基于BP神经网络的电化学还原硝酸盐过程智能控制

doi:10.13208/j.electrochem.211215

电化学（中英文） ›› 2023, Vol. 29 ›› Issue (12): 211215. doi: 10.13208/j.electrochem.211215

所属专题： “电催化和燃料电池”专题文章； “AI for Electrochemistry”专题文章； “电有机合成、水处理”专题文章

基于BP神经网络的电化学还原硝酸盐过程智能控制

张芯婉^a, 孟广源^a^,^*(), 方立强^a, 常定明^b, 李童^c, 胡锦文^a, 陈鹏^a^,^d, 刘勇弟^a^,^d, 张乐华^a^,^d^,^*()

^a华东理工大学高浓度难降解有机废水处理技术国家工程实验室，上海 200237
^b上海易湃富得环保科技有限公司，上海 200082
^c亳州大学继续教育中心，安徽亳州 236800
^d华东理工大学国家环境保护化工过程环境风险评价与控制重点实验室，上海 200237

收稿日期:2021-12-15 修回日期:2022-03-18 接受日期:2022-03-22 出版日期:2023-12-28 发布日期:2022-03-31
通讯作者: *孟广源，Tel: Tel: (86)19117198860，E-mail: mengguangyuan1997@outlook.com;张乐华，Tel: (86-21)64253321, E-mail: lezhanghua@163.com
基金资助:
国家重点研发计划(2019YFC0408202);国家自然科学基金(21876050)

Intelligent Control Based on BP Artificial Neural Network for Electrochemical Nitrate Removal

Xin-Wan Zhang^a, Guang-Yuan Meng^a^,^*(), Li-Qiang Fang^a, Ding-Ming Chang^b, Tong Li^c, Jin-Wen Hu^a, Peng Chen^a^,^d, Yong-Di Liu^a^,^d, Le-Hua Zhang^a^,^d^,^*()

^aNational Engineering Laboratory of High Concentration Refractory Organic Wastewater Treatment Technology, East China University of Science and Technology, Shanghai 200237, China
^bShanghai Espac Environmental Technology Co., Ltd., Shanghai 200082, China
^cContinuing Education Center, Bozhou University, Bozhou 236800, China
^dState Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process, East China University of Science and Technology, Shanghai 200237, China

Received:2021-12-15 Revised:2022-03-18 Accepted:2022-03-22 Published:2023-12-28 Online:2022-03-31

摘要/Abstract

摘要：

电化学还原硝酸盐过程关键在于该废水处理过程中参数的有效控制。基于硝态氮电化学还原的测试数据和各参数间的相关性，得出与出水效果密切相关的四因素，即反应时间、初始浓度、初始pH和电流密度，采用BP神经网络算法建立了电化学法还原硝态氮的预测模型，并验证了模型的准确性。结果表明，4-7-1型BP神经网络网络构型最优，模型预测的去除效果与实测值相吻合，R²为0.9095。利用BP神经网络模型对参数调控，可以优化电化学处理过程：对电流密度进行阶段性调控，在相同处理量下可降低15%的能耗；在水质波动情况下进行电流密度控制，在相同处理时间内可保证出水达标。该研究结果可以为智能控制电化学去除硝态氮的过程提供参考。

关键词: 硝态氮, 电化学还原, BP神经网络, 预测模型, 智能控制

Abstract:

Achieving effective control of parameters in the process of nitrate wastewater treatment is critical to electrochemical water treatment. The powerful nonlinear mapping ability, self-adaptation and self-learning ability of neural network technology can optimize the electrochemical processing. However, there are few researches in this direction. Hence, based on the test data of the electrochemical reduction of nitrate, an electrochemical prediction model was established by using the BP neural network algorithm. Considering the correlation of various parameters in the electrochemical process, the reaction time, initial nitrate nitrogen concentration, pH and current density were determined as the input layer of the BP neural network for model establishment. Results showed that the optimal network configuration of 4-7-1 was achieved by optimizing the hyperparameters of hidden layers number, and the numbers of neurons and epochs. The predicted value of nitrate nitrogen concentration was consistent with the measured value, and the R² value of 0.9095 was obtained. Meanwhile, the model predicts the effects of initial concentration, pH and current density on the removal efficiency of nitrate nitrogen. In the weak alkaline environment, the stability and reliability of nitrate electroreduction were higher than those in acidic and alkaline environments, and the predicted value of nitrate nitrogen is highly correlated to the true value (R²=0.9908). The initial concentration was negatively correlated to the removal rate, while the current density was positively correlated. Finally, the neural network model was used to control the electrochemical nitrate reduction process. Energy consumption tests were designed by optimizing current density, and 15% reduction energy consumption was obtained within the same processing time and processing efficiency. Also, through the prediction model, the effluent quality can be guaranteed by timely adjusting the parameter in the case of sudden water quality changes. The research results can provide a reference for the intelligent control in the electrochemical removal of nitrate. At the same time, combining the understanding of the electrochemical treatment system and artificial intelligence technology, several ideas are proposed for the application of artificial intelligence technology in the field of electrochemical water treatment.

Key words: Nitrate nitrogen, Electrochemical reduction, BPNN, Prediction model, Intelligent control

张芯婉, 孟广源, 方立强, 常定明, 李童, 胡锦文, 陈鹏, 刘勇弟, 张乐华. 基于BP神经网络的电化学还原硝酸盐过程智能控制[J]. 电化学（中英文）, 2023, 29(12): 211215.

Xin-Wan Zhang, Guang-Yuan Meng, Li-Qiang Fang, Ding-Ming Chang, Tong Li, Jin-Wen Hu, Peng Chen, Yong-Di Liu, Le-Hua Zhang. Intelligent Control Based on BP Artificial Neural Network for Electrochemical Nitrate Removal[J]. Journal of Electrochemistry, 2023, 29(12): 211215.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://electrochem.xmu.edu.cn/CN/10.13208/j.electrochem.211215

https://electrochem.xmu.edu.cn/CN/Y2023/V29/I12/211215

图/表 9

图1

图2

表1

图3

图4

表2

图5

表3

图6

参考文献 22

[1]	Zhao X Y, Zhao K, Quan X, Chen S, Yu H T, Zhang Z H, Niu J F, Zhang S S. Efficient electrochemical nitrate removal on Cu and nitrogen doped carbon[J]. Chem. Eng. J., 2021, 415: 128958. doi: 10.1016/j.cej.2021.128958 URL
[2]	Huang J X, Xu J Y, Liu X Q, Liu J, Wang L M. Spatial distribution pattern analysis of groundwater nitrate nitrogen pollution in Shandong intensive farming regions of China using neural network method[J]. Math. Comput. Model., 2011, 54(3-4): 995-1004. doi: 10.1016/j.mcm.2010.11.027 URL
[3]	WHO. Guidelines for drinking-water quality. 2nd ed. Volume 1: Recommendations[J]. Geneva Switzerland Who, 1993.
[4]	Niu H, Zhang Z F, Wang X T, Wan X H, Shao C, Guo Y Z. Theoretical insights into the mechanism of selective nitrate-to-ammonia electroreduction on single-atom catalysts[J]. Adv. Funct. Mater., 2020, 31(11): 2008533. doi: 10.1002/adfm.v31.11 URL
[5]	Singh R M, Datta B. Artificial neural network modeling for identification of unknown pollution sources in groundwater with partially missing concentration observation data[J]. Water Resour. Manag., 2007, 21(3): 557-572. doi: 10.1007/s11269-006-9029-z URL
[6]	Nolan B T, Fienen M N, Lorenz D L. A statistical learning framework for groundwater nitrate models of the Central Valley, California, USA[J]. J. Hydrol., 2015, 531: 902-911. doi: 10.1016/j.jhydrol.2015.10.025 URL
[7]	Saleh B A, Kayi H. Prediction of chemical oxygen demand from the chemical composition of wastewater by artificial neural networks[J]. J. Phys. Conf. Ser., 2021, 1818(1): 012035. doi: 10.1088/1742-6596/1818/1/012035
[8]	Debnath A, Majumder M, Pal M, Das N S, Chattopadhyay K K, Saha B. Enhanced adsorption of hexavalent chromium onto magnetic calcium ferrite nanoparticles: Kinetic, isotherm, and neural network modeling[J]. J. Disper. Sci. Technol., 2016, 37(12): 1806-1818. doi: 10.1080/01932691.2016.1141100 URL
[9]	Chen Z Q, Wang H C, Chen Z B, Ren N Q, Wang A J, Shi Y, Li X M. Performance and model of a full-scale up-flow anaerobic sludge blanket (UASB) to treat the pharmaceutical wastewater containing 6-APA and amoxicillin[J]. J. Hazard. Mater., 2011, 185(2-3): 905-913. doi: 10.1016/j.jhazmat.2010.09.106 pmid: 20970923
[10]	Tabatabai-Yazdi F S, Pirbazari A E, Saraei F E K, Gilani N. Construction of graphene based photocatalysts for photocatalytic degradation of organic pollutant and modeling using artificial intelligence techniques[J]. Physica B, 2021, 608: 412869. doi: 10.1016/j.physb.2021.412869 URL
[11]	Karaboga D, Kaya E. Adaptive network based fuzzy inference system (ANFIS) training approaches: a comprehensive survey[J]. Artif. Intell. Rev., 2019, 52(4): 2263-2293. doi: 10.1007/s10462-017-9610-2
[12]	Huang W W, Zhang B G, Li M, Chen N, Feng C P, Zhang Z Y. An electrochemical process intensified by bipolar iron particles for nitrate removal from synthetic groundwater[J]. J. Solid State Electr., 2013, 17(4): 1013-1020. doi: 10.1007/s10008-012-1956-4 URL
[13]	Xu D, Li Y, Yin L F, Ji Y Y, Niu J F, Yu Y X. Electrochemical removal of nitrate in industrial wastewater[J]. Front. Env. Sci. Eng., 2018, 12(1): 9. doi: 10.1007/s11783-018-1033-z
[14]	Wang Y T, Wang C H, Li M Y, Yu Y F, Zhang B. Nitrate electroreduction: mechanism insight, in situ characterization, performance evaluation, and challenges[J]. Chem. Soc. Rev., 2021, 50(12): 6720-6733. doi: 10.1039/D1CS00116G URL
[15]	Nasr M, Ateia M, Hassan K. Artificial intelligence for greywater treatment using electrocoagulation process[J]. Sep. Sci. Technol., 2016, 51(1): 96-105. doi: 10.1080/01496395.2015.1062399 URL
[16]	Manokaran P, Saravanathamizhan R, Basha C A, Kannadasan T. Feed-forward back-propagation neural network for the electro-oxidation of distillery effluent[J]. Chem. Eng. Commun., 2014, 201(10): 1404-1416. doi: 10.1080/00986445.2013.809710 URL
[17]	Moosavi S M, Chidambaram A, Talirz L, Haranczyk M, Stylianou K C, Smit B. Capturing chemical intuition in synthesis of metal-organic frameworks[J]. Nat. Commun., 2019, 10: 539. doi: 10.1038/s41467-019-08483-9 pmid: 30710082
[18]	Chen J W, Xu J, Wang Y L, Zhang H W, Li X H. Granary rice temperature prediction model based on BP neural[J]. Mod. Electron. Tech., 2021, 44(19): 178-182.
[19]	Song J Q, Li J, Chen G H, Zhang Z J. Influence of pH on denitrification with embedded immobilized technology[J]. China Water & Wastewater, 2019, 35(3): 78-82.
[20]	Luo Y, Yuan W, Luo L Y, Chen M C, Tang J, Wan W L, Fan J Z. Model of PM2.5 concentration prediction based on multivariable hybrid long short-term memory neural network in Changsha[J]. Sci. Technol. Eng., 2021, 21(25): 10967-10975.
[21]	Robissout D, Zaid G, Colombier B, Bossuet L, Habrard A. Online Performance evaluation of deep learning networks for profiled side-channel analysis[J]. International Workshop on Constructive Side-Channel Analysis and Secure Design, 2021, 12244: 200-218.
[22]	Huang W L, Li M, Zhang B G, Feng C P, Lei X H, Xu B. Influence of operating conditions on electrochemical reduction of nitrate in groundwater[J]. Water Environ. Res., 2013, 85(3): 224-231. pmid: 23581237

Parameter	Time	Initial concentration	Current density	Conductivity	pH	Dissolved oxygen concentration	30-min removal
Time	1	0.1470	-0.0810	0.3161	0.4522	0.0420	-0.4103
Initial concentration	0.1470	1	0.2015	0.4350	0.1818	-0.0605	0.3183
Current density	-0.0810	0.2015	1	0.0735	-0.0594	-0.110	0.1709
Conductivity	0.3161	0.4350	0.0735	1	0.4906	0.0508	0.0823
pH	0.4522	0.1818	-0.0593	0.4906	1	0.0709	-0.1863
Dissolved oxygen concentration	0.0420	-0.0605	-0.1105	0.0508	0.0709	1	-0.0555
30-min removal	-0.4103	0.3183	0.1709	0.0823	-0.1863	-0.0555	1

Group	Initial concentration /(mg·L^-1)	Current density /(mA·cm^-2)	Time /(min)	Final concentration /(mg·L^-1)	Target concentration /(mg·L^-1)	Relative energy consumption /(%)
Before regulation	89.64	7.6	120	53.39	53.78	100
After regulation	89.64	4.4	30	82.03	53.78	85
		4.4→4	60	70.48
		4→11.2	90	59.46
		11.2→6.4	120	53.58

Group	Initial concentration /(mg·L^-1)	Current density /(mA·cm^-2)	Time/(min)	Final concentration /(mg·L^-1)	Target concentration /(mg·L^-1)
Before change	94.69	7.6	120	56.86	58.90
After change	94.69	7.6	30	84.46	58.90
	84.46→91.30	7.6→12.5	60	75.05
	75.05→84.46	12.5→16.8	90	66.83
	66.83	16.8→18.8	120	58.90

基于BP神经网络的电化学还原硝酸盐过程智能控制

Intelligent Control Based on BP Artificial Neural Network for Electrochemical Nitrate Removal

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 22

相关文章 15

Metrics

[1]	毛麟, 钮东方, 胡硕真, 张新胜. 电化学合成乙酰基吡嗪[J]. 电化学（中英文）, 2022, 28(5): 2107061-.
[2]	刘佩璇, 彭芦苇, 何瑞楠, 李露露, 乔锦丽. 一种用于电还原CO₂生成甲酸的高性能连续流动式MEA反应器[J]. 电化学（中英文）, 2022, 28(1): 2104231-.
[3]	郭浩, 钮东方, 胡硕真, 张新胜. 对-（β-羟乙基砜）苯胺的电化学合成[J]. 电化学（中英文）, 2021, 27(5): 498-507.
[4]	张钰宁, 钮东方, 胡硕真, 张新胜. 基于纳米金属的增强效应在CO₂电还原反应中的应用进展[J]. 电化学（中英文）, 2020, 26(4): 495-509.
[5]	李二岭, 杨发, 阮明波, 宋平, 徐维林. Fe-N共掺杂纳米碳材料的形貌对电化学还原反应的影响[J]. 电化学（中英文）, 2019, 25(4): 486-496.
[6]	高敦峰，阎程程，汪国雄，包信和. Pd/C催化剂用于CO₂电化学还原生成CO:Pd载量的影响[J]. 电化学（中英文）, 2018, 24(6): 757-765.
[7]	张瑞，吕伟欣，雷立旭. H型电解池中CO₂电化学还原的阳极电解液问题[J]. 电化学（中英文）, 2017, 23(1): 72-79.
[8]	赵波, 姜莉, 袁铭辉, 符显珠, 孙蓉, 汪正平. 电化学法制备石墨烯及其复合材料[J]. 电化学（中英文）, 2016, 22(1): 1-19.
[9]	杨瑞枝, Peter Strasser, Michael Toney. 电化学去合金化Pt(Pd)-Cu对氧的电催化还原活性的研究[J]. 电化学（中英文）, 2012, 18(2): 141-146.
[10]	赵晨辰, 郭建伟, 王莉, 何向明, 王诚, 刘志祥. Sn/Cu电极电化学还原CO2的研究[J]. 电化学（中英文）, 2012, 18(2): 169-173.
[11]	赖宇坤, 王炜, . 循环伏安法测定铁胺络合物还原强度[J]. 电化学（中英文）, 2011, 17(1): 102-106.
[12]	樊俊丽, 叶伟林, 王荣, 徐立群, 吴霞琴, . 不同离子液体中硝基苯的电化学还原[J]. 电化学（中英文）, 2009, 15(3): 260-263.
[13]	王胜, 雷瑛, 时康, . 电化学诱导聚合甲基丙烯酸膜及葡萄糖酶电极制备[J]. 电化学（中英文）, 2009, 15(3): 255-259.
[14]	林娟, 赵炜, . 煤及其含氧基团模拟物的电化学还原[J]. 电化学（中英文）, 2007, 13(2): 177-182.
[15]	邱国红;汪的华;金先波;胡晓宏;陈政;. Cr_2O_3粉末在CaCl_2熔盐中直接电化学还原的金属通腔电极研究[J]. 电化学（中英文）, 2006, 12(3): 304-309.