基于混合模型的气流床气化炉建模

doi:10.11949/0438-1157.20201233

摘要/Abstract

摘要：

为了提高在煤质改变及工艺参数波动条件下气流床气化炉出口结果的预测精度，分别采用机理模型、广义回归神经网络（GRNN）模型以及混合模型对气化炉进行建模，其中混合模型由GRNN模型和机理模型构建，结合两种不同的煤样对三种模型的预测结果进行分析。结果表明：三种模型均可以较好地对气化过程进行模拟；其中在煤种固定的情况下混合模型关于气化温度和CO、CO₂及H₂含量的预测误差为0.18%和0.25%、1.72%及0.43%，与机理模型和GRNN模型相比误差更小；在煤种改变的情况下混合模型关于出口气体结果的预测最接近实际生产数据，误差为0.81%和0.11%、2.53%及0.42%。证明混合模型在煤种改变及工艺参数波动条件下可以有效地对气化过程进行模拟，在很大程度上提高了机理模型和GRNN模型的预测精度。

关键词: 气流床气化炉, 机理建模, 广义回归神经网络, 混合模型

Abstract:

In order to improve the prediction accuracy of the entrained-bed gasifier's outlet results under the conditions of coal type changes and process parameter fluctuations, a mechanism model, a generalized regression neural network (GRNN) model and a hybrid model are used to model the gasifier. The hybrid model constructed by GRNN model and mechanism model, combined with two different coal samples to analyze the prediction results of the three models. The results show that the three models can simulate the gasification process well. The prediction errors of the hybrid model regarding gasification temperature and the contents of CO, CO₂ and H₂ are 0.18% and 0.25%, 1.72% and 0.43% when the coal type is fixed. Compared with the mechanism model and the GRNN model, the error of hybrid model is smaller. When the coal type is changed, the prediction of the outlet gas result of the hybird model is the closest to the actual production data, and the error is 0.81% and 0.11%, 2.53% and 0.42% respectively. It is proved that the hybrid model can effectively simulate the gasification process under the conditions of coal type changes and process parameter fluctuations, which greatly improves the prediction accuracy of the mechanism model and the GRNN model.

Key words: entrained-bed gasifier, mechanism model, generalized regression neural network, hybrid model

中图分类号:

TP 183

姚源朝, 仇鹏, 许建良, 代正华, 刘海峰. 基于混合模型的气流床气化炉建模[J]. 化工学报, 2021, 72(5): 2727-2734.

YAO Yuanchao, QIU Peng, XU Jianliang, DAI Zhenghua, LIU Haifeng. Modeling of entrained-bed gasifier based on hybrid model[J]. CIESC Journal, 2021, 72(5): 2727-2734.

图/表 10

参考文献 31

1	梁咏诗, 赵香龙, 秦强, 等. 气流床气化炉的CPFD数值模拟[J]. 化工学报, 2019, 70(9): 3291-3299.
	Liang Y S, Zhao X L, Qin Q, et al. CPFD simulation on entrained-flow gasifier[J]. CIESC Journal, 2019, 70(9): 3291-3299.
2	张进春. 气流床煤气化工艺性能稳健优化与控制研究[D]. 长沙: 中南大学, 2011.
	Zhang J C. Study on robust optimization and control of the performance of entrained flow coal gasification[D]. Changsha: Central South University, 2011.
3	林慧丽. 单喷嘴粉煤气流床气化炉的稳态与动态模拟[D]. 上海: 华东理工大学, 2012.
	Lin H L. Steady and dynamic simulation of the single nozzle pulverized coal gasifier of entrained-flow[D]. Shanghai: East China University of Science and Technology, 2012.
4	Sun Z H, Dai Z H, Zhou Z J, et al. Numerical simulation of industrial opposed multiburner coal-water slurry entrained flow gasifier[J]. Industrial & Engineering Chemistry Research, 2012, 51(6): 2560-2569.
5	Jeong H J, Seo D K, Hwang J. CFD modeling for coal size effect on coal gasification in a two-stage commercial entrained-bed gasifier with an improved char gasification model[J]. Applied Energy, 2014, 123: 29-36.
6	Dai Z H, Gong X, Guo X L, et al. Pilot-trial and modeling of a new type of pressurized entrained-flow pulverized coal gasification technology[J]. Fuel, 2008, 87(10/11): 2304-2313.
7	Watanabe H, Kurose R. Modeling and simulation of coal gasification on an entrained flow coal gasifier[J]. Advanced Powder Technology, 2020, 31(7): 2733-2741.
8	杨俊宇. 多喷嘴对置式水煤浆气化系统动态模拟[D]. 上海: 华东理工大学, 2015.
	Yang J Y. Dynamic simulation of opposed multi-burner coal-water slurry gasification system[D]. Shanghai: East China University of Science and Technology, 2015.
9	李卓. 混合建模方法研究及其在化学化工过程中的应用[D]. 杭州: 浙江工业大学, 2019.
	Li Z. Study of hybrid modeling method and its application in chemical and engineering processes[D]. Hangzhou: Zhejiang University of Technology, 2019.
10	赵锦超, 龚欣, 代正华, 等. 用BP神经网络对气流床粉煤气化炉的预测[J]. 华东理工大学学报(自然科学版), 2009, 35(5): 688-692.
	Zhao J C, Gong X, Dai Z H, et al. Prediction of entrained-flow pulverized coal gasifier based on BP neural networks[J]. Journal of East China University of Science and Technology (Natural Science Edition), 2009, 35(5): 688-692.
11	Chen Y F, Shen L G, Li R J, et al. Quantification of interfacial energies associated with membrane fouling in a membrane bioreactor by using BP and GRNN artificial neural networks[J]. Journal of Colloid and Interface Science, 2020, 565: 1-10.
12	李向阳, 朱学峰, 刘焕彬. 工业过程混合建模方法研究及应用[J]. 计算机工程与应用, 2001, 37(6): 17-19.
	Li X Y, Zhu X F, Liu H B. Research and application of hybrid modeling method in industrial process[J]. Computer Engineering and Applications, 2001, 37(6): 17-19.
13	李晓光. 混合建模方法研究及其在化工过程中的应用[D]. 北京: 北京化工大学, 2008.
	Li X G. Research and application on hybrid modeling approach for chemical processes[D]. Beijing: Beijing University of Chemical Technology, 2008.
14	刘丽颖, 李悦, 方鲁杰, 等. 基于Adaboost混合模型的乙烯裂解结焦量软测量[J]. 自动化与仪器仪表, 2015, (6): 50-53.
	Liu L Y, Li Y, Fang L J, et al. Soft measurement of ethylene cracking coke content based on Adaboost model[J]. Automation & Instrumentation, 2015, (6): 50-53.
15	王惠杰, 苑国庆, 张晓博, 等. 基于混合模型的燃气轮机负荷与排气温度关系的研究[J]. 汽轮机技术, 2015, 57(5): 344-346, 332.
	Wang H J, Yuan G Q, Zhang X B, et al. Research on relationship between load and exhaust temperature of gas turbine based on mixed model[J]. Turbine Technology, 2015, 57(5): 344-346, 332.
16	郭晶晶, 徐金金, 杜文莉, 等. 自适应迭代混合建模及在碳二加氢过程的应用[J]. 化工学报, 2018, 69(11): 4814-4822.
	Guo J J, Xu J J, Du W L, et al. Self-adaptive iterative hybrid modeling and its application in acetylene hydrogenation process[J]. CIESC Journal, 2018, 69(11): 4814-4822.
17	叶贞成, 周换兰, 饶德宝. 乙炔加氢反应过程混合建模与优化[J]. 化工学报, 2019, 70(2): 496-507.
	Ye Z C, Zhou H L, Rao D B. Hybrid modeling and optimization of acetylene hydrogenation process[J]. CIESC Journal, 2019, 70(2): 496-507.
18	Ni Q Z, Williams A. A simulation study on the performance of an entrained-flow coal gasifier[J]. Fuel, 1995, 74(1): 102-110.
19	Merrick D. Mathematical models of the thermal decomposition of coal(3): Density, porosity and contraction behaviour[J]. Fuel, 1983, 62(5): 547-552.
20	Wen C Y, Chaung T Z. Entrainment coal gasification modeling[J]. Industrial & Engineering Chemistry Process Design and Development, 1979, 18(4): 684-695.
21	Niu D X, Wang H C, Chen H Y, et al. The general regression neural network based on the fruit fly optimization algorithm and the data inconsistency rate for transmission line icing prediction[J]. Energies, 2017, 10(12): 2066.
22	江帆, 刘辉, 王彬, 等. 基于CNN-GRNN模型的图像识别[J]. 计算机工程, 2017, 43(4): 257-262.
	Jiang F, Liu H, Wang B, et al. Image recognition based on CNN-GRNN model[J]. Computer Engineering, 2017, 43(4): 257-262.
23	李冬辉, 尹海燕, 郑博文. 基于MFOA-GRNN模型的年电力负荷预测[J]. 电网技术, 2018, 42(2): 585-590.
	Li D H, Yin H Y, Zheng B W. An annual load forecasting model based on generalized regression neural network with multi-swarm fruit fly optimization algorithm[J]. Power System Technology, 2018, 42(2): 585-590.
24	石卿志, 何俊仕. 基于GRNN模型的降水预测研究[J]. 南水北调与水利科技, 2015, 13(2): 241-244.
	Shi Q Z, He J S. Precipitation forecast based on GRNN model[J]. South-to-North Water Transfers and Water Science & Technology, 2015, 13(2): 241-244.
25	Qi J X, Jiang G Z, Li G F, et al. Surface EMG hand gesture recognition system based on PCA and GRNN[J]. Neural Computing and Applications, 2020, 32(10): 6343-6351.
26	杨振华, 苏维词, 赵卫权, 等. 基于GRNN模型的岩溶地区城市水生态足迹分析与预测[J]. 中国岩溶, 2016, 35(1): 36-42.
	Yang Z H, Su W C, Zhao W Q, et al. Analysis and forecast of water ecological footprint in Karst area based on GRNN model[J]. Carsologica Sinica, 2016, 35(1): 36-42.
27	王海军, 涂凯, 闫晓荣. 基于果蝇优化算法的GRNN模型在边坡稳定预测中的应用[J]. 水电能源科学, 2015, 33(1): 124-126, 144.
	Wang H J, Tu K, Yan X R. Application of general regression neural network to predict slope stability based on fruit fly optimization algorithm[J]. Water Resources and Power, 2015, 33(1): 124-126, 144.
28	王泽阳, 来兴平, 刘小明, 等. 综采面区段煤柱宽度预测GRNN模型构建与应用[J]. 西安科技大学学报, 2019, 39(2): 209-216.
	Wang Z Y, Lai X P, Liu X M, et al. Construction and application of the GRNN model of coal section pillar width prediction in fully mechanized face[J]. Journal of Xi'an University of Science and Technology, 2019, 39(2): 209-216.
29	饶运章, 袁博云, 吴卫强, 等. 基于GRNN模型的硫化矿石堆氧化自热温度预测[J]. 金属矿山, 2016, (6): 149-152.
	Rao Y Z, Yuan B Y, Wu W Q, et al. Prediction of oxidation and self-heating temperature of sulfide ore heap based on GRNN model[J]. Metal Mine, 2016, (6): 149-152.
30	杨召亮, 薛新华. 隧道围岩等级分类GRNN模型研究[J]. 西部探矿工程, 2018, 30(11): 161-162, 170.
	Yang Z L, Xue X H. Research on GRNN model of tunnel surrounding rock classification [J]. West-China Exploration Engineering, 2018, 30(11): 161-162, 170.
31	狄圣杰, 李晓敏, 魏樯. GRNN在边坡稳定预测分析中的应用[J]. 水利水电科技进展, 2011, 31(3): 80-83.
	Di S J, Li X M, Wei Q. Application of generalized regression neural network in prediction and analysis of slope stability[J]. Advances in Science and Technology of Water Resources, 2011, 31(3): 80-83.

煤样	工业分析/%(质量分数,干基)				元素分析/%(质量分数,干基)
煤样	FC	VM	ASH	FT(K)	C	H	O	N	S
1号	59.01	33.5	7.49	1469.15	75.88	4.42	10.69	0.96	0.56
2号	57.74	33.41	8.85	1447.15	75.93	4.24	9.90	0.88	0.20

煤样	工业分析/%(质量分数,干基)				元素分析/%(质量分数,干基)
煤样	FC	VM	ASH	FT(K)	C	H	O	N	S
1号	59.01	33.5	7.49	1469.15	75.88	4.42	10.69	0.96	0.56
2号	57.74	33.41	8.85	1447.15	75.93	4.24	9.90	0.88	0.20

煤样	项目	干煤流量/(kg/h)	氧气流量/(kg/m³)	水流量/(kg/h)	T/K	CO/%	CO₂/%	H₂/%
1号	工厂数据	36808.33	35366.29	24672.10	1518.65	42.57	18.51	37.69
1号	模拟结果	36808.33	35366.29	24672.10	1488.85	42.73	19.83	36.74
2号	工厂数据	51231.4	48540	33448.60	1515.2	49.83	14.73	34.9
2号	模拟结果	51231.4	48540	33448.60	1498.69	49.32	14.25	34.98

煤样	项目	干煤流量/(kg/h)	氧气流量/(kg/m³)	水流量/(kg/h)	T/K	CO/%	CO₂/%	H₂/%
1号	工厂数据	36808.33	35366.29	24672.10	1518.65	42.57	18.51	37.69
1号	模拟结果	36808.33	35366.29	24672.10	1488.85	42.73	19.83	36.74
2号	工厂数据	51231.4	48540	33448.60	1515.2	49.83	14.73	34.9
2号	模拟结果	51231.4	48540	33448.60	1498.69	49.32	14.25	34.98

项目		T/ K	CO/%	CO₂/%	H₂/%
工厂数据		1518.65	42.57	18.51	37.69
模拟结果	已训练	1517.98	42.70	18.45	37.63
	未训练	1531.16	42.712	19.45	38.65