基于智能预测和机理模型的换热网络清洗决策

doi:10.16085/j.issn.1000-6613.2021-0903

摘要/Abstract

摘要：

原油石化装置的换热器常受到结垢影响，导致换热器性能衰退严重，换热网络性能也会随之衰退，同时换热器之间的耦合关系，导致不同换热器的性能衰退对换热网络整体性能变化的影响不同。以往的清洗决策主要是根据单台换热器性能衰退到一定程度来制定的，这会导致换热网络整体可能处在较差的运行状态。因此，本文提出一种基于智能预测和机理模型的换热网络清洗决策方法，基于换热器的运行数据建立智能预测模型，获得换热器性能变化趋势，结合换热网络的性能模拟模型，进一步获得换热网络的性能变化趋势，从而从换热网络整体性能变化的角度来制定清洗方案。研究表明，对收集到的原油换热器运行数据，建立神经网络预测模型，具有较好的预测精度。通过对原油精馏装置换热网络的案例分析，当HE1、HE2和HE5三台换热器同时发生性能衰退时，换热网络年度公用工程能耗费用将增加12.1%。与传统基于单台换热器性能衰退情况制定的清洗方案相比，从换热网络整体性能衰退角度制定的清洗方案，年度额外公用工程费用减少13.1%，损失费用减少14.1%，年度总费用减少13.8%，而清洗次数仅增加3台次。

关键词: 换热器, 原油, 结垢, 清洗, 性能预测, 换热网络

Abstract:

The heat exchanger of crude oil petrochemical unit is often affected by fouling, which leads to the serious decline of heat exchanger performance and the decline of heat exchanger network performance. At the same time, due to the coupled relationship between heat exchangers, the performance decline of different heat exchangers has different effects on the change of heat exchanger network performance. In the past, cleaning decisions were mainly made based on the performance degradation of a single heat exchanger to a certain extent, resulting in the poor operation of the heat exchanger network. Therefore, a method of heat exchanger network cleaning decision-making based on intelligent prediction and mechanism was proposed in this paper. The intelligent prediction model was established for the operation data of heat exchangers to obtain the performance change trend of heat exchangers. Combined with the performance simulation model of heat exchangers network, the performance change trend of heat exchanger network was further obtained, so as to formulate the cleaning scheme from the perspective of the performance change of heat exchanger network. Based on the operation data of crude oil heat exchangers, the neural network prediction model was established, which has good prediction accuracy. Through the case study of heat exchange network of a crude oil distillation unit, when the performances of HE1, HE2 and HE5 heat exchangers decline at the same time, the annual additional utility energy consumption of heat exchanger network increases by 12.1%. Compared with the traditional cleaning scheme based on the performance of single heat exchanger, the annual additional cost of utility, loss cost and annual total cost of the cleaning scheme based on the performance degradation of heat exchanger network are reduced by 13.1%, 14.1% and 13.8%, respectively, while the cleaning number of times is only increased by 3.

Key words: heat exchanger, crude oil, fouling, cleaning, performance prediction, heat exchanger network

中图分类号:

TQ021.8

蒋宁, 张元毅, 范伟, 赵世超, 徐新杰, 徐英杰. 基于智能预测和机理模型的换热网络清洗决策[J]. 化工进展, 2022, 41(4): 1781-1792.

JIANG Ning, ZHANG Yuanyi, FAN Wei, ZHAO Shichao, XU Xinjie, XU Yingjie. Cleaning decision of heat exchanger network based on intelligent prediction and mechanism[J]. Chemical Industry and Engineering Progress, 2022, 41(4): 1781-1792.

图/表 18

表1 各维度数据分布指标表

项目	均值	最小值	最大值	中值
时间/h	32.5	5	60	32.5
流速/m·s^-1	0.481	0.481	0.484	0.482
Re	2559	2553	2573	2558
管壁温度/℃	252	246	264	251
腔体温度/℃	76.7	74.4	78.8	76.73
污垢热阻变化率/m²·K·kW^-1·h^-1	0.0002	-0.0007	0.0014	0.0001

图1 经验模型的拟合结果

图2 与传统机器学习模型结果比较

图3 不同预测模型评价指标结果对比

图4 本文方法的流程图

表2 物流数据表

物流	进口温度T_in/°C	出口温度T_out/°C	热容流率CP/kW·K^-1	单位费用UC/USD·kW^-1·a^-1
H1	140	40	470	—
H2	160	120	825	—
H3	210	45	42.42	—
H4	260	60	100	—
H5	280	210	357.14	—
H6	350	170	50	—
H7	380	160	136.36	—
C1	270	385	826.09	—
C2	130	270	500	—
C3	20	130	363.64	—
HU	500	499	—	60
CU	20	40	—	5

图5 现有换热网络结构图

图6 换热网络关键设备灵敏度分析

图7 HE1和HE2换热器传热系数时间变化曲线

图8 HE5换热器传热系数变化曲线

图9 公用能耗绝对增加量随时间的变化

图10 日公用能耗绝对增加量随时间的变化

图11 年度公用能耗绝对增加量和年度公用能耗相对变化率

图12 当HE1、HE2和HE5性能衰退30%、停用24h的清洗方案

图13 HE1、HE2和HE5停用24h网络需要的额外公用工程能耗

图14 当换热器网络性能衰退10%、停用24h的清洗方案

图15 HE1、HE2和HE5停用24h网络需要的额外公用工程能耗

图16 两种方案之间的比较

参考文献 27

1	蒋宁, 谢小东, 范伟, 等. 数据驱动的固定拓扑结构换热网络优化改造方法[J]. 化工进展, 2019, 38(10): 4452-4460.
	JIANG Ning, XIE Xiaodong, FAN Wei, et al. Data-driven optimization retrofit method with fixed topology structure for heat exchanger network[J]. Chemical Industry and Engineering Progress, 2019, 38(10): 4452-4460.
2	吴敏, 肖武, 贺高红. 基于遗传/模拟退火算法考虑压降的换热网络优化改造[J]. 化工进展, 2015, 34(4): 1171-1177.
	WU Min, XIAO Wu, HE Gaohong. Retrofit of heat exchanging network considering pressure drop based on GA/SA[J]. Chemical Industry and Engineering Progress, 2015, 34(4): 1171-1177.
3	KERN D. A theoretical analysis of thermal surface fouling[J]. British Chemical Engineering, 1959, 4: 258-262.
4	EBERT W, PANCHAL C B. Analysis of Exxon crude-oil-slip stream coking data[R]. 1995.
5	KNUDSEN J G, LIN D, EBERT W A. The determination of the threshold fouling curve for a crude oil[J]. Understanding Heat Exchanger Fouling and its Mitigation, 1999, 265: 272.
6	POLLEY G T, WILSON D I, YEAP B L, et al. Evaluation of laboratory crude oil threshold fouling data for application to refinery pre-heat trains[J]. Applied Thermal Engineering, 2002, 22(7): 777-788.
7	樊绍胜. 冷凝器污垢的灰色预测[J]. 电力科学与技术学报, 2007, 22(2): 12-15.
	FAN Shaosheng. Gray theory based prediction for condenser fouling[J]. Journal of Electric Power Science and Technology, 2007, 22(2): 12-15.
8	徐志明, 刘艳, 文孝强. 基于灰色理论模型的交叉缩放椭圆管污垢特性预测[J]. 华北电力大学学报(自然科学版), 2011, 38(4): 96-100.
	XU Zhiming, LIU Yan, WEN Xiaoqiang. Forecasting fouling characteristics of alternating elliptical axis tube based on grey theory model[J]. Journal of North China Electric Power University (Natural Science Edition), 2011, 38(4): 96-100.
9	SUN Lingfang, ZHANG Yingying, RINA Saqi. Fouling prediction of heat exchanger based on genetic optimal SVM algorithm[C]//2009 Third International Conference on Genetic and Evolutionary Computing. October 14-17, 2009, Guilin, China. IEEE, 2009: 112-116.
10	AMINIAN J, SHAHHOSSEINI S. Evaluation of ANN modeling for prediction of crude oil fouling behavior[J]. Applied Thermal Engineering, 2008, 28(7): 668-674.
11	SUNDAR S, RAJAGOPAL M C, ZHAO H Y, et al. Fouling modeling and prediction approach for heat exchangers using deep learning[J]. International Journal of Heat and Mass Transfer, 2020, 159: 120112.
12	SMAÏLI F, ANGADI D K, HATCH C M, et al. Optimization of scheduling of cleaning in heat exchanger networks subject to fouling: sugar industry case study[J]. Food and Bioproducts Processing, 1999, 77(2): 159-164.
13	BOTT R, MÜLLER-STEINHAGEN H. Fouling in heat exchangers. Rugby: IChemE[J]. Chemical Engineering Research and Design, 2001, 79(2): 216.
14	ISHIYAMA E M, PATERSON W R, WILSON D IAN. Optimum cleaning cycles for heat transfer equipment undergoing fouling and ageing[J]. Chemical Engineering Science, 2011, 66(4): 604-612.
15	POGIATZIS T, ISHIYAMA E M, PATERSON W R, et al. Identifying optimal cleaning cycles for heat exchangers subject to fouling and ageing[J]. Applied Energy, 2012, 89(1): 60-66.
16	POGIATZIS T A, WILSON D I, VASSILIADIS V S. Scheduling the cleaning actions for a fouled heat exchanger subject to ageing: MINLP formulation[J]. Computers & Chemical Engineering, 2012, 39: 179-185.
17	GEORGIADIS M C, PAPAGEORGIOU L G. Optimal energy and cleaning management in heat exchanger networks under fouling[J]. Chemical Engineering Research and Design, 2000, 78(2): 168-179.
18	樊婕, 李继龙, 刘琳琳, 等. 换热器网络设备面积与清洗时序同步优化[J]. 化工学报, 2014, 65(11): 4484-4489.
	FAN Jie, LI Jilong, LIU Linlin, et al. Simultaneous optimization of areas and cleaning schedule for heat exchanger networks[J]. CIESC Journal, 2014, 65(11): 4484-4489.
19	BIYANTO T R, KHAIRANSYAH M D, BAYUAJI R, et al. Imperialist competitive algorithm (ICA) for heat exchanger network (HEN) cleaning schedule optimization[J]. Procedia Computer Science, 2015, 72: 5-12.
20	XIAO Feng, DU Jian, LIU Linlin, et al. Simultaneous optimization of synthesis and scheduling of cleaning in flexible heat exchanger networks[J]. Chinese Journal of Chemical Engineering, 2010, 18(3): 402-411.
21	DIABY A L, MIKLAVCIC S J, ADDAI-MENSAH J. Optimization of scheduled cleaning of fouled heat exchanger network under ageing using genetic algorithm[J]. Chemical Engineering Research and Design, 2016, 113: 223-240.
22	ZUBAIR S M, QURESHI B A. A probabilistic fouling and cost model for plate-and-frame heat exchangers[J]. International Journal of Energy Research, 2006, 30(1): 1-17.
23	SALEH Z, SHEIKHOLESLAMI R, WATKINSON A P. Heat exchanger fouling by a light Australian crude oil[C]//Heat Exchanger Fouling and Cleaning Fundamentals and Applications, Santa Fe, 2003.
24	JAFARI NASR M R, MAJIDI GIVI M. Modeling of crude oil fouling in preheat exchangers of refinery distillation units[J]. Applied Thermal Engineering, 2006, 26(14/15): 1572-1577.
25	SUNDARAM B N. The effects of oxygen on synthetic crude oil fouling[D]. British Columbia: University of British Columbia, 1998.
26	AHMAD S, PATELA E. Supertarget: applications software for oil refinery retrofit[R]. American Institute of Chemical Engineers, New York, 1987.
27	CHEN P C, DU J. Synthesis of heat exchanger network subject to fouling and ageing with the cleaning schedule optimized[C]//Proceedings of the 6th International Conference on Process Systems Engineering (PSE ASIA). 2013: 27.

[1]	陈林, 徐培渊, 张晓慧, 陈杰, 徐振军, 陈嘉祥, 密晓光, 冯永昌, 梅德清. 液化天然气绕管式换热器壳侧混合工质流动及传热特性[J]. 化工进展, 2023, 42(9): 4496-4503.
[2]	李雪佳, 李鹏, 李志霞, 晋墩尚, 郭强, 宋旭锋, 宋芃, 彭跃莲. 亲水和疏水改性膜的抗结垢和润湿能力的对比[J]. 化工进展, 2023, 42(8): 4458-4464.
[3]	王云刚, 焦健, 邓世丰, 赵钦新, 邵怀爽. 冷凝换热与协同脱硫性能实验分析[J]. 化工进展, 2023, 42(8): 4230-4237.
[4]	赵健, 卓泽文, 董航, 高文健. 含蜡原油及其乳状液体系微观结构观测的新方法[J]. 化工进展, 2023, 42(8): 4372-4384.
[5]	吴亚, 赵丹, 方荣苗, 李婧瑶, 常娜娜, 杜春保, 王文珍, 史俊. 用于复杂原油乳液的高效破乳剂开发及应用研究进展[J]. 化工进展, 2023, 42(8): 4398-4413.
[6]	孙征楠, 李洪晶, 荆国林, 张福宁, 颜飚, 刘晓燕. EVA及其改性聚合物在原油降凝剂领域的应用[J]. 化工进展, 2023, 42(6): 2987-2998.
[7]	齐承鲁, 张忠良, 王明超, 李耀鹏, 宫晓辉, 孙鹏, 郑斌. 内置管束布置对换热器内固体颗粒流动的影响[J]. 化工进展, 2023, 42(5): 2306-2314.
[8]	朱添宇, 孙琳, 任超, 罗雄麟. 基于全周期持续节能的换热网络滑动窗口分析与裕量缓释优化控制[J]. 化工进展, 2023, 42(3): 1195-1205.
[9]	孙崇正, 樊欣, 李玉星, 许洁, 韩辉, 刘亮. 海上多孔介质通道内氢气换热与正仲氢转化的耦合特性[J]. 化工进展, 2023, 42(3): 1281-1290.
[10]	刘君康, 王宏超, 熊通, 晏刚, 郭宁, 刘睿. 热泵空调翅片管换热器流路优化研究进展[J]. 化工进展, 2023, 42(1): 107-117.
[11]	古新, 张前欣, 王超鹏, 方运阁, 李宁, 王永庆. U形导流板换热器传热和阻力性能分析[J]. 化工进展, 2022, 41(7): 3465-3474.
[12]	刘世杰, 莫逊, 涂爱民, 朱冬生, 谭连元. 新型纵流油冷却器壳程强化传热[J]. 化工进展, 2022, 41(7): 3475-3482.
[13]	王宇晶, 张楠, 刘涉江, 苗辰, 刘秀丽. 热化学清洗含油污泥的效果评价及机理[J]. 化工进展, 2022, 41(6): 3333-3340.
[14]	李帅, 刘明言, 马永丽. 基于BP人工神经网络预测地热井中流体的结垢位置[J]. 化工进展, 2022, 41(11): 5761-5770.
[15]	刘洪彬, 崔国民, 周志强, 肖媛, 张冠华, 杨其国. 应用于换热网络优化的并行双层RWCE算法[J]. 化工进展, 2022, 41(10): 5247-5258.