[1]张学阳,项雷军,林文辉,等.神经网络预测控制在污水处理溶解氧控制中的应用[J].华侨大学学报(自然科学版),2015,36(3):280-285.[doi:10.11830/ISSN.1000-5013.2015.03.0280]
　ZHANG Xue-yang,XIANG Lei-jun,LIN Wen-hui,et al.Application of Neural Network Predictive Control to Dissolved Oxygen Control in Sewage Treatment Process[J].Journal of Huaqiao University(Natural Science),2015,36(3):280-285.[doi:10.11830/ISSN.1000-5013.2015.03.0280]
点击复制

神经网络预测控制在污水处理溶解氧控制中的应用()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第36卷
期数:
2015年第3期
页码:
280-285
栏目:
出版日期:
2015-05-20

文章信息/Info

Title:
Application of Neural Network Predictive Control to Dissolved Oxygen Control in Sewage Treatment Process
文章编号:
1000-5013(2015)03-0280-06
作者:
张学阳1;  项雷军1;  林文辉2;  郭新华1
1. 华侨大学 信息科学与工程学院, 福建 厦门 361021;2. 泉州市益源环保设备有限公司, 福建 泉州 362021
Author(s):
ZHANG Xue-yang1;  XIANG Lei-jun1;  LIN Wen-hui2;  GUO Xin-hua1
1. College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China; 2. Quanzhou Yiyuan Environmental Protection Equipment Company Limited, Quanzhou 362021, China
关键词:
污水处理;  神经网络;  溶解氧浓度;  预测控制;  过程控制
Keywords:
sewage treatment;  neural network;  dissolved oxygen concentration;  predictive control;  process control
分类号:
TP273
DOI:
10.11830/ISSN.1000-5013.2015.03.0280
文献标志码:
A
摘要:
针对污水处理过程溶解氧浓度时变设定值难以控制的问题,提出一种溶解氧浓度的神经网络预测控制器设计方法.首先,在活性污泥法污水处理过程通用机理模型基础上,利用系统的输入、输出数据,采用递推学习更新模式,通过三层BP神经网络训练出系统神经网络逼近模型.然后,设计满足出水水质指标的溶解氧约束预测控制器.在考虑溶解氧测量白噪音干扰和进水流量发生阶跃变化情况下,将所设计的控制器用于污水处理溶解氧浓度的时变设定值跟踪控制.仿真结果表明:与传统PID控制器相比,神经网络预测控制器能够显著提高溶解氧跟踪控制性能,具有更好的自适应性和抗干扰能力.
Abstract:
In order to solve the difficult problem of controlling the dissolved oxygen(DO)concentration with time varying setpoint in sewage treatment process, a neural network predictive controller(NNPC)design method for the dissolved oxygen concentration is proposed in this paper. Firstly, based on the general mechanism model of the activated sludge sewage treatment process, by using the input and output data of the system and the recursive learning update mode, the neural network approximation model of the system is trained through three-layer BP neural network. Then the constrained predictive controller of dissolved oxygen is designed in the condition of satisfying effluent water quality indicators. Considering the white noise interference on the dissolved oxygen measurement and the step changing influent flow, the designed controller is applied to the time varying setpoint tracking control of dissolved oxygen concentration in sewage treatment process. Simulation results show that compared to the conventional PID controller, the neural network predictive controller can significantly improve the tracking control performance of dissolved oxygen concentration and has better adaptability and stronger disturbance rejection ability.

参考文献/References:

[1] HENZE M.Activated sludge models ASM1, ASM2, ASM2d and ASM3 [M].London:IWA Publishing,2000:13-15.
[2] KATEBI M R,JOHNSON M A,WILKE J.Control and instrumentation for wastewater treatment plant [M].London:Springer-Verlag,1999:38-41.
[3] NEJJARI F,BENHAMMOU A,DAHHOU B,et al.Non-linear multivariable adaptive control of an activated sludge wastewater treatment process[J].Int J Adapt Control Signal Process,1999,13(5):347-365.
[4] 张平,苑明哲,王宏.基于国际评价基准的溶解氧控制方法研究[J].信息与控制,2007,36(2):199-203.
[5] TZONEVA R.Optimal PID control of the dissolved oxygen concentration in the wastewater treatment plant[C]//IEEE AFRICON Conference.Windhoek:IEEE Press,2007:1-7.
[6] CHEN J C,CHANG Ni-bin.Mining the fuzzy control rules of aeration in a submerged biofilm wastewater treatment process[J].Engineering Applications of Artificial Intelligence,2007,20(7):959-969.
[7] 甄博然,韩红桂,乔俊飞.基于增长型神经网络的污水处理过程溶解氧控制[J].中南大学学报:自然科学版,2009,40(1):74-79.
[8] 王小艺,李万东,刘载文,等.一种模糊PID-Smith污水处理的控制方法[J].计算机与应用化学,2010,27(6):801-803.
[9] 付文韬,武利,王莉莉,等.神经网络PID的溶解氧控制系统[J].计算机与应用化学,2013,30(10):1135-1138.
[10] 胡玉玲,曹建国,乔俊飞.活性污泥污水处理系统的模糊神经网络控制[J].系统仿真学报,2005,17(10):2541-2544.
[11] SHEN Wen-hao,CHEN Xiao-quan,PONS M N,et al.Model predictive control for wastewater treatment process with feedforward compensation[J].Chemical Engineering Journal,2009,155(1/2):161-174.
[12] CRISTEA S,DEPRADA C,SARABIA D,et al.Aeration control of a wastewater treatment plant using hybrid NMPC[J].Computers and Chemical Engineering,2010,35(4):638-650.
[13] 刘载文,张春芝,王小艺,等.基于遗传算法的污水处理过程优化控制方法[J].计算机与应用化学,2007,24(7):959-962.
[14] HOLENDA B,DOMOKOS E,REDEY A,et al.Aeration optimization of a wastewater treatment plant using genetic algorithm[J].Optimal Control Applications and Methods,2007,28(3):191-208.
[15] 孙增圻,张再兴,邓志东.智能控制理论与技术[M].2版.北京:清华大学出版社,2011:123-126.
[16] CAMACHO E F,BORDONS C.Model predictive control.advanced textbooks in control and signal processing[M].2nd.London:Springer-Verlag,2004:3-9.

相似文献/References:

[1]刘甲耀,严桂兰,刘波.人工神经系统的研制与进展[J].华侨大学学报(自然科学版),1993,14(2):248.[doi:10.11830/ISSN.1000-5013.1993.02.0248]
　Liu Jiayao,Yan Guilan,Liu Bo.Research and Development of Artificial Neural System[J].Journal of Huaqiao University(Natural Science),1993,14(3):248.[doi:10.11830/ISSN.1000-5013.1993.02.0248]
[2]范慧琳.机器学习的若干方法分析[J].华侨大学学报(自然科学版),1995,16(1):116.[doi:10.11830/ISSN.1000-5013.1995.01.0116]
　Fan Huilin.An Analysis of Several Methods of Machine Learning[J].Journal of Huaqiao University(Natural Science),1995,16(3):116.[doi:10.11830/ISSN.1000-5013.1995.01.0116]
[3]韦鹏生.用结构可控神经网络作结构分析[J].华侨大学学报(自然科学版),1998,19(3):275.[doi:10.11830/ISSN.1000-5013.1998.03.0275]
　Wei Pengsheng.Structural Analysis by Using Structural Controllable Neural Network[J].Journal of Huaqiao University(Natural Science),1998,19(3):275.[doi:10.11830/ISSN.1000-5013.1998.03.0275]
[4]李旭明,康赐荣.基于遗传算法的最优模糊控制器设计[J].华侨大学学报(自然科学版),1999,20(1):95.[doi:10.11830/ISSN.1000-5013.1999.01.0095]
　Li Xuming,Kang Cirong.Design of Optimized Fuzzy Controller Based on Genetic Algorithm[J].Journal of Huaqiao University(Natural Science),1999,20(3):95.[doi:10.11830/ISSN.1000-5013.1999.01.0095]
[5]方千山,王永初.立窑水泥煅烧过程的控制策略[J].华侨大学学报(自然科学版),2000,21(4):357.[doi:10.3969/j.issn.1000-5013.2000.04.006]
　Fang Qianshan,Wang Yongchu.A Study on Strategy of Controlling Cement Calcination in Shaft Kiln[J].Journal of Huaqiao University(Natural Science),2000,21(3):357.[doi:10.3969/j.issn.1000-5013.2000.04.006]
[6]张新红.非参数估计的小波网络经济预测模型[J].华侨大学学报(自然科学版),2003,24(1):105.[doi:10.3969/j.issn.1000-5013.2003.01.019]
　Zhang Xinhong.A Wavelet Network Model for Nonparametric Estimation and Economic Forecasting[J].Journal of Huaqiao University(Natural Science),2003,24(3):105.[doi:10.3969/j.issn.1000-5013.2003.01.019]
[7]方瑞明,郑力新,黄东海.高速异步电机转子闭口槽集肤效应预测[J].华侨大学学报(自然科学版),2004,25(1):26.[doi:10.3969/j.issn.1000-5013.2004.01.007]
　Fang Ruiming,Zheng Lixin,Huang Donghai.Predicting the Skin Effect on Closed Slot of Rotor in High-Speed Motor[J].Journal of Huaqiao University(Natural Science),2004,25(3):26.[doi:10.3969/j.issn.1000-5013.2004.01.007]
[8]冯远静,李良福,冯祖仁.粗糙集CMAC神经网络故障诊断策略[J].华侨大学学报(自然科学版),2004,25(3):318.[doi:10.3969/j.issn.1000-5013.2004.03.023]
　Feng Yuanjing,Li Liangfu,Feng Zuren.Rough Set-Based CMAC Neural Network for Fault Diagrosis[J].Journal of Huaqiao University(Natural Science),2004,25(3):318.[doi:10.3969/j.issn.1000-5013.2004.03.023]
[9]王启志.神经网络辨识的自适应逆控制[J].华侨大学学报(自然科学版),2005,26(4):397.[doi:10.3969/j.issn.1000-5013.2005.04.017]
　Wang Qizhi.Adaptive Inverse Control Based on Neural Network Identification[J].Journal of Huaqiao University(Natural Science),2005,26(3):397.[doi:10.3969/j.issn.1000-5013.2005.04.017]
[10]方瑞明.神经网络推理机制的电机调整设计专家系统[J].华侨大学学报(自然科学版),2006,27(2):201.[doi:10.3969/j.issn.1000-5013.2006.02.024]
　Fang Ruiming.The Expert System of the Motor Adaptation and Design Based on Neural Network Inference[J].Journal of Huaqiao University(Natural Science),2006,27(3):201.[doi:10.3969/j.issn.1000-5013.2006.02.024]

备注/Memo

备注/Memo:
收稿日期: 2014-04-25
通信作者: 项雷军(1979-),男,讲师,博士,主要从事复杂工业系统建模、控制与优化的研究.E-mail:ljxiang@hqu.edu.cn.
基金项目: 福建省自然科学基金资助项目(2013J01198); 福建省泉州市科技计划重点项目(2013Z32)
更新日期/Last Update: 2015-05-20