基于可控参数的前馈神经网络出水总氮预测模型研究
赵子豪 , 王子昊 , 袁家洛 , 马骏 , 何哲灵 , 徐一兰 , 沈晓佳 , 朱亮
工程(英文) ›› 2021, Vol. 7 ›› Issue (2) : 195 -202.
基于可控参数的前馈神经网络出水总氮预测模型研究
Development of a Novel Feedforward Neural Network Model Based on Controllable Parameters for Predicting Effluent Total Nitrogen
当前,出水总氮(TN)稳定达标是我国城镇污水处理厂面临的关键问题。本文基于我国城镇污水处理厂主流工艺——序批式活性污泥工艺(SBR),构建了一种基于可控参数的前馈神经网络(FFNN)出水总氮预测模型。与已有预测模型相比,本模型具备以下两个特点:①采用可控参数(表面气速与缺氧段时长)代替溶解氧作为模型主要输入参数,明显提高模型可用可控性;②采用算法优化的前馈神经网络构建模型,显著提高模型预测精准度。研究结果表明:量化共轭梯度法优化的FFNN模型预测精准,其拟合相关系数(R)明显高于其他相关模型;优化后的FFNN模型可根据进水与关键控制参数实现出水TN精准预测,有望实现城镇污水处理厂总氮稳定去除、系统节能降耗,助力国家'3060'碳目标实现。
The problem of effluent total nitrogen (TN) at most of the wastewater treatment plants (WWTPs) in China is important for meeting the related water quality standards, even under the condition of high energy consumption. To achieve better prediction and control of effluent TN concentration, an efficient prediction model, based on controllable operation parameters, was constructed in a sequencing batch reactor process. Compared with previous models, this model has two main characteristics: ① Superficial gas velocity and anoxic time are controllable operation parameters and are selected as the main input parameters instead of dissolved oxygen to improve the model controllability, and ② the model prediction accuracy is improved on the basis of a feedforward neural network (FFNN) with algorithm optimization. The results demonstrated that the FFNN model was efficiently optimized by scaled conjugate gradient, and the performance was excellent compared with other models in terms of the correlation coefficient (R). The optimized FFNN model could provide an accurate prediction of effluent TN based on influent water parameters and key control parameters. This study revealed the possible application of the optimized FFNN model for the efficient removal of pollutants and lower energy consumption at most of the WWTPs.
前馈神经网络(FFNN) / 算法 / 可控参数 / 序批式活性污泥工艺 / 总氮
Feedforward neural network (FFNN) / Algorithms / Controllable operation parameters / Sequencing batch reactor (SBR) / Total nitrogen (TN)
| [1] |
National Bureau of Statistics of China. China statistical yearbook 2019. Beijing: China Statistics Press; 2019. Chinese. |
| [2] |
Lu J, Wang X, Liu H, Yu H, Li W. Optimizing operation of municipal wastewater treatment plants in China: the remaining barriers and future implications. Environ Int 2019;129:273–8. |
| [3] |
Irvine RL, Ketchum LH Jr, Asano T. Sequencing batch reactors for biological wastewater treatment. Crit Rev Environ Control 1989;18(4):255–94. |
| [4] |
Vieira M, Brito AG, Nogueira R. Nitrogen removal in a sequencing batch biofilm reactor: effect of carbon availability and intermittent aeration. World Rev Sci Techonol Sustainable Dev 2009;6(2–4):173. |
| [5] |
Ren Y, Ngo HH, Guo W, Wang D, Peng L, Ni BJ, et al. New perspectives on microbial communities and biological nitrogen removal processes in wastewater treatment systems. Bioresour Technol 2020;297:122491. |
| [6] |
Hu L, Wang J, Wen X, Qian Y. Study on performance characteristics of SBR under limited dissolved oxygen. Process Biochem 2005;40(1):293–6. |
| [7] |
Boon AG. Sequencing batch reactors: a review. Water Environ J 2003;17 (2):68–73. |
| [8] |
Singh M, Srivastava RK. Sequencing batch reactor technology for biological wastewater treatment: a review. Asia-Pac J Chem Eng 2011;6(1):3–13. |
| [9] |
Ingimundarson A, Ocampo-Martinez C, Bemporad A. Suboptimal model predictive control of hybrid systems based on mode-switching constraints. In: Proceedings of the 2007 46th IEEE Conference on Decision and Control; 2007 Dec 12–14; New Orleans, LA, USA. New York: IEEE; 2008. |
| [10] |
Olsson G, Newell B. Wastewater treatment systems: modelling, diagnosis and control. London: IWA Publishing; 2015. |
| [11] |
Baxter CW, Zhang Q, Stanley SJ, Shariff R, Tupas R-RT, Stark HL. Drinking water quality and treatment: the use of artificial neural networks. Can J Civ Eng 2001;28(S1):26–35. |
| [12] |
Miron M, Frangu L, Ifrim G, Garaman S. Modeling of a wastewater treatment process using neural networks. In: Proceedings of the 2016 20th International Conference on System Theory, Control and Computing; 2016 Oct 13–15; Sinaia, Romania. New York: IEEE; 2016. |
| [13] |
Fan M, Li T, Hu J, Cao R, Wu Q, Wei X, et al. Synthesis and characterization of reduced graphene oxide-supported nanoscale zero-valent iron (nZVI/rGO) composites used for Pb(II) removal. Materials 2016;9(8):687. |
| [14] |
Dreyfus G. Neural networks: an overview. In: Dreyfus G, editor. Neural networks—methodology and applications. Heidelberg: Springer; 2005. p. 1–83. |
| [15] |
Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw 1989;2(5):359–66. |
| [16] |
Ata R. Artificial neural networks applications in wind energy systems: a review. Renew Sustain Energy Rev 2018;84:173. Retraction of: Ata R. Renew Sustain Energy Rev 2015;49:534–62. |
| [17] |
Almási A, Woz´niak S, Cristea V, Leblebici Y, Engbersen T. Review of advances in neural networks: neural design technology stack. Neurocomputing 2016;174 (Pt A):31–41. |
| [18] |
Lin D, Vasilakos AV, Tang Y, Yao Y. Neural networks for computer-aided diagnosis in medicine: a review. Neurocomputing 2016;216:700–8. |
| [19] |
Lesnik KL, Liu H. Predicting microbial fuel cell biofilm communities and bioreactor performance using artificial neural networks. Environ Sci Technol 2017;51(18):10881–92. |
| [20] |
Silver D, Schrittwieser J, Simonyan K, Antonoglou I, Huang A, Guez A, et al. Mastering the game of Go without human knowledge. Nature 2017;550 (7676):354–9. |
| [21] |
Qian N. On the momentum term in gradient descent learning algorithms. Neural Netw 1999;12(1):145–51. |
| [22] |
Sadrzadeh M, Mohammadi T, Ivakpour J, Kasiri N. Neural network modeling of Pb2+ removal from wastewater using electrodialysis. Chem Eng Process 2009;48(8):1371–81. |
| [23] |
Association APH. Standard methods for the examination of water and wastewater. 21st ed. Washington, DC: American Public Health Association; 2005. |
| [24] |
Ojha VK, Abraham A, Snášel V. Metaheuristic design of feedforward neural networks: a review of two decades of research. Eng Appl Artif Intel 2017;60:97–116. |
| [25] |
Anzai Y. Learning by neural networks. In: Anzai Y, editor. Pattern recognition & machine learning. San Francisco: Morgan Kaufmann; 1992. p. 297–335. |
| [26] |
Zhang S, Choromanska A, LeCun Y. Deep learning with elastic averaging SGD. 2014. arXiv:1412.6651. |
| [27] |
MacKay DJC. A practical bayesian framework for backpropagation networks. Neural Comput 1992;4(3):448–72. |
| [28] |
Foresee F, Hagan M. Gauss–Newton approximation to Bayesian regularization. In: Proceedings of International-joint Conference on Neural Networks; 1997 Jun 9–12; Houston, TX, USA; New York: IEEE; 1997. |
| [29] |
Moller MF. A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 1993;6(4):525–33. |
| [30] |
Kundu P, Debsarkar A,Mukherjee S. Artificial neural networkmodeling for biological removal of organic carbon and nitrogen from slaughterhouse wastewater in a sequencing batch reactor. Adv Artif Neural Syst 2013;2013:268064. |
| [31] |
Gong H, Pishgar R, Tay JH. Artificial neural network modelling for organic and total nitrogen removal of aerobic granulation under steady-state condition. Environ Technol 2019;40(24):3124–39. |
| [32] |
Ebrahimi M, Gerber EL, Rockaway TD. Temporal performance assessment of wastewater treatment plants by using multivariate statistical analysis. J Environ Manage 2017;193:234–46. |
| [33] |
Brdjanovic D, Slamet A, van Loosdrecht MCM, Hooijmans CM, Alaerts GJ, Heijnen JJ. Impact of excessive aeration on biological phosphorus removal from wastewater. Water Res 1998;32(1):200–8. |
()
/
| 〈 |
|
〉 |