膜科学与技术

人工神经网络及智能算法在膜污染研究中的应用

作者：张冰¹，唐和礼¹，黄冬梅¹，申渝¹²，时文歆³

单位： 1 重庆工商大学国家智能制造服务国际科技合作基地，环境与资源学院，重庆 400067；2 重庆南向泰斯环保技术研究院，重庆 400060；3 重庆大学环境与生态学院，重庆 400044

关键词：膜分离技术；膜污染；人工神经网络；智能算法；模拟；预测；优化

出版年,卷(期):页码： 2021,41(4):160-169

摘要：

对膜通量、跨膜压差的变化趋势等膜污染特征的准确预测，有利于实现膜分离过程中膜污染自动化控制及膜分离过程的长期稳定运行。人工神经网络（ANNs）和智能算法可以用来准确预测膜污染特征，是模拟膜分离过程及预测与优化膜污染控制条件的有力工具，可为膜污染控制提供重要的指导作用。本文首先系统地介绍了ANNs的概念、结构及实现过程；然后，综述了不同架构类型的ANNs在对于不同膜分离系统的模拟和在膜污染特征预测方面的应用，以及智能算法在ANNs性能优化方面的应用；最后，讨论了ANNs和智能算法在膜分离过程中运行条件优化方面的指导作用，对今后的研究方向进行了展望，以期对后续膜分离过程调控研究提供帮助。

The accurate predictions of characteristics related to membrane fouling (such as the variation tendency of filtration flux and transmembrane pressure) are beneficial for automatical control of membrane fouling and stable operation of membrane separation system. Artificial neural networks (ANNs) and intelligent algorithms are powerful tools in forecasting and optimizing the membrane fouling behaviors attributing to accurately modeling the process of membrane separation. Therefore, ANNs and intelligent algorithms can provide important guidance for the control of membrane fouling. In this study, firstly, the conception and architecture of ANNs were systematically introduced. Secondly, the applications of various architectural types of ANNs in simulating the process of membrane separation and forecasting the characteristics related to membrane fouling were reviewed, moreover, the applications of intelligent algorithm in optimizing the performance of ANNs were also addressed. Finally, the guiding functions of ANNs and intelligent algorithm in optimizing operation conditions of membrane separation process were carefully discussed, and the prospects of future research directions were put forward in order to provide assistance for future research.

张冰（1987–），男，黑龙江哈尔滨人，助理研究员，博士，研究方向：膜法废水处理技术

参考文献：

[1] 黄冬梅, 张冰, 唐和礼, 等. 好氧颗粒污泥膜生物反应器的研究进展[J]. 膜科学与技术, 2020, 40(4): 132-140.
[2] Meng F G, Zhang S Q, Oh Y, et al. Fouling in membrane bioreactors: An updated review[J]. Water Research, 2017, 114: 151-180.
[3] Meng F G, Chae S R, Drews A, et al. Recent advances in membrane bioreactors(MBRs): membrane fouling and membrane material[J]. Water Research, 2009, 43(6): 1489-1512.
[4] 唐和礼, 张冰, 黄冬梅, 等. XDLVO理论在膜污染解析中的应用研究[J]. 化工学报, 2020, https://kns.cnki.net/kcms/detail/11.1946.TQ.20201013.1636.010.html.
[5] 韩永萍, 肖燕, 宋蕾, 等. MBR膜污染的形成及其影响因素研究进展[J]. 膜科学与技术, 2013, 33(01): 102-110.
[6] Bagheri M, Mirbagheri S A. Critical review of fouling mitigation strategies in membrane bioreactors treating water and wastewater[J]. Bioresource Technology, 2018, 258: 318-334.
[7] Wu M F, Chen Y F, Lin H J, et al. Membrane fouling caused by biological foams in a submerged membrane bioreactor: Mechanism insights[J]. Water Research, 2020, 181: 115932.
[8] Zhang B, Tang H L, Huang D M, et al. Effect of pH on anionic polyacrylamide adhesion: New insights into membrane fouling based on XDLVO analysis[J]. Journal of Molecular Liquids, 2020, 320: 114463.
[9] Chen Y F, Teng J H, Shen L G, et al. Novel insights into membrane fouling caused by gel layer in a membrane bioreactor: Effects of hydrogen bonding[J]. Bioresource Technology, 2019, 276: 219-225.
[10] Chen Y F, Teng J H, Liao B Q, et al. Molecular insights into the impacts of iron(III) ions on membrane fouling by alginate[J]. Chemosphere, 2020, 242: 125232.
[11] Zhang B, Zhang R J, Huang D M, et al. Membrane fouling in microfiltration of alkali/surfactant/polymer flooding oilfield wastewater: Effect of interactions of key foulants[J]. Journal of Colloid and Interface Science, 2020, 570: 20-30.
[12] Zhang B, Huang D M, Shen Y, et al. Treatment of municipal wastewater with aerobic granular sludge membrane bioreactor(AGMBR): Performance and membrane fouling[J]. Journal of Cleaner Production, 2020, 273: 123124.
[13] 马琳, 秦国彤. 膜污染的机理和数学模型研究进展[J]. 水处理技术, 2007, 33(06): 1-4+17.
[14] 崔彦杰, 刘美, 王湛, 等. 超滤通量模型的研究进展[J]. 膜科学与技术, 2008, 28(6): 93-98.
[15] 穆思图, 樊慧菊, 韩秉均, 等. 中空纤维膜的膜污染过程及数学模型研究进展[J]. 膜科学与技术, 2018, 38(01): 114-121.
[16] 刘志峰, 潘丹, 王建华, 等. PSO-BP神经网络在MBR工艺中的膜污染预测[J]. 北京工业大学学报, 2012, 38(1): 126-131.
[17] 熊日华, 王世昌. 神经网络在膜技术中的应用[J]. 膜科学与技术, 2003, 23(6): 44-48.
[18] Khayet M, Cojocaru C, Essalhi M. Artificial neural network modeling and response surface methodology of desalination by reverse osmosis[J]. Journal of Membrane Science, 2011, 368(1-2): 202-214.
[19] Libotean D, Giralt J, Giralt F, et al. Neural network approach for modeling the performance of reverse osmosis membrane desalting[J]. Journal of Membrane Science, 2009, 326(2): 408-419.
[20] Purkait M K, Kumar V D, Maity D. Treatment of leather plant effluent using NF followed by RO and permeate flux prediction using artificial neural network[J]. Chemical Engineering Journal, 2009, 151(1-3): 275-285.
[21] Jawad J, Hawari A H, Zaidi S. Modeling of forward osmosis process using artificial neural networks(ANN) to predict the permeate flux[J]. Desalination, 2020, 484: 114427.
[22] Alver A, Kazan Z. Prediction of full-scale filtration plant performance using artificial neural networks based on principal component analysis[J]. Separation and Purification Technology, 2020, 230: 115868.
[23] 石耀科. 膜法水处理系统模拟及膜污染预测研究[D]. 兰州: 兰州理工大学, 2020.
[24] Fan M, Hu J, Cao R, et al. A review on experimental design for pollutants removal in water treatment with the aid of artificial intelligence[J]. Chemosphere, 2018, 200: 330-343.
[25] 窦鹏伟, 王珍, 佘侃侃, 等. 基于改进BP神经网络的中药水提液陶瓷膜污染预测研究[J]. 中医药信息学, 2017, 24(4): 92-96.
[26] Badrnezhad R, Mirza B. Modeling and optimization of cross-flow ultrafiltration using hybrid neural network-genetic algorithm approach[J]. Journal of Industrial and Engineering Chemistry, 2014, 20(2): 528-543.
[27] Soleimani R, Shoushtari N A, Mirza B, et al. Experimental investigation, modeling and optimization of membrane separation using artificial neural network and multi-objective optimization using genetic algorithm[J]. Chemical Engineering Research and Design, 2013, 91(5): 883-903.
[28] 王雨墨, 李彦博, 李晓平, 等. 人工神经网络预测管道冲蚀速率研究进展[J]. 石油科学通报, 2020, 5(1): 114-121.
[29] Schmitt F, Banu R, Yeom I-T, et al. Development of artificial neural networks to predict membrane fouling in an anoxic-aerobic membrane bioreactor treating domestic wastewater[J]. Biochemical Engineering Journal, 2018, 133: 47-58.
[30] 蒋卓. 基于径向基神经网络对碟管式反渗透膜通量的预测[D]. 成都: 西南交通大学, 2018.
[31] Bagheri M, Akbari A, Mirbagheri S A. Advanced control of membrane fouling in filtration systems using artificial intelligence and machine learning techniques: A critical review[J]. Process Safety and Environmental Protection, 2019, 123: 229-252.
[32] 阳虎. 基于神经网络的纳滤膜通量预测[D]. 大连: 大连交通大学, 2012.
[33] Dornier M, Decloux M, Trystram G, et al. Dynamic modeling of crossflow microfiltration using neural networks[J]. Journal of Membrane Science, 1995, 98(3): 263-273.
[34] 石宝强, 张捍民, 杨凤林, 等. 人工神经网络在膜生物反应器膜污染预测中的应用前景[J]. 工业水处理, 2006, 26(12): 14-17.
[35] Aydiner C, Demir I, Yildiz E. Modeling of flux decline in crossflow microfiltration using neural networks: the case of phosphate removal[J]. Journal of Membrane Science, 2005, 248(1-2): 53-62.
[36] Chew C M, Aroua M K, Hussain M A. A practical hybrid modelling approach for the prediction of potential fouling parameters in ultrafiltration membrane water treatment plant[J]. Journal of Industrial and Engineering Chemistry, 2017, 45: 145-155.
[37] Gao K, Xi X, Wang Z, et al. Use of support vector machine model to predict membrane permeate flux[J]. Desalination and Water Treatment, 2015, 34(18): 1-12.
[38] Cai G S, Li C Q. Application of Improved Wavelet Neural Network in MBR Flux Prediction [C]. //IEEE/ACIS International Conference on Computer & Information Science. IEEE, 2017: 359-363.
[39] Aidan A, Abdel-Jabbar N, Ibrahim T H, et al. Neural network modeling and optimization of scheduling backwash for membrane bioreactor[J]. Clean Technologies and Environmental Policy, 2008, 10(4): 389-395
[40] 王旭辉. BP神经网络在超滤膜通量预测中的应用研究[D]. 北京: 北京交通大学, 2006.
[41] Bowen W R, Jones M G, Yousef H N S. Prediction of the rate of crossflow membrane ultrafiltration of colloids: A neural network approach[J]. Chemical Engineering Science, 1998, 53(22): 3793-3802.
[42] Hosseinzadeh A, Zhou J L, Altaee A, et al. Modeling water flux in osmotic membrane bioreactor by adaptive network-based fuzzy inference system and artificial neural network[J]. Bioresource Technology, 2020, 310: 123391
[43] Teodosiu C, Pastravanu O, Macoveanu M. Neural network models for ultrafiltration and backwashing[J]. Water Research, 2000, 34(18): 4371-4380.
[44] Chen H, Kim A S. Prediction of permeate flux decline in crossflow membrane filtration of colloidal suspension: a radial basis function neural network approach[J]. Desalination, 2006, 192(1-3): 415-428.
[45] Salehi F, Razavi S M A. Dynamic modeling of flux and total hydraulic resistance in nanofiltration treatment of regeneration waste brine using artificial neural networks[J]. Desalination and Water Treatment, 2012, 41(1-3): 95-104.
[46] Niemi H, Bulsari A, Palosaari S. Simulation of membrane separation by neural networks [J]. Journal of Membrane Science, 1995, 102: 185-191.
[47] Delgrange N, Cabassud C, Cabassud M, et al. Neural networks for prediction of ultrafiltration transmembrane pressure–application to drinking water production[J]. Journal of Membrane Science, 1998, 150: 111-123.
[48] Liu Q F, Kim S H, Lee S. Prediction of microfiltration membrane fouling using artificial neural network models[J]. Separation and Purification Technology, 2009, 70(1): 96-102.
[49] Hazrati H, Moghaddam A H, Rostamizadeh M. The influence of hydraulic retention time on cake layer specifications in the membrane bioreactor: Experimental and artificial neural network modeling[J]. Journal of Environmental Chemical Engineering, 2017, 5(3): 3005-3013.
[50] Razavi S M A, Mousavi S M, Mortazavi S A. Dynamic prediction of milk ultrafiltration performance: A neural network approach[J]. Chemical Engineering Science, 2003, 58(18): 4185-4195
[51]. Razavi M A, Mortazavi A, Mousavi M. Application of neural networks for crossflow milk ultrafiltration simulation[J]. International Dairy Journal, 2004, 14(1): 69-80.
[52] Barello M, Manca D, Patel R, et al. Neural network based correlation for estimating water permeability constant in RO desalination process under fouling[J]. Desalination, 2014, 345: 101-111.
[53] Aminian A. Prediction of temperature elevation for seawater in multi-stage flash desalination plants using radial basis function neural network[J]. Chemical Engineering Journal, 2010, 162(2): 552-556.
[54] Zhu M, El-Halwagi M M, Al-Ahmad M. Optimal design and scheduling of flexible reverse osmosis networks[J]. Journal of Membrane Science, 1997, 129(2): 161-174.
[55] 王改革. 基于智能算法的目标威胁估计[D]. 长春: 中国科学院大学, 2013.
[56] 梁楷. 基于模拟退火算法的支持向量机在MBR膜污染中的应用研究[D]. 天津: 天津工业大学, 2017.
[57] 张鹏程. 基于改进遗传算法的冷链物流路径优化硏究[D]. 淮南: 安徽理工大学, 2016.
[58] 严露. 粒子群算法研究与应用[D]. 成都: 电子科技大学, 2013.
[59] 高超. 基于局部搜索改进的蝙蝠算法及应用研究[D]. 北京: 北京建筑大学, 2020.
[60] 陶颖新. PSO_RBF及CFD在MBR中的应用研究[D]. 天津: 天津工业大学, 2019.
[61] 闫宏英, 李春青. MBR膜污染的智能模拟预测方法研究[J]. 计算机测量与控制, 2013, 08(08): 2177-2190.
[62] 胡文博, 李春青, 任淑霞. Adaboost_BP在MBR膜污染中的应用研究[J]. 软件, 2016, 37(12): 21-25.
[63] Sahoo G B, Ray C. Predicting flux decline in crossflow membranes using artificial neural networks and genetic algorithms[J]. Journal of Membrane Science, 2006, 283(1-2): 147-157.
[64] Mirbagheri S A, Bagheri M, Bagheri Z, et al. Evaluation and prediction of membrane fouling in a submerged membrane bioreactor with simultaneous upward and downward aeration using artificial neural network-genetic algorithm[J]. Process Safety and Environmental Protection, 2015, 96: 111-124.
[65] 汤佳. RBF神经网络在MBR膜污染仿真预测中的应用研究[D]. 天津: 天津工业大学, 2017.
[66] 聂敬云, 李春青, 李威威, 等. 关于遗传算法优化的最小二乘支持向量机在MBR仿真预测中的研究[J]. 软件, 2015, 36(5): 40-44.
[67] 铁晓波. 大数据平台下基于人工免疫系统的MBR膜污染研究[D]. 天津: 天津工业大学, 2017.
[68] 李威威. 基于Hadoop的MBR膜污染数据的分析与仿真预测研究[D]. 天津: 天津工业大学, 2016.
[69] 王辛畅. PSO_GA_Elman及CFD在MBR模拟仿真中的应用研究[D]. 天津: 天津工业大学, 2019.
[70] 杨帆, 周敏, 金继民, 等. 智能优化算法及人工神经网络在催化裂化模型分析中的应用进展[J]. 石油学报(石油加工), 2020, 36(04): 878-888.
[71] Zhao B, Chen H, Gao D, et al. Cleaning decision model of MBR membrane based on Bandelet neural network optimized by improved Bat algorithm[J]. Applied Soft Computing, 2020, 91: 106211.
[72] Pardeshi P M, Mungray A A, Mungray A K. Determination of optimum conditions in forward osmosis using a combined Taguchi–neural approach[J]. Chemical Engineering Research and Design, 2016, 109: 215-225.
[73] Salahi A, Abbasi M, Mohammadi T. Permeate flux decline during UF of oily wastewater: Experimental and modeling[J]. Desalination, 2010, 251(1-3): 153-160.
[74] Abbasi M, Mirfendereski M, Nikbakht M, et al. Performance study of mullite and mullite–alumina ceramic MF membranes for oily wastewaters treatment[J]. Desalination, 2010, 259(1-3): 169-178.
[75] Salahi A, Badrnezhad R, Abbasi M, et al. Oily wastewater treatment using a hybrid UF/RO system [J]. Desalination and Water Treatment, 2011, 28(1-3): 75-82.

服务与反馈：

【文章下载】【加入收藏】

《膜科学与技术》编辑部地址：北京市朝阳区北三环东路19号蓝星大厦邮政编码：100029 电话：010-64426130/64433466 传真：010-80485372邮箱：mkxyjs@163.com