基于模糊神经网络的A/O废水处理控制系统的研究
|
摘要
随着工业的不断发展,工业废水的污染日益严重,治理污水的任务变得愈加繁重。造纸行业是污染我国环境的主要行业之一,解决造纸工业的水污染,成为了迫在眉睫的任务。而目前造纸废水的处理工艺主要采用“物化-生化”工艺处理,生化处理部分大多采用的是活性污泥法工艺处理的。由于活性污泥法处理造纸废水具有多变量、非线性、大滞后、不确定性和复杂性的特点,单纯人工的操作难以实现废水处理稳定性和良好的出水效果。传统的自动控制技术自身存在缺陷,建立的数学模型不够精确,控制效果不够理想,导致污水处理过程控制自动化水平相对落后。鉴于此,本论文致力于研究用模糊神经网络算法实现对废纸造纸废水生化处理系统曝气量的智能控制,得到以下成果:
根据废纸造纸废水的特征,确定了实验室条件下的造纸废水处理工艺,完成了MCGS组态软件的组态和PLC程序的设计,在此基础上建立了造纸废水处理的自动控制系统,并在此自动控制系统下进行试验,获取大量的样本数据。再根据对废纸造纸废水处理特征和模糊神经网络的分析,提出了智能预测和控制模型方案。利用获取的样本数据,采用Takagi-Sugeno推理的网络建立A/O生化池出水COD预测模型,结合模糊C均值聚类和混合算法完成网络的结构辨识和参数辨识,借助MATLAB软件对建立的预测模型进行仿真分析,仿真结果表明,预测模型具有很好的学习能力和泛化能力,训练数据的相对误差绝对值范围为0~0.0073%,测试数据的相对误差绝对值范围为0~10.4636%。
通过建立的Takagi-Sugeno预测模型与单纯的BP网络的预测模型进行性能比较,前者的训练数据和测试数据的平均绝对误差率MAPE分别为1.486×10-3 %、2.703%,而后者的训练数据和测试数据的平均绝对误差率MAPE分别为2.785%、11.53%。通过两者的性能对比可知,Takagi-Sugeno预测模型的平均绝对误差率MAPE远远小于单纯的BP网络的预测模型,说明了前者更适合用于预测生化池的出水COD值。
采用基于Mamdani规则的模糊神经网络建立曝气量控制模型,利用出水COD值的变化量和出水COD值的变化率作为控制模型的输入变量,曝气量的修正量作为控制模型输出,用于调节曝气量。结合混合算法完成网络的结构辨识和参数辨识,确定控制模型的具体参数。在MCGS高级开发包生成的VB程序中编写了模糊神经算法,按照MCGS的接口函数规范将算法嵌入到MCGS中,实现了对造纸废水处理系统的智能控制。在实验室条件下进行验证试验,将期待出水COD值设定在100mg/L,结果表明在不同进水负荷下,生化池出水COD值在91~109mg/L范围,基本维持在100mg/L左右,说明基于模糊神经网络算法的智能控制系统能够有效地实现造纸废水处理系统的智能控制。
本课题的研究成果为实现废纸造纸废水生化处理系统的自动控制提供了一种有效的解决方案,同时为污水处理过程实现优化控制提供了新的途径,具有一定的推广价值。
As the constant development of the industry, the pollution of industrial wastewater becomes more and more serious. Sewage treatment has become an arduous task. The papermaking industry is one of the major pollutive industries in China, so solving the pollution of papermaking wastewater has become an urgent task. At present the treatment method used in paper wastewater treatment are mainly physicochemical and biochemical technology, in which activated sludge process is mostly adopted. In the wastewater process there are many characteristics, such as multi-variables, nonlinearity, hysteresis, uncertainty and complexity, etc, all of which cause poor stability and bad effluent quality. However, the traditional control owing to its shorting, is difficult to build precise mathematical model,so the control effect is not satisfactory. Therefore, in this paper the fuzzy neural network intelligent control system for aeration in wastewater treatment system was presented. And several valuable conclusions were reached.
According to the characteristics of papemaking wastewater, the automatic control system based on Windows CE.NET OS and MCGS software of wastewater was constructed, and the design method and the hybrid intelligent structure were proposed with the consideration of Fuzzy neural network control. The predictive model of effluent COD value is based on the Takagi-Sugeno inferential network. In order to improve the network performance, fuzzy C-means clustering was used to identify model’s architecture and optimize fuzzy rule. The simulation indicated that the predictive model had good ability both in learning and generalization, with relative errors of training and test data are 0~0.0073% and 0~10.4636%, respectively.
Camparing the predictive modle based on Takagi-Sugeno with the predictive modle based on BP network in performance, when training, MAPE (Mean Absolute Percentage Error)between the predicted and observed values was1.486×10-3 % using Takagi-Sugeno model, and it was 2.703% when testing But MAPE of the training and testing usingBP modle were 2.785% and 11.53%, repectively. Mape using the Takagi-Sugeno predictive model was lower than that using ANN. Therefore, the Takagi-Sugeno modle is more suitable to predict the effluent COD value.
The control model was built up based on Mamdani network. The change and change rate of COD in effluent were considered as the input variables of control model, and correction of aeration was considered as the output variable, which was adopted for regulating aeration. Fuzzy neural network algorithm with MCGS development package using VB program was developed,and embeded it into MCGS according to MCGS interface function criterion, so that intelligent control system for papermaking wastewater treatmen was achived. And then The validation experiment was finally given in laboratory. The expectation COD value of effluent was setted to 100 mg/L. The results show that under different influent laod, the COD value of effluent was between 91 to 109 mg/L, remaining at about 100 mg/L. It proved that the intelligent control system based on fuzzy neural network was effective.
The reasearch can provide an effective way to achive autocontrol for wastewater biochemical treatment system from papermaking and can provide guidance for the further study of intelligent control in the field of wastewater treatment and the popularization of wastewater treatment project with intelligent control.
根据废纸造纸废水的特征,确定了实验室条件下的造纸废水处理工艺,完成了MCGS组态软件的组态和PLC程序的设计,在此基础上建立了造纸废水处理的自动控制系统,并在此自动控制系统下进行试验,获取大量的样本数据。再根据对废纸造纸废水处理特征和模糊神经网络的分析,提出了智能预测和控制模型方案。利用获取的样本数据,采用Takagi-Sugeno推理的网络建立A/O生化池出水COD预测模型,结合模糊C均值聚类和混合算法完成网络的结构辨识和参数辨识,借助MATLAB软件对建立的预测模型进行仿真分析,仿真结果表明,预测模型具有很好的学习能力和泛化能力,训练数据的相对误差绝对值范围为0~0.0073%,测试数据的相对误差绝对值范围为0~10.4636%。
通过建立的Takagi-Sugeno预测模型与单纯的BP网络的预测模型进行性能比较,前者的训练数据和测试数据的平均绝对误差率MAPE分别为1.486×10-3 %、2.703%,而后者的训练数据和测试数据的平均绝对误差率MAPE分别为2.785%、11.53%。通过两者的性能对比可知,Takagi-Sugeno预测模型的平均绝对误差率MAPE远远小于单纯的BP网络的预测模型,说明了前者更适合用于预测生化池的出水COD值。
采用基于Mamdani规则的模糊神经网络建立曝气量控制模型,利用出水COD值的变化量和出水COD值的变化率作为控制模型的输入变量,曝气量的修正量作为控制模型输出,用于调节曝气量。结合混合算法完成网络的结构辨识和参数辨识,确定控制模型的具体参数。在MCGS高级开发包生成的VB程序中编写了模糊神经算法,按照MCGS的接口函数规范将算法嵌入到MCGS中,实现了对造纸废水处理系统的智能控制。在实验室条件下进行验证试验,将期待出水COD值设定在100mg/L,结果表明在不同进水负荷下,生化池出水COD值在91~109mg/L范围,基本维持在100mg/L左右,说明基于模糊神经网络算法的智能控制系统能够有效地实现造纸废水处理系统的智能控制。
本课题的研究成果为实现废纸造纸废水生化处理系统的自动控制提供了一种有效的解决方案,同时为污水处理过程实现优化控制提供了新的途径,具有一定的推广价值。
As the constant development of the industry, the pollution of industrial wastewater becomes more and more serious. Sewage treatment has become an arduous task. The papermaking industry is one of the major pollutive industries in China, so solving the pollution of papermaking wastewater has become an urgent task. At present the treatment method used in paper wastewater treatment are mainly physicochemical and biochemical technology, in which activated sludge process is mostly adopted. In the wastewater process there are many characteristics, such as multi-variables, nonlinearity, hysteresis, uncertainty and complexity, etc, all of which cause poor stability and bad effluent quality. However, the traditional control owing to its shorting, is difficult to build precise mathematical model,so the control effect is not satisfactory. Therefore, in this paper the fuzzy neural network intelligent control system for aeration in wastewater treatment system was presented. And several valuable conclusions were reached.
According to the characteristics of papemaking wastewater, the automatic control system based on Windows CE.NET OS and MCGS software of wastewater was constructed, and the design method and the hybrid intelligent structure were proposed with the consideration of Fuzzy neural network control. The predictive model of effluent COD value is based on the Takagi-Sugeno inferential network. In order to improve the network performance, fuzzy C-means clustering was used to identify model’s architecture and optimize fuzzy rule. The simulation indicated that the predictive model had good ability both in learning and generalization, with relative errors of training and test data are 0~0.0073% and 0~10.4636%, respectively.
Camparing the predictive modle based on Takagi-Sugeno with the predictive modle based on BP network in performance, when training, MAPE (Mean Absolute Percentage Error)between the predicted and observed values was1.486×10-3 % using Takagi-Sugeno model, and it was 2.703% when testing But MAPE of the training and testing usingBP modle were 2.785% and 11.53%, repectively. Mape using the Takagi-Sugeno predictive model was lower than that using ANN. Therefore, the Takagi-Sugeno modle is more suitable to predict the effluent COD value.
The control model was built up based on Mamdani network. The change and change rate of COD in effluent were considered as the input variables of control model, and correction of aeration was considered as the output variable, which was adopted for regulating aeration. Fuzzy neural network algorithm with MCGS development package using VB program was developed,and embeded it into MCGS according to MCGS interface function criterion, so that intelligent control system for papermaking wastewater treatmen was achived. And then The validation experiment was finally given in laboratory. The expectation COD value of effluent was setted to 100 mg/L. The results show that under different influent laod, the COD value of effluent was between 91 to 109 mg/L, remaining at about 100 mg/L. It proved that the intelligent control system based on fuzzy neural network was effective.
The reasearch can provide an effective way to achive autocontrol for wastewater biochemical treatment system from papermaking and can provide guidance for the further study of intelligent control in the field of wastewater treatment and the popularization of wastewater treatment project with intelligent control.
引文
[1]商敏儿,杜树新,吴铁军.活性污泥法污水处理过程自动控制的研究现状[J].环境污染治理与设备.2001,3(1):84-87
[2]王树青,元英进.生化过程自动化技术[M].化学工业出版社.2001.
[3]赵耘挚,刘振鸿.活性污泥的发展及在SBR工艺中的应用[J].上业水处理.2002,22(9):12-16.
[4] Olsson G, Aspegren H,Nielsen M K. Operation and control of wastewater treatment—a Scandinavian perspective over 20 years[J]. Water Science and Technology. 1998,37 (12): 1-13
[5] Ohto T. Control, computers and communications: Fusion in instrumentation, control and automation of water and wastewater system in Japan [J]. Water Science and Technology 1998, 37(12):15-19
[6] Garrett M T.Instrumentation,control and automation progress in the United States in the last 24 years [J].Water Science and Technology.1998, 37(12):21-25
[7] Huntingdo R. Twenty years developments of ICA in a water utility [J]. Water Science and Technology, 1998, 37(12):27-34
[8] Kabouris J C. Modeling.Instrumentation, automation and optimization of wastewater treatment facilities [J]. Water Environment Research, 1999, 71(5):729-736
[9]刘华.基于神经网络和模糊PID控制的嵌入式造纸废水处理系统的研究[D].华南理工大学硕士学位论文, 2008
[10]胡志华.基于GA-BP网络的造纸废水处理智能控制研究[D].华南理工大学硕士学位论文, 2007
[11]黄明护.基于模糊神经网络模型的废纸造纸废水处理智能控制研究[D].华南理工大学硕士学位论文, 2007
[12]杜树新.污水生化处理过程建模与控制[J].控制理论与应用.2002,19(5):660-666
[13]孙增圻,张再兴,邓志东.智能控制理论与技术[M].北京:清华大学出版社, 1997
[14]高大文,彭永臻,王淑莹,高景峰.污水处理智能控制的研究、应用与发展[J].中国给水排水,2002,18(6):35-39
[15] Ferrer J, Rodrigo M A, Seco A, etal. Energy saving in the aeration process by fuzzy logic control [J]. Wat Sic Tech, 1998, 38(3):209-217
[16] Manesis S A. Intelligent control of wastewater treatment plants [J]. Artificial Intelligencein engineering, 1998, 12:275-281
[17]王之晖,王淑莹,彭永臻等.智能控制在污水生物处理系统中的应用[J].环境污染治理技术与设备, 2004, 45(3): 71-72
[18] Tsai Y P, Ouyang C F, Wu M Y, etal. Fuzzy control of a dynamic activated sludge process for the forecast and control of effluent suspended solid concentration [J]. Wat Sci Tech, 1993, 28(12): 355-367
[19]彭永臻,王淑莹,周刊等.生物电极脱氮法的在线模糊控制-模糊控制系统的组成与基本思想[J].中国给水排水, 1999, 15(2): 5-9
[20]欧林林,王先路,陈长琦等.污水处理实验室系统中溶解氧模糊控制器的设计[J].自动化与仪器仪表, 2003, 105(1): 17-21
[21]高景峰,彭永臻,王淑莹.以DO-ORP-pH控制SBR法的脱氮过程[J].中国给水排水, 2001, 17(4): 6-11
[22]陆杰.模糊控制在污水处理系统中的应用[J].盐湖研究, 2000, 8(2): 29-32
[23]张燕聪.废纸造纸废水处理BP神经网络智能控制系统的研制[D].华南理工大学硕士学位论文, 2006
[24] Karama A, Bernard O, Gouze J L, etal. Hybrid neural modeling of an anaerobic digester with respect to biological constraints [J]. Wat Sic Tech, 2001, 43(7): 1-8
[25] Martin Cote, Bernard P A Grandjean, Paul Lessard, etal.Dynamic modeling of the activated sludge process: improving prediction using neural networks [J]. Water Research, 1995, 29(4): 995-1004
[26] Faur-Brasquet C, Le Cloirec P. Neural network modeling of organics removal by activated carbon cloths [J]. J Environ Eng, 2001, 10 (1): 889-894
[27] S.J.Wilcox, D.L.Hawkes, F.R.Hawkes, A.J. Guwy. A neural network based on bicarbonate monitoring to control an aerobic digestion [J]. Wat Res, 1995, 29(6): 1465-1470
[28]田禹,王宝贞,周定.基于BP人工神经元网络的臭氧生物活性炭系统建模研究[J].中国给水排水, 1998, 14(3): 24-27
[29]吴凡松,彭永臻,王维斌. RBF网络用于活性污泥系统仿真研究[J].中国给水排水, 2003, 19(9): 48-49
[30]白桦,李圭白.混凝投药的神经网络控制方法[J].给水排水, 2001, 27(11): 83-86
[31] Barett M W. Expert systems for anaerobic-digestion-process operation. ASCE[J],Journal of Environmental Engineering, 1992,118(6):949-963
[32] Sung Woo Nam. On-line integrated control system for an industrial activated sludge process[J]. Wat Environ Res,1996,68(1):70-75
[33]施汉昌,王玉珏.污水处理厂故障诊断专家系统[J].给水排水.2001,27(8):88-90
[34]王耀南.智能控制系统:模糊控制·专家系统·神经网络控制[M].湖南大学出版社, 1996
[35] Tay,Joo-Hwa,Zhang Xiyue. Fast predicting neural fuzzy model for high-rate anaerobic wastewater treatment systems [J]. Water Res, 2000, 34(11): 2849-2860
[36] Carrasco,E.F.;Rodriguez,J.;Punal,A.etal.Expert system for the on-line diagnosis of anaerobic wastewater treatment plants [J].Control Eng. Pract.2004, 12(1):59-64
[37] Bongards M.Improving the efficiency of a wastewater treatment plant by fuzzy control and neural networks [J]. Water Sci.Techn, 2001, 3(11):189-196
[38]曲春风.曝气生物滤池性能及动力学研究[D].合肥工业大学硕士学位论文,2006.
[39]王淑莹,彭永臻,周利.用溶解氧浓度作为SBR法过程控制和反应时间控制参数[J].中国环境科学,1998,18(5):415-418.
[40]赵全起.活性污泥法污水处理厂曝气池供氧量的讨论[J]西南给排水, 2007,29(1):1-4
[41]李学海. PIC单片机原理,北京航空航天大学出版社,2004
[42]高俊岭,李咏梅.IPM高智能功率模块在变频器中的应用.煤矿机械,2004,11:9-10
[43]王小明.电动机的单片机控制[M],北京航空航天大学出版社,2002
[44]楼顺天,胡昌华等.基于MATLAB的系统分析与设计—模糊系统[M].西安电子科技大学出版社,2001
[45]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].清华大学出版社,2006
[46]孙曾圻,张再兴,邓兴东.智能控制理论与技术[M].第2版,清华大学出版社, 1997
[47]李士勇.模糊控制、神经控制和智能控制论[M].第1版,哈尔滨工业大学出版社, 1996
[48] Zhang Wenyi, Zhong Meiying, Cai Jian-an. Modeling Study of Activated Sludge Process Based on Artificial Neural Network[J]. Water & Wastewater Engineering, 2002, 28(6): 12-15
[49] Chen J C, Chang N B, Shieh W K. Assessing wastewater reclamation potential by neural network model[J]. Engineering Applications of Artificial Intelligence, 2003,16: 149–157
[50] Pai TY. Grey and neural network prediction of effluent from the wastewater treatment plant of industrial park using influent quality[J]. Environ Eng Sci, 2008, 25
[51] Zhang Q, Stanley S J. Real-time water treatment process control with artificial neural networks. J Environ Eng ASCE, 1999, 125(2): 153–60
[52] Pai T Y, Chuang S H, Ho H H, Yu L F, Su H C, Hu H C. Predicting performance of grey and neural network in industrial effluent using online monitoring parameters[J]. Process Biochemistry, 2008, 43: 199–205
[53] Ren Nanqi, Chen Zhaobo, Wang Xiangjing, et al. Optimized operational parameters of a pilot scale membrane bioreactor for high-strength organic wastewater treatment[J]. International Biodeterioration and Biodegradation, 2005, 56(4): 216-223
[54]刘金琨.智能控制.北京:电子工业出版社, 2005:148
[55]赵振宇,徐用懋.模糊理论和神经网络基础与应用.北京:清华大学出版社,1995
[56] Hunt K J et al., Neural Networks for Control Systems-A Survey, Automatica, 1992, 28(6):1083-1112
[57]李晓忠,汪培庄,罗承忠.模糊神经网络[M],贵阳:贵阳科技出版社,1994
[58] Horikawa S et al., On Fuzzy Modeling using Fuzzy Neural networks with the Back-propagation Algorithm [J], IEEE Trans. on Neural Networks, 1992,3(5):801-806
[59]李少远,李柠.复杂系统的模糊预测控制及其应用[M].北京:科学出版社,2003
[60]高新波.模糊聚类分析及其应用[M].西安电子科技大学出版社, 2004
[61]万金泉,马邕文.废纸造纸及其污染控制[M].中国轻工业出版社,2004
[62]万金泉,马邕文,王艳等.废纸造纸废水特点及其处理技术[J].造纸科学与技术,2005, 24 (5):58-60
[63]张燕聪,万金泉,马邕文等. BP神经网络预测废水处理过程的研究[J].中华纸业,2006,27(2):60-63
[64]美国哈希公司.哈希公司COD在线检测仪说明书
[65] AWA公司. AWA公司COD在线检测仪说明书
[66]保定兰格恒流泵有限公司.兰格蠕动泵使用说明书, 2003
[67]李迪,唐辉等.基于的废纸造纸废水处理过程的动态建模[J].华南理工大学学报(自然科学版) ,2005,33(12):42-45
[68]西门子公司. STEP7-MicroWIN32编程软件说明书
[69]北京昆仑通态自动化软件科技公司. MCGS工控组态软件参考手册, 2003
[70]李运锋,袁景淇,薛耀锋.发酵过程中神经网络训练样本的选取[J].化工自动化及仪表, 2004, 31(6): 21-24
[71] Kocjancic R, Zupan J. Modelling of the River Flow rate: the Influence of the Training Set Selection [J]. Chemometrics and Intelligent Laboratory Systems, 2000, 54(1): 21-34
[72]张震,张德聪.实验设计与数据评价[M].广州:华南理工大学出版社, 2004
[73] Hecht-Nielsen R. Theory of the backpropagation neural network [J]. ProcIJCNN. Washington, 1989, 1:593-605
[2]王树青,元英进.生化过程自动化技术[M].化学工业出版社.2001.
[3]赵耘挚,刘振鸿.活性污泥的发展及在SBR工艺中的应用[J].上业水处理.2002,22(9):12-16.
[4] Olsson G, Aspegren H,Nielsen M K. Operation and control of wastewater treatment—a Scandinavian perspective over 20 years[J]. Water Science and Technology. 1998,37 (12): 1-13
[5] Ohto T. Control, computers and communications: Fusion in instrumentation, control and automation of water and wastewater system in Japan [J]. Water Science and Technology 1998, 37(12):15-19
[6] Garrett M T.Instrumentation,control and automation progress in the United States in the last 24 years [J].Water Science and Technology.1998, 37(12):21-25
[7] Huntingdo R. Twenty years developments of ICA in a water utility [J]. Water Science and Technology, 1998, 37(12):27-34
[8] Kabouris J C. Modeling.Instrumentation, automation and optimization of wastewater treatment facilities [J]. Water Environment Research, 1999, 71(5):729-736
[9]刘华.基于神经网络和模糊PID控制的嵌入式造纸废水处理系统的研究[D].华南理工大学硕士学位论文, 2008
[10]胡志华.基于GA-BP网络的造纸废水处理智能控制研究[D].华南理工大学硕士学位论文, 2007
[11]黄明护.基于模糊神经网络模型的废纸造纸废水处理智能控制研究[D].华南理工大学硕士学位论文, 2007
[12]杜树新.污水生化处理过程建模与控制[J].控制理论与应用.2002,19(5):660-666
[13]孙增圻,张再兴,邓志东.智能控制理论与技术[M].北京:清华大学出版社, 1997
[14]高大文,彭永臻,王淑莹,高景峰.污水处理智能控制的研究、应用与发展[J].中国给水排水,2002,18(6):35-39
[15] Ferrer J, Rodrigo M A, Seco A, etal. Energy saving in the aeration process by fuzzy logic control [J]. Wat Sic Tech, 1998, 38(3):209-217
[16] Manesis S A. Intelligent control of wastewater treatment plants [J]. Artificial Intelligencein engineering, 1998, 12:275-281
[17]王之晖,王淑莹,彭永臻等.智能控制在污水生物处理系统中的应用[J].环境污染治理技术与设备, 2004, 45(3): 71-72
[18] Tsai Y P, Ouyang C F, Wu M Y, etal. Fuzzy control of a dynamic activated sludge process for the forecast and control of effluent suspended solid concentration [J]. Wat Sci Tech, 1993, 28(12): 355-367
[19]彭永臻,王淑莹,周刊等.生物电极脱氮法的在线模糊控制-模糊控制系统的组成与基本思想[J].中国给水排水, 1999, 15(2): 5-9
[20]欧林林,王先路,陈长琦等.污水处理实验室系统中溶解氧模糊控制器的设计[J].自动化与仪器仪表, 2003, 105(1): 17-21
[21]高景峰,彭永臻,王淑莹.以DO-ORP-pH控制SBR法的脱氮过程[J].中国给水排水, 2001, 17(4): 6-11
[22]陆杰.模糊控制在污水处理系统中的应用[J].盐湖研究, 2000, 8(2): 29-32
[23]张燕聪.废纸造纸废水处理BP神经网络智能控制系统的研制[D].华南理工大学硕士学位论文, 2006
[24] Karama A, Bernard O, Gouze J L, etal. Hybrid neural modeling of an anaerobic digester with respect to biological constraints [J]. Wat Sic Tech, 2001, 43(7): 1-8
[25] Martin Cote, Bernard P A Grandjean, Paul Lessard, etal.Dynamic modeling of the activated sludge process: improving prediction using neural networks [J]. Water Research, 1995, 29(4): 995-1004
[26] Faur-Brasquet C, Le Cloirec P. Neural network modeling of organics removal by activated carbon cloths [J]. J Environ Eng, 2001, 10 (1): 889-894
[27] S.J.Wilcox, D.L.Hawkes, F.R.Hawkes, A.J. Guwy. A neural network based on bicarbonate monitoring to control an aerobic digestion [J]. Wat Res, 1995, 29(6): 1465-1470
[28]田禹,王宝贞,周定.基于BP人工神经元网络的臭氧生物活性炭系统建模研究[J].中国给水排水, 1998, 14(3): 24-27
[29]吴凡松,彭永臻,王维斌. RBF网络用于活性污泥系统仿真研究[J].中国给水排水, 2003, 19(9): 48-49
[30]白桦,李圭白.混凝投药的神经网络控制方法[J].给水排水, 2001, 27(11): 83-86
[31] Barett M W. Expert systems for anaerobic-digestion-process operation. ASCE[J],Journal of Environmental Engineering, 1992,118(6):949-963
[32] Sung Woo Nam. On-line integrated control system for an industrial activated sludge process[J]. Wat Environ Res,1996,68(1):70-75
[33]施汉昌,王玉珏.污水处理厂故障诊断专家系统[J].给水排水.2001,27(8):88-90
[34]王耀南.智能控制系统:模糊控制·专家系统·神经网络控制[M].湖南大学出版社, 1996
[35] Tay,Joo-Hwa,Zhang Xiyue. Fast predicting neural fuzzy model for high-rate anaerobic wastewater treatment systems [J]. Water Res, 2000, 34(11): 2849-2860
[36] Carrasco,E.F.;Rodriguez,J.;Punal,A.etal.Expert system for the on-line diagnosis of anaerobic wastewater treatment plants [J].Control Eng. Pract.2004, 12(1):59-64
[37] Bongards M.Improving the efficiency of a wastewater treatment plant by fuzzy control and neural networks [J]. Water Sci.Techn, 2001, 3(11):189-196
[38]曲春风.曝气生物滤池性能及动力学研究[D].合肥工业大学硕士学位论文,2006.
[39]王淑莹,彭永臻,周利.用溶解氧浓度作为SBR法过程控制和反应时间控制参数[J].中国环境科学,1998,18(5):415-418.
[40]赵全起.活性污泥法污水处理厂曝气池供氧量的讨论[J]西南给排水, 2007,29(1):1-4
[41]李学海. PIC单片机原理,北京航空航天大学出版社,2004
[42]高俊岭,李咏梅.IPM高智能功率模块在变频器中的应用.煤矿机械,2004,11:9-10
[43]王小明.电动机的单片机控制[M],北京航空航天大学出版社,2002
[44]楼顺天,胡昌华等.基于MATLAB的系统分析与设计—模糊系统[M].西安电子科技大学出版社,2001
[45]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].清华大学出版社,2006
[46]孙曾圻,张再兴,邓兴东.智能控制理论与技术[M].第2版,清华大学出版社, 1997
[47]李士勇.模糊控制、神经控制和智能控制论[M].第1版,哈尔滨工业大学出版社, 1996
[48] Zhang Wenyi, Zhong Meiying, Cai Jian-an. Modeling Study of Activated Sludge Process Based on Artificial Neural Network[J]. Water & Wastewater Engineering, 2002, 28(6): 12-15
[49] Chen J C, Chang N B, Shieh W K. Assessing wastewater reclamation potential by neural network model[J]. Engineering Applications of Artificial Intelligence, 2003,16: 149–157
[50] Pai TY. Grey and neural network prediction of effluent from the wastewater treatment plant of industrial park using influent quality[J]. Environ Eng Sci, 2008, 25
[51] Zhang Q, Stanley S J. Real-time water treatment process control with artificial neural networks. J Environ Eng ASCE, 1999, 125(2): 153–60
[52] Pai T Y, Chuang S H, Ho H H, Yu L F, Su H C, Hu H C. Predicting performance of grey and neural network in industrial effluent using online monitoring parameters[J]. Process Biochemistry, 2008, 43: 199–205
[53] Ren Nanqi, Chen Zhaobo, Wang Xiangjing, et al. Optimized operational parameters of a pilot scale membrane bioreactor for high-strength organic wastewater treatment[J]. International Biodeterioration and Biodegradation, 2005, 56(4): 216-223
[54]刘金琨.智能控制.北京:电子工业出版社, 2005:148
[55]赵振宇,徐用懋.模糊理论和神经网络基础与应用.北京:清华大学出版社,1995
[56] Hunt K J et al., Neural Networks for Control Systems-A Survey, Automatica, 1992, 28(6):1083-1112
[57]李晓忠,汪培庄,罗承忠.模糊神经网络[M],贵阳:贵阳科技出版社,1994
[58] Horikawa S et al., On Fuzzy Modeling using Fuzzy Neural networks with the Back-propagation Algorithm [J], IEEE Trans. on Neural Networks, 1992,3(5):801-806
[59]李少远,李柠.复杂系统的模糊预测控制及其应用[M].北京:科学出版社,2003
[60]高新波.模糊聚类分析及其应用[M].西安电子科技大学出版社, 2004
[61]万金泉,马邕文.废纸造纸及其污染控制[M].中国轻工业出版社,2004
[62]万金泉,马邕文,王艳等.废纸造纸废水特点及其处理技术[J].造纸科学与技术,2005, 24 (5):58-60
[63]张燕聪,万金泉,马邕文等. BP神经网络预测废水处理过程的研究[J].中华纸业,2006,27(2):60-63
[64]美国哈希公司.哈希公司COD在线检测仪说明书
[65] AWA公司. AWA公司COD在线检测仪说明书
[66]保定兰格恒流泵有限公司.兰格蠕动泵使用说明书, 2003
[67]李迪,唐辉等.基于的废纸造纸废水处理过程的动态建模[J].华南理工大学学报(自然科学版) ,2005,33(12):42-45
[68]西门子公司. STEP7-MicroWIN32编程软件说明书
[69]北京昆仑通态自动化软件科技公司. MCGS工控组态软件参考手册, 2003
[70]李运锋,袁景淇,薛耀锋.发酵过程中神经网络训练样本的选取[J].化工自动化及仪表, 2004, 31(6): 21-24
[71] Kocjancic R, Zupan J. Modelling of the River Flow rate: the Influence of the Training Set Selection [J]. Chemometrics and Intelligent Laboratory Systems, 2000, 54(1): 21-34
[72]张震,张德聪.实验设计与数据评价[M].广州:华南理工大学出版社, 2004
[73] Hecht-Nielsen R. Theory of the backpropagation neural network [J]. ProcIJCNN. Washington, 1989, 1:593-605