基于人工智能混合模型的乙二醇电渗析脱盐优化

doi:10.16085/j.issn.1000-6613.2023-1814

化工进展 ›› 2024, Vol. 43 ›› Issue (11): 6049-6058.DOI: 10.16085/j.issn.1000-6613.2023-1814

• 化工过程与装备 • 上一篇

基于人工智能混合模型的乙二醇电渗析脱盐优化

李耀翔¹^,²(), 范峥¹(), 郝新宇³, 刘姝延⁴, 张叶⁵, 韩洁⁶

^1.西安石油大学化学化工学院，陕西西安 710065
^2.中石油华东设计院有限公司，山东青岛 266071
^3.陕西延长石油（集团）有限责任公司炼化公司，陕西延安 727406
^4.西北农林科技大学资源环境学院，陕西咸阳 712199
^5.深圳如钦巴科技集团有限公司，广东深圳 518126
^6.陕西铭泽易昇能源技术有限公司，陕西咸阳 712000

收稿日期:2023-10-16 修回日期:2024-05-06 出版日期:2024-11-15 发布日期:2024-12-07
通讯作者: 范峥
作者简介:李耀翔（1999—），男，硕士研究生，研究方向为石油天然气化工过程人工智能优化。E-mail：21212070950@stumail.xsyu.edu.cn。
基金资助:
中国国家留学基金(201908610135);西安石油大学研究生创新与实践能力培养项目(YCS23213076);2021年西安石油大学研究生教育综合改革研究与实践项目(2021-X-YJG-004)

Optimization of ethylene glycol electrodialysis desalination based on artificial intelligence hybrid model

LI Yaoxiang¹^,²(), FAN Zheng¹(), HAO Xinyu³, LIU Shuyan⁴, ZHANG Ye⁵, HAN Jie⁶

^1.College of Chemistry and Chemical Engineering, Xi’an Shiyou University, Xi’an 710065, Shaanxi, China
^2.CNPC EastChina Design Institute Company Limited, Qingdao 266071, Shandong, China
^3.Shaanxi Yanchang Petroleum (Group) Company Limited Refining and Chemical Company, Yan’an 727406, Shaanxi, China
^4.College of Natural Resources and Environment, Northwest A&F University, Xianyang 712199, Shaanxi, China
^5.Shenzhen Ruqinba Technology Group Company Limited, Shenzhen 518126, Guangdong, China
^6.Shaanxi Mingze Yisheng Energy Technology Company Limited, Xianyang 712000, Shaanxi, China

Received:2023-10-16 Revised:2024-05-06 Online:2024-11-15 Published:2024-12-07
Contact: FAN Zheng

摘要/Abstract

摘要：

利用小波神经网络和模拟退火-粒子群算法对电渗析法脱盐工艺进行参数优化。首先，通过单因素实验初步探讨了电渗析单位膜电压、操作时间、极板间距和极液浓度对脱盐效果的影响规律，然后利用小波神经网络模型对数据样本进行训练和预测，并对实验影响因素进行了Sobol灵敏度分析，最后将小波神经网络模型与模拟退火-粒子群算法相互耦合，得到了该体系下优化的电渗析条件及其对应的脱盐率。试凑法结果表明，4-10-8-1小波双隐层神经网络模型为适宜的预测模型；各因素对脱盐效果的作用程度由大到小依次为单位膜电压、操作时间、极液浓度和极板间距；当单位膜电压为0.42V/cm²、运行时间为13.85h、极板间距为12.11cm、极液浓度为0.21mol/L时，预测的优化脱盐率可达97.13%，经统计检定值（t）检验该值与验证实验结果高度一致。该研究可为乙二醇电渗析法脱盐工艺的全面推广和深度应用提供准确可靠的理论支撑和数据来源。

关键词: 乙二醇, 电渗析, 脱盐, 神经网络, 算法, 粒子群优化, 模拟退火

Abstract:

Utilizing wavelet neural network and simulated annealing-particle swarm optimization algorithm to optimize the parameters of electrodialysis desalination process. Firstly, a single factor experiment was conducted to preliminarily explore the influence of electrodialysis operation voltage, operation time, electrode plate spacing, and electrode liquid concentration on desalination efficiency. Then, a wavelet neural network model was used to train and predict the data samples, and Sobol sensitivity analysis was conducted on the experimental influencing factors. Finally, the wavelet neural network model was coupled with the simulated annealing-particle swarm optimization algorithm. The optimized electrodialysis conditions and corresponding desalination rates in this system were obtained. The trial-and-error method results indicated that the 4-10-8-1 wavelet double hidden layer neural network model was a suitable prediction model. The degree of influence of various factors on the desalination effect was in descending order: operating voltage, operating time, electrode liquid concentration, and electrode plate spacing. When the unit membrane voltage was 0.42V/cm², the operating time was 13.85 hours, the electrode spacing was 12.11cm, and the electrode liquid concentration was 0.21mol/L, the predicted optimized desalination rate reached 97.13%. After t-test, this value was highly consistent with the validation experimental results. This study can provide accurate and reliable theoretical support and data sources for the comprehensive promotion and deep application of ethylene glycol electrodialysis desalination process.

Key words: ethylene glycol, electrodialysis, desalination, neural network, algorithm, particle swarm optimization, simulated annealing

中图分类号:

TE646

李耀翔, 范峥, 郝新宇, 刘姝延, 张叶, 韩洁. 基于人工智能混合模型的乙二醇电渗析脱盐优化[J]. 化工进展, 2024, 43(11): 6049-6058.

LI Yaoxiang, FAN Zheng, HAO Xinyu, LIU Shuyan, ZHANG Ye, HAN Jie. Optimization of ethylene glycol electrodialysis desalination based on artificial intelligence hybrid model[J]. Chemical Industry and Engineering Progress, 2024, 43(11): 6049-6058.

图/表 13

图1 电渗析装置结构图

图2 小波双隐含层神经网络拓扑图

图3 基于WNN的模拟SA-PSO算法寻优流程图

图4 不同单位膜电压对电渗析效果的影响

图5 不同运行时间对电渗析效果的影响

图6 不同极板间距对电渗析效果的影响

图7 不同极液浓度对电渗析效果的影响

图8 各因素与脱盐率的关系图

图9 隐含层节点数对均方误差影响规律

图10 WNN模型期望输出与预测输出对比图

图11 各因素灵敏度系数直方图

图12 SA-PSO算法全局最优搜索过程

表1 EG电渗析法脱盐优化条件验证

序号	脱盐率	自由度	标准偏差	t值	p值
1	96.94%	2	0.0611	-3.4962	0.0730
2	97.06%
3	97.02%

参考文献 25

1	谢鹏, 常江涛, 肖卓临. 天然气水合物开采区内海床不均匀沉降对管道力学性能的影响[J]. 海洋工程, 2020, 38(6): 1-10.
	XIE Peng, CHANG Jiangtao, XIAO Zhuolin. Influence of uneven seabed subsidence on mechanical properties of pipeline in natural gas hydrate mining area[J]. The Ocean Engineering, 2020, 38(6): 1-10.
2	张吉红, 朱忠祥, 陈兆录, 等. PVP动力学抑制剂对乙二醇防冻效果的影响[J]. 石油化工, 2016, 45(12): 1513-1518.
	ZHANG Jihong, ZHU Zhongxiang, CHEN Zhaolu, et al. Influence of poly-N-vinylpyrrolidone as kinetic inhibitor on anti-freezing effect of ethylene glycol[J]. Petrochemical Technology, 2016, 45(12): 1513-1518.
3	赵方生, 马勇, 陈宾, 等. 乙二醇再生工艺在海上平台的应用[J]. 石油和化工设备, 2013, 16(5): 35-37.
	ZHAO Fangsheng, MA Yong, CHEN Bin, et al. Application of ethylene glycol regeneration process in offshore platform[J]. Petro & Chemical Equipment, 2013, 16(5): 35-37.
4	齐典伟, 张佳琦, 徐凤, 等. 严寒C区新型相变流体太阳能光热系统实验研究[J]. 工程热物理学报, 2023, 44(1): 183-190.
	QI Dianwei, ZHANG Jiaqi, XU Feng, et al. Experimental study of cold C-zone solar photothermal system based on phase change fluid[J]. Journal of Engineering Thermophysics, 2023, 44(1): 183-190.
5	朱海山, 李达. 陵水17-2气田“深海一号” 能源站总体设计及关键技术研究[J]. 中国海上油气, 2021, 33(3): 160-169.
	ZHU Haishan, LI Da. Research on overall design and key technologies of “Deep Sea No.1” energy station in LS17-2 gas field[J]. China Offshore Oil and Gas, 2021, 33(3): 160-169.
6	张亚南, 马来波, 高春娟, 等. 不同电流和电压对电渗析分离深层海水的影响[J]. 盐科学与化工, 2023, 52(1): 26-29.
	ZHANG Yanan, MA Laibo, GAO Chunjuan, et al. Effect of different current and voltage on electrodialysis separation of deep sea water[J]. Journal of Salt Science and Chemical Industry, 2023, 52(1): 26-29.
7	SHI Jihong, GONG Liang, ZHANG Tao, et al. Study of the seawater desalination performance by electrodialysis[J]. Membranes, 2022, 12(8): 767.
8	刘雪奇, 周洪, 梅拥军, 等. 电渗析对飞机除冰废水脱盐性能的研究[J]. 水处理技术, 2018, 44(7): 66-68, 82.
	LIU Xueqi, ZHOU Hong, MEI Yongjun, et al. Research on desalination performance of aircraft deicing waste fluid by electrodialysis[J]. Technology of Water Treatment, 2018, 44(7): 66-68, 82.
9	李鹏飞, 陈青柏, 王建友, 等. 含盐乙二醇溶液电渗析脱盐工艺研究[J]. 水处理技术, 2021, 47(10): 71-74.
	LI Pengfei, CHEN Qingbai, WANG Jianyou, et al. Research on electrodialysis desalination process of salt-containing ethylene glycol solution[J]. Technology of Water Treatment, 2021, 47(10): 71-74.
10	BRYSON F E, INGALL E D, HANNA A M, et al. Development of the miniature robotic electrodialysis (MR ED) system for small-scale desalting of liquid samples with recovery of organics[J]. Earth and Space Science, 2023, 10(3): 2022EA002620.
11	张傲, 王好, 冉凡, 等. 页岩气压裂返排液电渗析脱盐处理技术研究[J]. 工业水处理, 2022, 42(8): 102-107.
	ZHANG Ao, WANG Hao, RAN Fan, et al. Research on electrodialysis desalination technology for shale gas fracturing flowback fluid[J]. Industrial Water Treatment, 2022, 42(8): 102-107.
12	李世霖, 王毅霖, 杨雪莹, 等. 电渗析法处理高含盐有机废水中有机物迁移研究进展与发展方向[J]. 现代化工, 2023, 43(5): 70-73.
	LI Shilin, WANG Yilin, YANG Xueying, et al. Research progress on organics migration in electrodialysis treatment of high salinity organic wastewater and development direction[J]. Modern Chemical Industry, 2023, 43(5): 70-73.
13	GONG Wenyin, CAI Zhihua, JIANG Liangxiao. Enhancing the performance of differential evolution using orthogonal design method[J]. Applied Mathematics and Computation, 2008, 206(1): 56-69.
14	JI Yun. Fuzzy reliability analysis of nonlinear structural system based on stochastic response surface method[J]. Advanced Materials Research, 2014, 912/913/914: 1268-1271.
15	梁生荣, 李文君, 翁军利, 等. 基于BP神经网络的天然气采气管线甲醇加注量预测及其分配管网优化[J]. 石油与天然气化工, 2020, 49(6): 45-52.
	LIANG Shengrong, LI Wenjun, WENG Junli, et al. Quantitative prediction of the methanol injection for natural gas production pipelines based on BP artificial neural networks and optimization of the distribution network[J]. Chemical Engineering of Oil & Gas, 2020, 49(6): 45-52.
16	张东东. 人工神经网络图像模式识别综述[J]. 电子世界, 2018(9): 97.
	ZHANG Dongdong. Summary of image pattern recognition based on artificial neural network[J]. Electronics World, 2018(9): 97.
17	李光保, 高栋, 路勇, 等. 基于改进神经网络与Fluent的气液固技术的内表面处理[J]. 吉林大学学报(工学版)， 54(6): 1537-1547.
	LI Guangbao, GAO Dong, LU Yong, et al. Internal surface treatment of gas-liquid-solid technology based on improved neural network and Fluent[J]. Journal of Jilin University(Engineering and Technology Edition)， 54(6): 1537-1547.
18	刘文杰, 余昊, 陈冬梅. 基于GA-BP神经网络的航空涡轮组件再制造工时预测[J]. 机械设计, 2023, 40(8): 69-75.
	LIU Wenjie, YU Hao, CHEN Dongmei. Prediction of remanufacturing man-hours for aero-engine turbine components based on GA-BP neural network[J]. Journal of Machine Design, 2023, 40(8): 69-75.
19	LIRA Jéssica O B, RIELLA Humberto G, PADOIN Natan, et al. Computational fluid dynamics (CFD), artificial neural network (ANN) and genetic algorithm (GA) as a hybrid method for the analysis and optimization of micro-photocatalytic reactors: NOx abatement as a case study[J]. Chemical Engineering Journal, 2022, 431: 133771.
20	王郁, 解利昕, 李凭力, 等. 低盐汲取液电渗析系统脱盐性能研究[J]. 水处理技术, 2013, 39(11): 29-32, 35.
	WANG Yu, XIE Lixin, LI Pingli, et al. Study on desalination performance of electrodialysis system with low-salinity draw solution[J]. Technology of Water Treatment, 2013, 39(11): 29-32, 35.
21	王保国, 刘淑艳, 钱耕, 等. 一种小波神经网络与遗传算法结合的优化方法[J]. 航空动力学报, 2008, 23(11): 1953-1960.
	WANG Baoguo, LIU Shuyan, QIAN Geng, et al. Optimization method by combination of wavelet neural networks and genetic algorithm[J]. Journal of Aerospace Power, 2008, 23(11): 1953-1960.
22	何恩业, 杨静, 李尚鲁, 等. 基于双隐层ANN模型的叶绿素a浓度智能预报方法[J]. 海洋预报, 2021, 38(1): 43-53.
	HE Enye, YANG Jing, LI Shanglu, et al. Intelligent prediction method for Chl-a based on the artificial neural network[J]. Marine Forecasts, 2021, 38(1): 43-53.
23	ARASOMWAN Martins Akugbe, ADEWUMI Aderemi Oluyinka. On the performance of linear decreasing inertia weight particle swarm optimization for global optimization[J]. The Scientific World Journal, 2013, 2013: 860289.
24	员汝娜, 马海霞, 夏勇, 等. 电渗析法处理被污染的三甘醇工艺优化[J]. 精细化工, 2015, 32(11): 1278-1283.
	YUN Runa, MA Haixia, XIA Yong, et al. Optimization for treatment of contaminated triethylene glycol by electrodialysis process[J]. Fine Chemicals, 2015, 32(11): 1278-1283.
25	ROTTIERS T, DE LA MARCHE G, VAN DER BRUGGEN B, et al. Co-ion fluxes of simple inorganic ions in electrodialysis metathesis and conventional electrodialysis[J]. Journal of Membrane Science, 2015, 492: 263-270.

[1]	戴征舒, 左元浩, 陈孝罗, 张犁, 赵根, 张学军, 张华. 机器学习在喷射器研究中的应用进展[J]. 化工进展, 2024, 43(S1): 1-12.
[2]	邹志云, 于蒙, 刘英莉. 基于LSTM和BP神经网络的间歇蒸馏过程工况预测[J]. 化工进展, 2024, 43(S1): 21-31.
[3]	王博葳, 郑明朕, 王乐萌, 付东, 王珊, 朱生俊, 赵昆, 张盼. Na₂SO₄电解制备NaOH捕集CO₂[J]. 化工进展, 2024, 43(S1): 604-614.
[4]	王亚男, 刘琳琳, 庄钰, 都健. 基于代理模型的环氧乙烷制乙二醇工艺优化同步热集成[J]. 化工进展, 2024, 43(9): 5234-5241.
[5]	李依梦, 陈运全, 何畅, 张冰剑, 陈清林. 基于物理信息神经网络的甲烷无氧芳构化反应的正反问题[J]. 化工进展, 2024, 43(9): 4817-4823.
[6]	张佳鑫, 张淼, 戴一阳, 董立春. 面向实际化工过程故障诊断的强化深度卷积神经网络模型构建与应用[J]. 化工进展, 2024, 43(9): 4833-4844.
[7]	张笑恬, 刘思琪, 崔国民, 黄晓璜, 段欢欢, 王金阳. 基于定向协调策略改进换热单元优化的换热网络综合[J]. 化工进展, 2024, 43(8): 4342-4353.
[8]	怀立业, 仲兆平, 杨宇轩. 脱硫石膏转化α-半水石膏的特征及机理：实验与模拟[J]. 化工进展, 2024, 43(8): 4694-4703.
[9]	李凯, 魏鹤琳, 尹志凡, 左夏华, 于晓宇, 尹宏远, 杨卫民, 阎华, 安瑛. 基于GA-BP神经网络模型预测水基炭黑-胶原蛋白纳米流体热导率和黏度[J]. 化工进展, 2024, 43(7): 4138-4147.
[10]	易智康, 刘思琪, 崔国民, 段欢欢, 肖媛. 有分流棋盘模型应用于不相容多组分质量交换网络优化[J]. 化工进展, 2024, 43(6): 2986-2995.
[11]	冼学权, 杜芳黎, 刘忠林, 刘婉玉, 黎演明, 龙思宇, 黄华林. 利用PEG/Na₂CO₃双水相乳液法制备碳酸钙微球及其形成机理[J]. 化工进展, 2024, 43(6): 3221-3231.
[12]	郑可欣, 江雨欣, 毕可鑫, 赵祺铭, 陈少臣, 王冰冰, 任俊宇, 吉旭, 邱彤, 戴一阳. 用于蒸汽裂解产物成分预测的集成迁移学习框架[J]. 化工进展, 2024, 43(5): 2880-2889.
[13]	李萍, 陈修乐, 张强, 念腾飞, 王育兴, 王盟. 抑烟沥青复掺配比优化及抑烟效果评价[J]. 化工进展, 2024, 43(4): 1923-1933.
[14]	张瑞, 寇悦, 孙鹤, 王辰予, 李琢宇, 王庆宏, 陈春茂. 汽提净化水回用原油电脱盐过程的溶解性有机物转移特征[J]. 化工进展, 2024, 43(4): 2153-2160.
[15]	张书铭, 刘化章. 基于BP神经网络模型优化Fe_1-_x O基氨合成催化剂[J]. 化工进展, 2024, 43(3): 1302-1308.

基于人工智能混合模型的乙二醇电渗析脱盐优化

Optimization of ethylene glycol electrodialysis desalination based on artificial intelligence hybrid model

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 25

相关文章 15

编辑推荐

Metrics

本文评价