神经网络时间序列方法对混合氨基酸盐溶液二氧化碳吸收数据预测

熊昊晨; 秦佳敏; 武西宁; 赵国庆; 聂艳; 徐龙

doi:10.12434/j.issn.2097-2547.20240505

您当前的位置：

首页 >

文章列表页 >

神经网络时间序列方法对混合氨基酸盐溶液二氧化碳吸收数据预测

更新时间：2025-05-08

- 神经网络时间序列方法对混合氨基酸盐溶液二氧化碳吸收数据预测
- Prediction of carbon dioxide absorption data in mixed amino acid salt solution by neural network time series method
- 低碳化学与化工 2025: 1-10.
- 作者机构：
  
  西北大学化工学院，碳氢资源清洁利用国际科技合作基地，陕北能源先进化工利用技术教育部工程研究中心，陕西省洁净煤转化工程技术研究中心，陕北能源化工产业发展协同创新中心，陕西西安 710127
- 作者简介：
  
  熊昊晨（2001—），硕士研究生，研究方向为二氧化碳减排与机器学习，E-mail：X1581274056X@163.com。
  徐龙（1976—），博士，教授，研究方向为二氧化碳减排与综合利用，E-mail：longxuxulong@163.com。
- 基金信息：
  
  陕西省创新能力支撑计划(2024RS-CXTD-53);陕西省重点研发计划(2024GX-YBXM-428)
- DOI：10.12434/j.issn.2097-2547.20240505
  中图分类号： TQ028
- 收稿日期：2024-12-20，
  
  修回日期：2025-02-14，
  
  网络出版日期：2025-05-06，
- 稿件说明：
移动端阅览
熊昊晨,秦佳敏,武西宁等.神经网络时间序列方法对混合氨基酸盐溶液二氧化碳吸收数据预测[J].低碳化学与化工,

XIONG Haochen,QIN Jiamin,WU Xining,et al.Prediction of carbon dioxide absorption data in mixed amino acid salt solution by neural network time series method[J].Low-Carbon Chemistry and Chemical Engineering,
熊昊晨,秦佳敏,武西宁等.神经网络时间序列方法对混合氨基酸盐溶液二氧化碳吸收数据预测[J].低碳化学与化工, DOI：10.12434/j.issn.2097-2547.20240505.

XIONG Haochen,QIN Jiamin,WU Xining,et al.Prediction of carbon dioxide absorption data in mixed amino acid salt solution by neural network time series method[J].Low-Carbon Chemistry and Chemical Engineering, DOI：10.12434/j.issn.2097-2547.20240505.

摘要

氨基酸盐溶液作为二氧化碳吸收剂具有吸收速率快、吸收负荷大和毒性低等优点，是二氧化碳捕集领域的研究热点之一。以质量分数分别为15%、15%和5%的N-甲基二乙醇胺（MDEA）、乙醇胺和赖氨酸钾组成的混合氨基酸盐溶液作为二氧化碳吸收剂，利用基于反向传播（BP）算法的神经网络时间序列方法对该吸收剂在400 min内、不同温度下的二

氧化碳吸收数据进行预测，并将预测数据与实验数据进行了对比。结果表明，预测模型的最优超参数为输入层-隐含层-输出层4-7-1、初始阻尼因子0.05、Tansig函数作激活函数，采用Levenberg-Marquardt算法迭代的粒子群（PSO）-BP神经网络算法。在对数据进行多次模拟后，该预测模型的平均均方误差为1.8289 × 10

-11

。在所得最优超参数下，使用验证组在验证组+训练组中占比为70%、决定系数为0.9836的模型进行预测时，在400 min、40 ℃下，吸收负荷预测数据与实验数据的最大相对误差为2.031%。

Abstract

Amino acid salt solutions

as carbon dioxide absorbents

have garnered significant attention in the field of CO

capture due to their advantages of rapid absorption rate

high absorption capacity

and low toxicity. Using the mixed amino acid salt solution with mass fraction of 15% N-methyldiethanolamine (MDEA)

15% monoethanolamine

and 5% potassium lysine

respectively

as the CO

absorbent

a neural network time series method based on backpropagation (BP) algorithm was utilized to predict CO

absorption data under varying temperatures during 400 min

and the predicted data were systematically compared with experimental data. The results show that the optimal hyperparameters for the prediction model are as follows: 4-7-1 architecture for input-hidden-output layers

initial damping factor of 0.05

Tansig function as activation function

and the algorithm of Particle Swarm Optimization (PSO)-BP neural network algorithm integrated with Levenberg-Marquardt iterative optimization. After multiple data simulations

the model achieved an average mean squared error of 1.8289 × 10

-11

. With the optimal hyperparameters

using the model with the verification group proportion of 70% in verification group and training group and the determination coefficient of 0.9836

the maximum relative error between predicted and experimental absorption capacity values reaches 2.031% at 40 °C during 400 minute.

关键词

Keywords

references

张守营 . 在安全供应前提下推进能源清洁低碳转型 [N ] . 中国经济导报 , 2023-10-19 (007).

ZHANG S Y . Promoting energy clean and low-carbon transformation under the premise of safety supply [N ] . China Economic Herald , 2023-10-19 (007).

王建行 , 赵颖颖 , 李佳慧 , 等 . 二氧化碳的捕集、固定与利用的研究进展 [J ] . 无机盐工业 , 2020 , 52 ( 4 ): 12 - 17 .

WANG J X , ZHAO Y Y , LI J H , et al . Research progress of carbon dioxide capture, fixation and utilization [J ] . Inorganic Chemicals Industry , 2020 , 52 ( 4 ): 12 - 17 .

夏明珠 , 严莲荷 , 雷武 , 等 . 二氧化碳的分离回收技术与综合利用 [J ] . 现代化工 , 1999 , 20 ( 5 ): 48 - 50 .

XIA M Z , YAN L H , LEI W , et al . Separation, recovery and comprehensive utilization of carbon dioxide [J ] . Modern Chemical Industry , 1999 , 20 ( 5 ): 48 - 50 .

杨开宇 . 燃煤电厂二氧化碳捕捉技术进展研究 [J ] . 能源与节能 , 2022 , 27 ( 1 ): 49 - 53 .

YANG K Y . Research on CO 2 capture technology progress for coal-fired power plant [J ] . Energy and Energy Conservation , 2022 , 27 ( 1 ): 49 - 53 .

宋倩倩 , 蒋庆哲 , 宋昭峥 . 炼油厂CO 2 分离技术的研究 [J ] . 现代化工 , 2015 , 35 ( 3 ): 12 - 17 .

SONG Q Q , JIANG Q Z , SONG Z Z . CO 2 separation technologies in oil refineries [J ] . Modern Chemical Industry , 2015 , 35 ( 3 ): 12 - 17 .

SONG H J , PARK S W , KIM H T , et al . Carbon dioxide absorption characteristics of aqueous amino acid salt solutions [J ] . International Journal of Greenhouse Gas Control , 2012 , 11 : 64 - 72 .

HALLENBECK A P , EGBEBI A , RESNIK K P , et al . Comparative microfluidic screening of amino acid salt solutions for post-combustion CO 2 capture [J ] . International Journal of Greenhouse Gas Control , 2015 , 43 : 189 - 197 .

PORTUGAL A F , SOUSA J M , MAGALHÃES F D , et al . Solubility of carbon dioxide in aqueous solutions of amino acid salts [J ] . Chemical Engineering Science , 2009 , 64 ( 9 ): 1993 - 2002 .

KONTOS G , LEONTIADIS K , TSIVINTZELIS I . CO 2 solubility in aqueous solutions of blended amines: Experimental data for mixtures with MDEA, AMP and MPA and modeling with the modified Kent-Eisenberg model [J ] . Fluid Phase Equilibria , 2023 , 570 : 113800 .

付柯 , 谢良才 , 闫雨瑗 , 等 . 改进BP神经网络预测Ni/Al 2 O 3 催化CH 4 -CO 2 重整反应 [J ] . 化工进展 , 2017 , 36 ( 7 ): 2393 - 2399 .

FU K , XIE L C , YAN Y Y , et al . Predicting model of CH 4 -CO 2 reforming on Ni/Al 2 O 3 catalyst by improved back propagation (BP) neural network [J ] . Chemical Industry and Engineering Progress , 2017 , 36 ( 7 ): 2393 - 2399 .

ZHANG Z E , LI Y F , ZHANG W X , et al . Effectiveness of amino acid salt solutions in capturing CO 2 : A review [J ] . Renewable and Sustainable Energy Reviews , 2018 , 98 : 179 - 188 .

SOROUSH E , MESBAH M , HAJILARY N , et al . ANFIS modeling for prediction of CO 2 solubility in potassium and sodium based amino acid salt solutions [J ] . Journal of Environmental Chemical Engineering , 2019 , 7 ( 1 ): 102925 .

CUI K , JING X . Research on prediction model of geotechnical parameters based on BP neural network [J ] . Neural Computing and Applications , 2019 , 31 ( 12 ): 8205 - 8215 .

LECUN Y , BOTTOU L , BENGIO Y , et al . Gradient-based learning applied to document recognition [J ] . Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 .

RUMELHART D E , HINTON G E , WILLIAMS R J . Learning representations by back-propagating errors [J ] . Nature , 1986 , 323 ( 6088 ): 533 - 536 .

王吉权 . BP神经网络的理论及其在农业机械化中的应用研究 [D ] . 沈阳 : 沈阳农业大学 , 2012 .

WANG J Q . Research on BP neural network theory and its application in agricultural mechanization [D ] . Shenyang : Shenyang Agricultural University , 2012 .

艾洪福 , 石莹 . 基于BP人工神经网络的雾霾天气预测研究 [J ] . 计算机仿真 , 2015 , 32 ( 1 ): 402 - 405+415 .

AI H F , SHI Y . Study on prediction of haze based on BP neural network [J ] . Computer Simulation , 2015 , 32 ( 1 ): 402 - 405+415 .

江岳春 , 张丙江 , 邢方方 , 等 . 基于混沌时间序列GA-VNN模型的超短期风功率多步预测 [J ] . 电网技术 , 2015 , 39 ( 8 ): 2160 - 2166 .

JIANG Y C , ZHANG B J , XING F F , et al . Super-short-term multi-step prediction of wind power based on GA-VNN model of chaotic time series [J ] . Power System Technology , 2015 , 39 ( 8 ): 2160 - 2166 .

刘书含 , 孙文强 , 石晓星 , 等 . 基于BP神经网络的热风炉群煤气消耗量预测 [J ] . 中国冶金 , 2022 , 32 ( 2 ): 77 - 83 .

LIU S H , SUN W Q , SHI X X , et al . Prediction of gas consumption of a hot blast stove group based on BP neutral network [J ] . China Metallurgy , 2022 , 32 ( 2 ): 77 - 83 .

马国光 , 周明杰 , 雷洋 , 等 . 氮气双膨胀制冷提氦联产乙烷工艺设计与优化 [J ] . 低碳化学与化工 , 2024 , 49 ( 10 ): 110 - 118 .

MA G G , ZHOU M J , LEI Y , et al . Process design and optimization of helium extraction and ethane co-production by nitrogen double expansion refrigeration [J ] . Low-Carbon Chemistry and Chemical Engineering , 2024 , 49 ( 10 ): 110 - 118 .

钟颖 , 汪秉文 . 基于遗传算法的BP神经网络时间序列预测模型 [J ] . 系统工程与电子技术 , 2002 , 24 ( 4 ): 9 - 11 .

ZHONG Y , WANG B W . BP network sequence prediction model based on genetic algorithm [J ] . Systems Engineering and Electronics , 2002 , 24 ( 4 ): 9 - 11 .

周启超 . BP算法改进及在软件成本估算中的应用 [J ] . 计算机技术与发展 , 2016 , 26 ( 2 ): 195 - 198 .

ZHOU Q C . Improvement of BP algorithms and its application in software cost estimation [J ] . Computer Technology and Development , 2016 , 26 ( 2 ): 195 - 198 .

王嵘冰 , 徐红艳 , 李波 , 等 . BP神经网络隐含层节点数确定方法研究 [J ] . 计算机技术与发展 , 2018 , 28 ( 4 ): 31 - 35 .

WANG R B , XU H Y , LI B , et al . Research on method of determining hidden layer nodes in BP neural network [J ] . Computer Technology and Development , 2018 , 28 ( 4 ): 31 - 35 .

孙佰清 , 潘启树 , 冯英浚 , 等 . 提高BP网络训练速度的研究 [J ] . 哈尔滨工业大学学报 , 2001 , 48 ( 4 ): 439 - 441 .

SUN B Q , PAN Q S , FENG Y Jet al . Improvement of BP network training rate [J ] . Journal of Harbin Institute of Technology , 2001 , 48 ( 4 ): 439 - 441 .

CHEN X Y , CHAU K W , BUSARI A O . A comparative study of population-based optimization algorithms for downstream river flow forecasting by a hybrid neural network model [J ] . Engineering Applications of Artificial Intelligence , 2015 , 46 : 258 - 268 .

JIA W K , ZHAO D A , SHEN T A , et al . An optimized classification algorithm by BP neural network based on PLS and HCA [J ] . Applied Intelligence , 2015 , 43 ( 1 ): 176 - 191 .

于小岚 , 熊伟 , 韩驰 . 基于神经网络的效能评估方法综述 [J ] . 兵工自动化 , 2023 , 42 ( 3 ): 1 - 8+43 .

YU X L , XIONG W , HAN C . A survey of effectiveness evaluation methods based on neural network [J ] . Ordnance and Industry Automation , 2023 , 42 ( 3 ): 1 - 8+43 .

MORÉ J J . The Levenberg-Marquardt algorithm: Implementation and theory [C ] //WATSON G A. Numerical Analysis . Berlin : Springer , 1978 : 105 - 116 .

刘建华 . 粒子群算法的基本理论及其改进研究 [D ] . 长沙 : 中南大学 , 2010 .

LIU J H . The Research of basic theory and improvement on particle swarm optimization [D ] . Changsha : Central South University , 2010 .

葛继科 , 邱玉辉 , 吴春明 , 等 . 遗传算法研究综述 [J ] . 计算机应用研究 , 2008 , 25 ( 10 ): 2911 - 2916 .

GE J K , QIU Y H , WU C M , et al . Summary of genetic algorithms research , [J ] . Application Research of Computers , 2008 , 25 ( 10 ): 2911 - 2916 .

文绍纯 , 罗飞 , 付连续 . 遗传算法在人工神经网络中的应用综述 [J ] . 计算技术与自动化 , 2001 , 20 ( 2 ): 1 - 5 .

WEN S C , LUO F , F L X . Survey on the application of genetic algorithms in the artificial neural networks [J ] . Computing Technology and Automation , 2001 , 20 ( 2 ): 1 - 5 .

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据