基于灰色关联BP神经网络的压缩式蓄冷系统中的水合物生成量预测

doi:10.16085/j.issn.1000-6613.2020-0600

摘要/Abstract

摘要：

CO₂水合物作为一种新型的蓄冷介质，具有良好的应用前景。在蓄冷系统中，CO₂水合物的生成量对蓄冷量有直接影响，但CO₂水合物生成计算较为复杂，进而导致系统蓄冷量的计算同样复杂起来，因此建立能够快速分析和预测系统中水合物生成量的模型具有实际意义。本文介绍了可以解决复杂问题的BP神经网络模型（BP）和灰色关联预测模型［GRM(1,n)］，并利用Matlab语言编程建立了GRM(1,n)-BP神经网络组合模型来预测水合物的生成量。本文选取实验系统的数据利用3种模型分别进行了预测，并将3种模型的结果与实验结果进行对比，结果表明，GRM(1,n)-BP神经网络组合模型的准确性和稳定性效果更好。最后通过考察充注压力这一单一变量对水合物生成量的影响，并对比模型预测结果，进一步验证了GRM(1,n)-BP神经网络组合模型的准确性。

关键词: 二氧化碳, 水合物, 神经网络, 预测

Abstract:

As a new cold storage medium, CO₂ hydrate has a good application prospect. In the cold storage system, the amount of CO₂ hydrate generation has a direct impact on the amount of cold storage, but the calculation of the amount of CO₂ hydrate generation is complicated, which leads to the calculation of the amount of cold storage in the system is also complicated. Therefore, it is of practical significance to establish a model that can quickly analyze and predict the amount of hydrate production in the system. In this paper, BP neural network model (BP) and grey relational prediction model [GRM(1,n)] which can solve complex problems were introduced, and GRM(1,n)-BP neural network combination model was established by Matlab programming language to predict hydrate production. Three models were selected to predict the data of the experimental system, and the results of the three models were compared with the experimental results. The results showed that the GRM(1,n)-BP neural network combination model has better accuracy and stability. Finally, the accuracy of the GRM(1,n)-BP neural network combination model by investigating the influence of the single variable of charging pressure on hydrate production and comparing the predicted results of the model was further verified.

Key words: carbon dioxide, hydrate, neural networks, prediction

中图分类号:

TB61⁺5

杨文宇, 谢应明, 闫坤, 邹俊华, 舒胜. 基于灰色关联BP神经网络的压缩式蓄冷系统中的水合物生成量预测[J]. 化工进展, 2021, 40(2): 664-670.

Wenyu YANG, Yingming XIE, Kun YAN, Junhua ZOU, Sheng SHU. Prediction of hydrate production in compressive cold storage system based on grey relational BP neural network[J]. Chemical Industry and Engineering Progress, 2021, 40(2): 664-670.

图/表 1

参考文献 30

1	陈伟军, 刘妮, 肖晨, 等. CO₂水合物浆在蓄冷空调中的应用前景[J]. 制冷学报, 2012, 33(3): 1-4.
	CHEN Weijun, LIU Ni, XIAO Chen, et al. Perspective of CO₂ hydrate slurry application in air conditioning system with cool storage[J]. Journal of Refrigeration, 2012, 33(3): 1-4.
2	孙嘉颖, 谢应明, 徐政涛, 等. 纳米流体强化CO₂水合物生成的研究进展[J]. 现代化工, 2019, 39(12): 26-30.
	SUN Jiaying, XIE Yingming, XU Zhengtao, et al. Research progress in nanofluids-enhanced formation of CO₂ hydrate[J]. Modern Chemical Industry, 2019, 39(12): 26-30.
3	叶鹏, 刘道平, 时竞竞. 二氧化碳水合物生成驱动力的研究[J]. 天然气化工, 2013, 38(2): 38-41.
	YE Peng, LIU Daoping, SHI Jingjing, et al. Study on driving force for carbon dioxide hydrate formation[J]. Natural Gas Chemical Industry, 2013, 38(2): 38-41.
4	王树立, 黄俊尧, 闫朔, 等. 基于化学亲和力模型的水合物生成动力学[J]. 化工进展, 2020, 39(3): 966-974.
	WANG Shuli., HUANG Junyao, YAN Shuo, et al. Hydrate formation kinetics based on chemical affinity model[J]. Chemical Industry and Engineering Progress, 2020, 39(3): 966-974.
5	HUANG Yingchao, JIN Shuo, WU Liqun. A hydrate blockage recognition technique for natural gas pipelines based on BP neural network[J]. Journal of Physics: Conference Series, 2019, 1345(1): 022004.
6	唐永红, 王超, 龚安, 等. 基于小波神经网络的水合物形成条件预测方法[J]. 计算机与现代化, 2013(6): 5-8.
	TANG Yonghong, WANG Chao, GONG An, et al. A prediction method for hydrate formation conditions based on wavelet neural network[J]. Computer and Modernization, 2013(6): 5-8.
7	PARENTE M T, MATTIS S, GUPTA S. Efficient parameter estimation for a methane hydrate model with active subspaces[J]. Computational Geosciences, 2019, 23(2): 355-372.
8	文涛, 刘建仪, 周昊. GRM(1, n)模型在天然气水合物生成预测中的应用[J]. 天然气技术, 2007, 1(4): 41-43.
	WEN Tao, LIU Jianyi, ZHOU Hao. Application of GRM (1, n) model in prediction of gas hydrate formation[J]. Natural Gas Technology, 2007, 1(4): 41-43.
9	付康伟, 张学强, 彭炎. BP神经网络算法在陆域天然气水合物成藏预测中的应用[J]. 物探与化探, 2019, 43(3): 486-493.
	FU Kangwei, ZHANG Xueqiang, PENG Yan. Application of BP neural network algorithm in prediction of land natural gas hydrate accumulation[J]. Geophysical and Geochemical Exploration, 2019, 43 (3): 486-493.
10	马金凤, 梁建, 郭军, 等. BP神经网络在天然气水合物化探中的应用[J]. 地质学刊, 2016, 40(1): 113-117.
	MA Jinfeng, LIANG Jian, GUO Jun, et al. Application of BP neural network in gas hydrate exploration[J]. Journal of Geology, 2016, 40 (1): 113-117.
11	GHIASI M M, NOOROLLAHI Y, ASLANI A. CO₂ hydrate: modeling of incipient stability conditions and dissociation enthalpy[J]. Petroleum Science and Technology, 2018, 36(4): 259-265.
12	MESBAH M, SOROUSH E, ROHAM M, et al. Phase equilibrium modeling of semi-clathrate hydrates of the CO₂+H₂/CH₄/N₂+TBAB aqueous solution system[J]. Petroleum Science & Technology, 2017, 35(15): 1588-1594.
13	慕亚茹. 基于灰色-RBF算法的瓦斯水合物相平衡预测研究[D]. 哈尔滨: 黑龙江科技大学, 2015.
	MU Yaru. Gas hydrate equilibrium prediction research based on gray-RBF algorithm[D]. Harbin: Heilongjiang University of Science and Technology, 2015.
14	马贵阳, 宫清君, 潘振, 等. 基于支持向量机结合遗传算法的天然气水合物相平衡研究[J]. 天然气工业, 2017, 37(5): 46-52.
	MA Guiyang, GONG Qingjun, PAN Zhen, et al. GA-SVM based study on natural gas hydrate phase equilibrium[J]. Natural Gas Industry, 2017, 37 (5): 46-52.
15	苏鑫, 裴华健, 吴迎亚, 等. 应用经遗传算法优化的BP神经网络预测催化裂化装置焦炭产率[J]. 化工进展, 2016, 35(2): 389-396.
	SU Xin, PEI Huajian, WU Yingya, et al. Predicting coke yield of FCC unit using genetic algorithm optimized BP neural network[J]. Chemical Industry and Engineering Progress, 2016, 35(2): 389-396.
16	贺婷婷, 陆军, 丁进良, 等. 原油总碳含量的粒子群优化集成神经网络预测模型[J]. 控制理论与应用, 2019, 36(2): 192-198.
	HE Tingting, LU Jun, DING Jinliang, et al. Prediction model of total carbon content of crude oil using ensemble random weights neural network optimized by particle swarm optimization[J]. Control Theory & Application, 2019, 36(2): 192-198.
17	周麟晨, 孙志高, 李娟, 等. 水合物形成促进剂研究进展[J]. 化工进展, 2019, 38(9): 4131-4141.
	ZHOU Linchen, SUN Zhigao, LI Juan, et al. Progress of hydrate formation promoters[J]. Chemical Industry and Engineering Progress, 2019, 38(9): 4131-4141.
18	谢振兴, 谢应明, 周兴法, 等. 充注压力对压缩式制冷循环连续制备CO₂水合物的影响[J]. 化工学报, 2014, 65(6): 2301-2307.
	XIE Zhenxing, XIE Yingming, ZHOU Xingfa, et al. Effects of charge pressure on continuous production of CO₂ hydrate in compression refrigeration cycle[J]. CIESC Journal, 2014, 65(6): 2301-2307.
19	庄雅琪, 谢应明, 耿时江, 等. 充注压力对CO₂水合物蓄冷系统性能的影响[J]. 制冷技术, 2017, 37(6): 6-10.
	ZHUANG Yaqi, XIE Yingming, GENG Shijiang, et al. Effect of charge pressure on performance of CO₂ hydrate cool storage system[J]. Chinese Journal of Refrigeration Technology, 2017, 37(6): 6-10.
20	周麟晨, 孙志高, 陆玲, 等. 有机相变乳液中HCFC-141b水合物生成及稳定性[J]. 化工学报, 2019, 70(5): 1674-1681.
	ZHOU Linchen, SUN Zhigao, LU Ling, et al. Formation and stability of HCFC-141b hydrate in organic phase change emulsion[J]. CIESC Journal, 2019, 70(5): 1674-1681.
21	黄鸿云, 刘卫校, 丁佐华. 基于多维灰色模型及神经网络的销售预测[J]. 软件学报, 2019, 30(4): 1031-1044.
	HUANG Hongyun, LIU Weixiao, DING Zuohua. Sales forecasting based on multi-dimensional grey model and neural network[J]. Journal of Software, 2019, 30 (4): 1031-1044.
22	YIN Kedong, GENG Yan, LI Xuemei. Improved grey prediction model based on exponential grey action quantity[J]. Journal of Systems Engineering and Electronics, 2018, 29(3): 560-570.
23	ZHAO Biao, YU Tianyu, DING Wenfen, et al. BP neural network based flexural strength prediction of open-porous Cu-Sn-Ti composites[J]. Progress in Natural Science: Materials International, 2018, 28(3): 315-324.
24	ZHAO Guodong, ZHANG Yuewei, SHI Yiqi, et al. The application of BP neural networks to analysis the national vulnerability[J]. Computers Materials & Continua, 2019, 58(2): 421-436.
25	王书涛, 陈东营, 王兴龙, 等. 一种荧光光谱法和PSO-BP神经网络相结合的山梨酸钾浓度测定的新方法[J]. 光谱学与光谱分析, 2015, 35(12): 3549-3554.
	WANG Shu-tao, CHEN Dong-ying, WANG Xing-long, et al. A new method for the determination of potassium sorbate combining fluorescence spectra method with PSO-BP neural network[J]. Spectroscopy and Spectral Analysis, 2015, 35(12): 3549-3554.
26	LIU Zhenpeng, HE Yupeng, WANG Wensheng, et al. DDoS attack detection scheme based on entropy and PSO-BP neural network in SDN[J]. China Communications, 2019, 16(7): 144-155.
27	王志芳, 王书涛, 王贵川. 粒子群优化BP神经网络在甲烷检测中的应用[J]. 光子学报, 2019, 48(4): 147-154.
	WANG Zhifang, WANG Shutao, WANG Guichuang. Application of particle swarm optimization BP neural network in methane detection[J]. Acta Photonica Sinica, 2019, 48(4): 147-154.
28	VISCONDI G F, ALVES-SOUZA S N. A Systematic literature review on big data for solar photovoltaic electricity generation forecasting[J]. Sustainable Energy Technologies and Assessments, 2019, 31: 54-63.
29	范胜龙, 邱凌婧, 茹凯丽, 等. 基于BP神经网络和支持向量机的农用地分等方法研究[J]. 中国农业大学学报, 2018, 23(12): 138-148.
	FAN Shenglong, QIU Lingjing, RU Kaili, et al. Classification method of agricultural land quality based on back-propagation neural network and support vector machine[J]. Journal of China Agricultural University, 2018, 23(12): 138-148.
30	吴强, 张家豪, 高霞, 等. 热力学促进剂对瓦斯水合物相平衡的影响[J]. 黑龙江科技大学学报, 2016, 26(3): 235-239.
	WU Qiang, ZHANG Jiahao, GAO Xia, et al. Effect of thermodynamics promoters on phase equilibrium of mine gas hydrate[J]. Journal of Heilongjiang University of Science and Technology, 2016, 26(3): 235-239.

[1]	杨寒月, 孔令真, 陈家庆, 孙欢, 宋家恺, 王思诚, 孔标. 微气泡型下向流管式气液接触器脱碳性能[J]. 化工进展, 2023, 42(S1): 197-204.
[2]	徐晨阳, 都健, 张磊. 基于图神经网络的化学反应优劣评价[J]. 化工进展, 2023, 42(S1): 205-212.
[3]	王胜岩, 邓帅, 赵睿恺. 变电吸附二氧化碳捕集技术研究进展[J]. 化工进展, 2023, 42(S1): 233-245.
[4]	时永兴, 林刚, 孙晓航, 蒋韦庚, 乔大伟, 颜彬航. 二氧化碳加氢制甲醇过程中铜基催化剂活性位点研究进展[J]. 化工进展, 2023, 42(S1): 287-298.
[5]	郑谦, 官修帅, 靳山彪, 张长明, 张小超. 铈锆固溶体Ce_0.25Zr_0.75O₂光热协同催化CO₂与甲醇合成DMC[J]. 化工进展, 2023, 42(S1): 319-327.
[6]	戴欢涛, 曹苓玉, 游新秀, 徐浩亮, 汪涛, 项玮, 张学杨. 木质素浸渍柚子皮生物炭吸附CO₂特性[J]. 化工进展, 2023, 42(S1): 356-363.
[7]	孙玉玉, 蔡鑫磊, 汤吉海, 黄晶晶, 黄益平, 刘杰. 反应精馏合成甲基丙烯酸甲酯工艺优化及节能[J]. 化工进展, 2023, 42(S1): 56-63.
[8]	王谨航, 何勇, 史伶俐, 龙臻, 梁德青. 气体水合物阻聚剂研究进展[J]. 化工进展, 2023, 42(9): 4587-4602.
[9]	李由, 吴越, 钟禹, 林琦璇, 任俊莉. 酸性熔盐水合物预处理麦秆高效制备木糖及其对酶解效率的影响[J]. 化工进展, 2023, 42(9): 4974-4983.
[10]	尹新宇, 皮丕辉, 文秀芳, 钱宇. 特殊浸润性材料在防治油气管道中水合物成核与聚集的应用[J]. 化工进展, 2023, 42(8): 4076-4092.
[11]	王耀刚, 韩子姗, 高嘉辰, 王新宇, 李思琪, 杨全红, 翁哲. 铜基催化剂电还原二氧化碳选择性的调控策略[J]. 化工进展, 2023, 42(8): 4043-4057.
[12]	刘毅, 房强, 钟达忠, 赵强, 李晋平. Ag/Cu耦合催化剂的Cu晶面调控用于电催化二氧化碳还原[J]. 化工进展, 2023, 42(8): 4136-4142.
[13]	黄玉飞, 李子怡, 黄杨强, 金波, 罗潇, 梁志武. 光催化CO₂和CH₄重整催化剂研究进展[J]. 化工进展, 2023, 42(8): 4247-4263.
[14]	陈森, 殷鹏远, 杨证禄, 莫一鸣, 崔希利, 锁显, 邢华斌. 功能固体材料智能合成研究进展[J]. 化工进展, 2023, 42(7): 3340-3348.
[15]	娄宝辉, 吴贤豪, 张驰, 陈臻, 冯向东. 纳米流体用于二氧化碳吸收分离研究进展[J]. 化工进展, 2023, 42(7): 3802-3815.