = k 7 C N H 3 C O 2$	$k 7 = 1.58 × 1013 e x p - 15000 T$
	CaO	$r 7' = k 7' C N H 3 C O 2$	$k 7' = 6.65 × 109 e x p - 10000 T$
（8） $N O + C O → C O 2 + 12 N 2$	char	$r 8 = k 8 p N O k 81 p N O + k 82 k 8 p N O + k 81 p N O + k 82$	$k 8 = 2.1 × 10 - 6 e x p - 13000 T$
			$k 81 = 7.3 × 10 - 9 e x p - 9560 T$
			$k 82 = 0.015 e x p - 20100 T$
	CaO	$r 8' = k 8' C N O C C O$	$k 8' = 1.58 × 108 e x p - 8920 T$
（9） $N O + H 2 → H 2 O + 12 N 2$	Char	$r 9 = k 9 C N O C H 2$	$k 9 = 4.6 T e x p - 12120 T$
	CaO	$r 9' = k 9' C N O C H 2$	$k 9' = 7 × 1010 e x p - 9320 T$
（10） $H C N + O 2 → N O + C O$	—	$r 10 = k 10 ρ C O 2 b C H C N$	$k 10 = 1011 e x p - 33700 T$

附表2 炉内均相反应速率

Appendix 2　Homogeneous reaction rate in the furnace

化学反应	催化剂	反应速率
（1） $2 H 2 + O 2 → 2 H 2 O$	—	$r 1 = k 1 C H 2 1.5 C O 2$	$k 1 = 1.63 × 109 T 1.5 e x p - 3420 T$
（2） $C H 4 + 32 O 2 → C O + H 2 O$	—	$r 2 = k 2 C C H 4 0.7 C O 2 0.8$	$k 2 = 1.585 × 1010 e x p - 24157 T$
（3） $C O + 12 O 2 → C O 2$	—	$r 3 = k 3 C C O C H 2 O 0.5 C O 2 0.3$	$k 3 = 1.9 × 106 e x p - 8050 T$
（4） $t a r + 7.5 O 2 → 6 C O 2 + H 2 O$	—	$r 4 = k 4 C t a r C O 2$	$k 4 = 3.8 × 107 e x p - 0.555 × 108 T$
（5） $N H 3 + N O + 14 O 2 → N 2 + 32 H 2 O$	—	$r 5 = k 5 C N H 3 C N O$	$k 5 = 2.45 × 1017 e x p - 29400 T$
	CaO	$r 5' = k 5' C N H 3$	$k 5' = 0.73 × 106 e x p - 7000 T$
（6） $N H 3 + 54 O 2 → N O + 32 H 2 O$	—	$r 6 = k 6 C N H 3$	$k 6 = 2.21 × 1014 e x p - 38160 T$
	char	$r 6' = k 6' C N H 3 C O 2$	$k 6' = 4.95 × 1012 e x p - 15000 T$
	CaO	$r 6 ″ = k 6 ″ C N H 3 C O 2$	$k 6 ″ = 2.67 × 1010 e x p - 10000 T$
（7） $2 N H 3 + 32 O 2 → N 2 + 3 H 2 O$	char	$r 7 = k 7 C N H 3 C O 2$	$k 7 = 1.58 × 1013 e x p - 15000 T$
	CaO	$r 7' = k 7' C N H 3 C O 2$	$k 7' = 6.65 × 109 e x p - 10000 T$
（8） $N O + C O → C O 2 + 12 N 2$	char	$r 8 = k 8 p N O k 81 p N O + k 82 k 8 p N O + k 81 p N O + k 82$	$k 8 = 2.1 × 10 - 6 e x p - 13000 T$
			$k 81 = 7.3 × 10 - 9 e x p - 9560 T$
			$k 82 = 0.015 e x p - 20100 T$
	CaO	$r 8' = k 8' C N O C C O$	$k 8' = 1.58 × 108 e x p - 8920 T$
（9） $N O + H 2 → H 2 O + 12 N 2$	Char	$r 9 = k 9 C N O C H 2$	$k 9 = 4.6 T e x p - 12120 T$
	CaO	$r 9' = k 9' C N O C H 2$	$k 9' = 7 × 1010 e x p - 9320 T$
（10） $H C N + O 2 → N O + C O$	—	$r 10 = k 10 ρ C O 2 b C H C N$	$k 10 = 1011 e x p - 33700 T$

参考文献 45

1	Gungor A. Simulation of NO _x emission in circulating fluidized beds burning low-grade fuels[J]. Energy & Fuels, 2009, 23(5): 2475-2481.
2	Gungor A. One dimensional numerical simulation of small scale CFB combustors[J]. Energy Conversion and Management, 2009, 50(3): 711-722.
3	Wu H C, Yang C, He H X, et al. A hybrid simulation of a 600 MW supercritical circulating fluidized bed boiler system[J]. Applied Thermal Engineering, 2018, 143: 977-987.
4	Ke X W, Li D F, Li Y R, et al. 1-Dimensional modelling of in-situ desulphurization performance of a 550 MWe ultra-supercritical CFB boiler[J]. Fuel, 2021, 290: 120088.
5	毛玉如. 循环流化床富氧燃烧技术的试验和理论研究[D]. 杭州: 浙江大学, 2003.
	Mao Y R. Theoretical and experimental study on oxygen-enriched combustion technology in circulating fluidized bed[D]. Hangzhou: Zhejiang University, 2003.
6	魏莉, 钟文琪, 邵应娟. 煤流化床加压富氧燃烧过程的动态特性[J]. 东南大学学报(自然科学版), 2020, 50(2): 358-367.
	Wei L, Zhong W Q, Shao Y J. Dynamic characteristics of pressurized oxy-fuel combustion in fluidized bed[J]. Journal of Southeast University (Natural Science Edition), 2020, 50(2): 358-367.
7	戚龙周. 600MW超临界直流锅炉热力性能建模与仿真研究[D]. 武汉: 华中科技大学, 2012.
	Qi L Z. Modeling and simulation research on thermodynamic performances of 600MW supercritical once through boiler[D]. Wuhan: Huazhong University of Science and Technology, 2012.
8	Magnanelli E, Tranås O L, Carlsson P, et al. Dynamic modeling of municipal solid waste incineration[J]. Energy, 2020, 209: 118426.
9	谢海立. 垃圾焚烧炉排炉的炉内过程动态特性数字仿真[D]. 南京: 东南大学, 2017.
	Xie H L. Numerical simulation on the dynamic characteristics of combustion in mechanical grate incinerator[D]. Nanjing: Southeast University, 2017.
10	Jensen L S. NO _x from cement production-reduction by primary measures[D]. Denmark: Technical University of Denmark, 1999.
11	Iliuta I, Dam-Johansen K, Jensen L S. Mathematical modeling of an in-line low-NO _x calciner[J]. Chemical Engineering Science, 2002, 57(5): 805-820.
12	Iliuta I, Dam-Johansen K, Jensen A, et al. Modeling of in-line low-NO _x calciners—a parametric study[J]. Chemical Engineering Science, 2002, 57(5): 789-803.
13	Iliuta I, Dam-Johansen K, Jensen A. Modelling of in-line low-NO _x calciners-NO _x emission[J]. Chemical Engineering Research and Design, 2003, 81(5): 537-548.
14	Nieuwland J J, Delnoij E, Kuipers J A M, et al. An engineering model for dilute riser flow[J]. Powder Technology, 1997, 90(2): 115-123.
15	Fellaou S, Harnoune A, Seghra M A, et al. Statistical modeling and optimization of the combustion efficiency in cement kiln precalciner[J]. Energy, 2018, 155: 351-359.
16	Hao X C, Guo T T, Huang G L, et al. Energy consumption prediction in cement calcination process: a method of deep belief network with sliding window[J]. Energy, 2020, 207: 118256.
17	Hao X C, Xu Q Q, Shi X, et al. Prediction of nitrogen oxide emission concentration in cement production process: a method of deep belief network with clustering and time series[J]. Environmental Science and Pollution Research International, 2021, 28(24): 31689-31703.
18	He W, Li J F, Tang Z H, et al. A novel hybrid CNN-LSTM scheme for nitrogen oxide emission prediction in FCC unit[J]. Mathematical Problems in Engineering, 2020, 2020: 8071810.
19	Hvala N, Kocijan J. Design of a hybrid mechanistic/Gaussian process model to predict full-scale wastewater treatment plant effluent[J]. Computers & Chemical Engineering, 2020, 140: 106934.
20	Bangi M S F, Kwon J S I. Deep hybrid modeling of chemical process: application to hydraulic fracturing[J]. Computers & Chemical Engineering, 2020, 134: 106696.
21	Bhadriraju B, Bangi M S F, Narasingam A, et al. Operable adaptive sparse identification of systems: application to chemical processes[J]. AIChE Journal, 2020, 66(11): e16980.
22	Nielsen R F, Nazemzadeh N, Sillesen L W, et al. Hybrid machine learning assisted modelling framework for particle processes[J]. Computers & Chemical Engineering, 2020, 140: 106916.
23	华丰, 方舟, 邱彤. 乙烯裂解炉反应与传热耦合的智能混合建模与模拟[J]. 化工学报, 2018, 69(3): 923-930.
	Hua F, Fang Z, Qiu T. Recirculation and reaction hybrid intelligent modeling and simulation for industrial ethylene cracking furnace[J]. CIESC Journal, 2018, 69(3): 923-930.
24	von Stosch M, Oliveira R, Peres J, et al. Hybrid semi-parametric modeling in process systems engineering: past, present and future[J]. Computers & Chemical Engineering, 2014, 60: 86-101.
25	Venkatasubramanian V. The promise of artificial intelligence in chemical engineering: is it here, finally? [J]. AIChE Journal, 2019, 65(2): 466-478.
26	Zendehboudi S, Rezaei N, Lohi A. Applications of hybrid models in chemical, petroleum, and energy systems: a systematic review[J]. Applied Energy, 2018, 228: 2539-2566.
27	Hill S C, Smoot L D. Modeling of nitrogen oxides formation and destruction in combustion systems[J]. Progress in Energy and Combustion Science, 2000, 26(4/5/6): 417-458.
28	Yang Y, Zhang Y, Li S J, et al. Numerical simulation of low nitrogen oxides emissions through cement precalciner structure and parameter optimization[J]. Chemosphere, 2020, 258: 127420.
29	Mickley H S, Trilling C A. Heat transfer characteristics of fluidized beds[J]. Industrial & Engineering Chemistry, 1949, 41(6): 1135-1147.
30	苏亚欣, 骆仲泱, 岑可法. 循环流化床颗粒团更新传热模型的修正[J]. 动力工程, 2001, 21(5): 1426-1429, 1416.
	Su Y X, Luo Z Y, Cen K F. Modification to the CFB cluster-renewal heat transfer model[J]. Power Engineering, 2001, 21(5): 1426-1429, 1416.
31	Smoot L D, Smith P J. Coal Combustion and Gasification[M]. New York: Plenum Press, 1985.
32	Liu Z C, Zhong W Q, Shao Y J, et al. Exergy analysis of supercritical CO₂ coal-fired circulating fluidized bed boiler system based on the combustion process[J]. Energy, 2020, 208: 118327.
33	Field M A, Gill D W, Morgan B B, et al. Combustion of Pulverized Coal[M]. Leatherhead: BCURA, 1967.
34	Zhong W Q, Yu A B, Zhou G W, et al. CFD simulation of dense particulate reaction system: approaches, recent advances and applications[J]. Chemical Engineering Science, 2016, 140: 16-43.
35	Basu P. Combustion of coal in circulating fluidized-bed boilers: a review[J]. Chemical Engineering Science, 1999, 54(22): 5547-5557.
36	Mikulčić H, Vujanović M, Duić N. Improving the sustainability of cement production by using numerical simulation of limestone thermal degradation and pulverized coal combustion in a cement calciner[J]. Journal of Cleaner Production, 2015, 88: 262-271.
37	Fidaros D K, Baxevanou C A, Dritselis C D, et al. Numerical modelling of flow and transport processes in a calciner for cement production[J]. Powder Technology, 2007, 171(2): 81-95.
38	Mikulčić H, von Berg E, Vujanović M, et al. Numerical modelling of calcination reaction mechanism for cement production[J]. Chemical Engineering Science, 2012, 69(1): 607-615.
39	胡芝娟, 刘志江, 王世杰. 模拟分解炉中煤焦燃烧生成NO的特性[J]. 化工学报, 2005, 56(3): 545-550.
	Hu Z J, Liu Z J, Wang S J. NO formation from coal char combustion in cement precalciner[J]. Journal of Chemical Industry and Engineering (China), 2005, 56(3): 545-550.
40	黄来, 陆继东, 李卫杰, 等. 分解炉中NO生成模拟与优化[J]. 化工学报, 2006, 57(11): 2624-2630.
	Huang L, Lu J D, Li W J, et al. Numerical simulation of NO in precalciner and its optimization[J]. Journal of Chemical Industry and Engineering (China), 2006, 57(11): 2624-2630.
41	胡道和, 徐德龙, 蔡玉良. 气固过程工程学及其在水泥工业中的应用[M]. 武汉: 武汉理工大学出版社, 2003.
	Hu D H. Xu D L, Cai Y L. Gas Solid Process Engineering and Its Application in Cement Industry[M]. Wuhan: Wuhan University of Technology Press, 2003.
42	金涌. 流态化工程原理[M]. 北京: 清华大学出版社, 2001.
	Jin Y. Fluidization Engineering Principles[M]. Beijing: Tsinghua University Press, 2001.
43	Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989, 2(5): 359-366.
44	李昌勇, 金春强, 胡道和. SLC-S分解炉气固两相运动规律研究[J]. 燃烧科学与技术, 2003, 9(3): 239-243.
	Li C Y, Jin C Q, Hu D H. Synthetic study of the motion patterns of gas and solid phases in SLC-S calciner[J]. Journal of Combustion Science and Technology, 2003, 9(3): 239-243.
45	李相国, 马保国, 吴贝, 等. 喷腾型分解炉内冷态流场的模拟与优化设计[J]. 哈尔滨工业大学学报, 2009, 41(4): 226-228.
	Li X G, Ma B G, Wu B, et al. Numerical simulation and optimization of cold airflow field in sprayed calciners[J]. Journal of Harbin Institute of Technology, 2009, 41(4): 226-228.

[1]	杨欣, 王文, 徐凯, 马凡华. 高压氢气加注过程中温度特征仿真分析[J]. 化工学报, 2023, 74(S1): 280-286.
[2]	宋嘉豪, 王文. 斯特林发动机与高温热管耦合运行特性研究[J]. 化工学报, 2023, 74(S1): 287-294.
[3]	张思雨, 殷勇高, 贾鹏琦, 叶威. 双U型地埋管群跨季节蓄热特性研究[J]. 化工学报, 2023, 74(S1): 295-301.
[4]	温凯杰, 郭力, 夏诏杰, 陈建华. 一种耦合CFD与深度学习的气固快速模拟方法[J]. 化工学报, 2023, 74(9): 3775-3785.
[5]	诸程瑛, 王振雷. 基于改进深度强化学习的乙烯裂解炉操作优化[J]. 化工学报, 2023, 74(8): 3429-3437.
[6]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[7]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[8]	徐野, 黄文君, 米俊芃, 申川川, 金建祥. 多源信息融合的离心式压缩机喘振诊断方法[J]. 化工学报, 2023, 74(7): 2979-2987.
[9]	高学金, 姚玉卓, 韩华云, 齐咏生. 基于注意力动态卷积自编码器的发酵过程故障监测[J]. 化工学报, 2023, 74(6): 2503-2521.
[10]	黄磊, 孔令学, 白进, 李怀柱, 郭振兴, 白宗庆, 李平, 李文. 油页岩添加对准东高钠煤灰熔融行为影响的研究[J]. 化工学报, 2023, 74(5): 2123-2135.
[11]	贠程, 王倩琳, 陈锋, 张鑫, 窦站, 颜廷俊. 基于社团结构的化工过程风险演化路径深度挖掘[J]. 化工学报, 2023, 74(4): 1639-1650.
[12]	吴心远, 刘奇磊, 曹博渊, 张磊, 都健. Group2vec：基于无监督机器学习的基团向量表示及其物性预测应用[J]. 化工学报, 2023, 74(3): 1187-1194.
[13]	吴选军, 王超, 曹子健, 蔡卫权. 数据与物理信息混合驱动的固定床吸附穿透深度学习模型[J]. 化工学报, 2023, 74(3): 1145-1160.
[14]	张江淮, 赵众. 碳三加氢装置鲁棒最小协方差约束控制及应用[J]. 化工学报, 2023, 74(3): 1216-1227.
[15]	张梦波, 楼琳瑾, 冯艺荣, 郑雨婷, 张浩淼, 王靖岱, 阳永荣. 烷基铝氧烷合成技术研究进展[J]. 化工学报, 2023, 74(2): 525-534.