污水处理过程模拟及系统软件开发
|
摘要
对于污水处理和回用技术,更高的处理效率,更低的处理成本是人们一直追求的目标。但是,由于进水水质复杂、多种污水处理工艺组合应用,生物处理过程受多种因素影响,常常致使污水处理效果不佳,处理率低下,故障频现,为水体污染控制和管理造成困难。因此,亟需开展污水处理过程的模拟和预测,为污水处理过程的正常运行和管理提供参考；另外还需加强故障诊断方面的工作,为故障处置提供依据。本文结合BP神经网络和支持向量机回归(SVR)开展污水处理过程模拟和反问题研究,并开发污水处理系统软件。取得以下研究结果：
1.发展了组合寻优法和逐步网格搜索法分别用于BP神经网络和SVR相关参数的优化设置。选取某污水处理厂污水处理过程和垂直折流多功能生化反应器(VTBR)非稳态污水处理过程作为两个典型案例,考察BP神经网络和SVR在出水水质模拟方面的性能。结果表明BP神经网络和SVR均能获得良好的模拟结果,并各具特色。由于网络结构的复杂性,BP神经网络可能产生欠拟合或者过拟合现象,一般难以获取最佳模型；SVR则能较好地解决该问题,获得全局最优解。但是BP神经网络把相关建模信息内化于网络结构和权重中,应用连接权值法和网络图形法可进行变量重要性和网络结构的解释,考察和分析进出水参数之间的相关关系,为出水水质控制提供参考和依据。
2.应用BP神经网络和SVR进行污水处理过程模拟的反问题研究,为进一步深入开展污水处理过程的故障分析和诊断研究提供基础。对于整个污水处理厂的污水处理过程,由于其间涉及到多种污水处理过程和工艺,出水水质到进水水质的映射关系并不明显,因此,部分反问题的模拟和预测结果并不理想。但是对于VTBR工艺过程,可根据出水水质情况对进水水质进行良好的模拟和预测,SVR在反问题研究上同样表现出较BP神经网络好的建模效果。由于反问题研究主要关心进水数据的模拟和预测,以用于故障的分析和诊断,而不再需要考察进出水参数之间的相关关系,因此SVR较适用于污水处理过程模拟的反问题研究,为今后进行实际工作提供了较为明确的模拟基础。
3.应用Visual Basic 6.0结合AutoCAD 2010和Access,在Windows XP操作系统平台上实现了污水处理工艺的计算机辅助设计和系统软件开发,可以进行格栅、沉淀池、调节池、混凝、吸附、活性污泥法、生物膜法、氧化沟等单元操作的自动设计计算和工程图纸的绘制；可进行纺织印染废水、化工废水和含油废水等三种工业废水处理工艺的投资估算及流程选择；并建立了相关数据库及图库可用于数据及工程图的存储及调用。
For the technology of wastewater treatment and reuse, higher processing efficiency and lower processing costs are the goal that people are pursuing. However, due to complex influent quality, combination of various wastewater treatment processes and susceptible biological processes, the effect of wastewater treatment is often not so good with low processing rate and frequent malfunctions, which causes difficulties for the water pollution control and management. Therefore, on the one side, simulating and predicting of wastewater treatment processes are urgently needed to be carried out in order to providing reference for the normal operation of the wastewater treatment process and management; on the other side, fault diagnosing are also needed to be enhanced in order to provide the basis for the failure handing. In the present study, simulation of the wastewater treatment process and its inverse problem were investigated using BP network and support vector machine regression (SVR), and a system software for the wastewater treatment process was developed. The obtained results are as follows:
1. A portfolio optimization method and a step grid search method were developed and used for setting the parameters of BP network and SVR, respectively. The wastewater treatment processes of a wastewater treatment plant (WWTP) and unsteady VTBR were chosen to investigate the performance of BP network and SVR on simulating effluent. Results showed that BP network and SVR could both build good models. Due to the complication of the network, BP network could cause under-fitting or over-fitting results, so in general it is not easy to obtain the optimal model. As SVR can solve the above question, it can get the optimal model. However, for BP network, modeling information was internalized in network and weights, so calculation of variable importance and explaination of network can be realized by using the Connection Weights method and Network Interpretation Diagram. Based on the explaination of BP network, the relationship between influent and effluent can be analyzed, which provides reference for the control of effluent quality.
2. Inverse problem of process simulation of wastewater treatment was also investigated using BP network and SVR, which was designed to provide basis for fault diagnosing. For the WWTP, the mapping relationship from effluent to influent might be not good, since a variety of wastewater treatment processes were used in the WWTP. Therefore, simulation and prediction of the inverse problem might not be so good. However, simulation and prediction of the influent from effluent are good for VTBR process, and SVR models performed better than BP network models. Furthermore, simulation and prediction of the data of influent, not the the relationship between influent and effluent, are the main concern for the study of inverse problem. Therefore, SVR is more suitable for the study of inverse problem.
3. On platform of Windows XP operating system, the Computer-aided design (CAD) and system software for wastewater treatment processes were developed using Visual Basic 6.0, AutoCAD 2010 and Access. It can be used for automatic design and automatic engineering drawings for bar screen, sedimentation tank, regulating reservoir, coagulation, adsorption, activated sludge process, bio-membrane process, Qxidation Ditch, etc; for process selection and investment estmation of textile wastewater treatment, chemical wastewater treatment and oil wastewater treatment; and for storage and calling of data and drawings from corresponding databases.
1.发展了组合寻优法和逐步网格搜索法分别用于BP神经网络和SVR相关参数的优化设置。选取某污水处理厂污水处理过程和垂直折流多功能生化反应器(VTBR)非稳态污水处理过程作为两个典型案例,考察BP神经网络和SVR在出水水质模拟方面的性能。结果表明BP神经网络和SVR均能获得良好的模拟结果,并各具特色。由于网络结构的复杂性,BP神经网络可能产生欠拟合或者过拟合现象,一般难以获取最佳模型；SVR则能较好地解决该问题,获得全局最优解。但是BP神经网络把相关建模信息内化于网络结构和权重中,应用连接权值法和网络图形法可进行变量重要性和网络结构的解释,考察和分析进出水参数之间的相关关系,为出水水质控制提供参考和依据。
2.应用BP神经网络和SVR进行污水处理过程模拟的反问题研究,为进一步深入开展污水处理过程的故障分析和诊断研究提供基础。对于整个污水处理厂的污水处理过程,由于其间涉及到多种污水处理过程和工艺,出水水质到进水水质的映射关系并不明显,因此,部分反问题的模拟和预测结果并不理想。但是对于VTBR工艺过程,可根据出水水质情况对进水水质进行良好的模拟和预测,SVR在反问题研究上同样表现出较BP神经网络好的建模效果。由于反问题研究主要关心进水数据的模拟和预测,以用于故障的分析和诊断,而不再需要考察进出水参数之间的相关关系,因此SVR较适用于污水处理过程模拟的反问题研究,为今后进行实际工作提供了较为明确的模拟基础。
3.应用Visual Basic 6.0结合AutoCAD 2010和Access,在Windows XP操作系统平台上实现了污水处理工艺的计算机辅助设计和系统软件开发,可以进行格栅、沉淀池、调节池、混凝、吸附、活性污泥法、生物膜法、氧化沟等单元操作的自动设计计算和工程图纸的绘制；可进行纺织印染废水、化工废水和含油废水等三种工业废水处理工艺的投资估算及流程选择；并建立了相关数据库及图库可用于数据及工程图的存储及调用。
For the technology of wastewater treatment and reuse, higher processing efficiency and lower processing costs are the goal that people are pursuing. However, due to complex influent quality, combination of various wastewater treatment processes and susceptible biological processes, the effect of wastewater treatment is often not so good with low processing rate and frequent malfunctions, which causes difficulties for the water pollution control and management. Therefore, on the one side, simulating and predicting of wastewater treatment processes are urgently needed to be carried out in order to providing reference for the normal operation of the wastewater treatment process and management; on the other side, fault diagnosing are also needed to be enhanced in order to provide the basis for the failure handing. In the present study, simulation of the wastewater treatment process and its inverse problem were investigated using BP network and support vector machine regression (SVR), and a system software for the wastewater treatment process was developed. The obtained results are as follows:
1. A portfolio optimization method and a step grid search method were developed and used for setting the parameters of BP network and SVR, respectively. The wastewater treatment processes of a wastewater treatment plant (WWTP) and unsteady VTBR were chosen to investigate the performance of BP network and SVR on simulating effluent. Results showed that BP network and SVR could both build good models. Due to the complication of the network, BP network could cause under-fitting or over-fitting results, so in general it is not easy to obtain the optimal model. As SVR can solve the above question, it can get the optimal model. However, for BP network, modeling information was internalized in network and weights, so calculation of variable importance and explaination of network can be realized by using the Connection Weights method and Network Interpretation Diagram. Based on the explaination of BP network, the relationship between influent and effluent can be analyzed, which provides reference for the control of effluent quality.
2. Inverse problem of process simulation of wastewater treatment was also investigated using BP network and SVR, which was designed to provide basis for fault diagnosing. For the WWTP, the mapping relationship from effluent to influent might be not good, since a variety of wastewater treatment processes were used in the WWTP. Therefore, simulation and prediction of the inverse problem might not be so good. However, simulation and prediction of the influent from effluent are good for VTBR process, and SVR models performed better than BP network models. Furthermore, simulation and prediction of the data of influent, not the the relationship between influent and effluent, are the main concern for the study of inverse problem. Therefore, SVR is more suitable for the study of inverse problem.
3. On platform of Windows XP operating system, the Computer-aided design (CAD) and system software for wastewater treatment processes were developed using Visual Basic 6.0, AutoCAD 2010 and Access. It can be used for automatic design and automatic engineering drawings for bar screen, sedimentation tank, regulating reservoir, coagulation, adsorption, activated sludge process, bio-membrane process, Qxidation Ditch, etc; for process selection and investment estmation of textile wastewater treatment, chemical wastewater treatment and oil wastewater treatment; and for storage and calling of data and drawings from corresponding databases.
引文
[1]吴雅琼,吕志坚,安斌.1985—2008年间我国废水排放量动态研究[J].科技情报开发与经济,2011,21(17)：183-185.
[2]中投顾问.2011-2015年中国污水处理行业投资分析及前景预测报告[R].2011.7.
[3]张文巧.浅谈我国城市污水处理的紧迫性[J].山西建筑,2010,36(11)：174-175.
[4]陈中颖,刘爱萍,刘永,许振成.中国城镇污水处理厂运行状况调查分析[J].环境污染与防治,2009,3l(9)：99-102.
[5]杜彬,侯宏良.我国城市污水处理面临的问题及解决对策[J].环境保护与循环经济,2011,4： 73-75.
[6]王宝贞.水污染控制工程[M].北京：高等教育出版社,1990.
[7]高廷耀,顾国维.水污染控制工程(第三版)[M].北京：高等教育出版社,2007.
[8]Henze M, Gujer W, Mino T, et al. Activated sludge models ASM1, ASM2, ASM2d and ASM3 [M]. London:IWA Publishing,2002.
[9]Gernaey K V, van Loosdrecht M C M, Henze M, et al. Activated sludge wastewater treatment plant modelling and simulation:state of the art [J]. Environmental Modelling & Software,2004,19:763-783.
[10]李峰,吴敏,杨哲.活性污泥数学模型在我国的研究进展[J].中国资源综合利用,2007,25(11)：21-23.
[11]黄明智,马邕文,万金泉等.污水处理中人工神经网络应用研究的探讨[J].环境科学与技术,2008,31(3)：131-135.
[12]苏书惠,张绍德,谭敬辉.基于支持向量机的污水处理软测量算法的研究[J].自动化与仪器仪表,2009,146(6)：6-9.
[13]宋岩,潘丰.基于SVM软测量技术的污水处理控制系统设计[J].自动化与仪表,2008,29(11)：5-7,22.
[14]赖惠鸽,朱学军,俞金寿.基于智能算法的污水处理软测量技术及其展望[J].化工自动化与仪表,201l,3：241-244.
[15]Ye H T, Luo F, Xu Y G. Application of RBF Network Based on Immune Algorithm to Predicting of Wastewater Treatment [J]. Lecture Notes in Computer Science,2009, 5553(3):1197-1202.
[16]Pai T Y. Gray and neural network prediction of effluent from the wastewater treatment plant of industrial park using influent quality [J]. Environ Eng Sci, 2008,25(5):757-765.
[17]郭劲松,龙腾锐,高旭,等.间歇曝气活性污泥系统神经网络水质模型[J].中国给水排水,2000,16(11)：15-18.
[18]易赛莉,雒文生.人工神经网络在UASB反应器处理生活污水中的模拟预测与应用[J].武汉大学学报(工学版),2004,37(1)：46-50.
[19]Hamed M M, Khalafallah M G, Hassanien E A. Prediction of wastewater treatment plant performance using artificial neural networks[J]. Environmental Modelling & Software,2004,19:919-928.
[20]胡坚,严敏,刘俊萍,等.径向基函数人工神经网络预测污水处理厂出水水质[J].浙江工业大学学报.2006,34(6)：633—636,
[21]朱启兵,黄敏,崔宝同.基于小波神经网络的污水处理厂出水水质预测[J].计算机工程与应用,2007,43(28)：15-17,33.
[22]Mjalli F S, Al-Asheh S, Alfadala H E. Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance [J]. Journal of Environmental Management,2007,83:329-338.
[23]Raduly B, Gernaey K V, Capodaglio A G, et al. Artificial neural networks for rapid WWTP performance evaluation:Methodology and case study[J]. Environmental Modelling & Software 2007,22:1208-1216.
[24]万金泉,黄明智,马邕文.基于模糊神经网络的工业废水处理预测研究[J].中国造纸学报,2008,23(2)：96-99.
[25]宋贤民,衷卫声.基于RS-SVM的TN软测量建模研究[J].制造业自动化,2007,29(1)：90-92.
[26]黄银蓉,张绍德MIMO最小二乘支持向量机污水处理在线软测量研究[J].自动化与仪器仪表,2010,4：15-17.
[27]张杰,张建秋,冯辉,等.支持向量机和神经网络联合软测量SBR污水处理中COD的方法[J].传感技术学报,2009,22(10)：1519-1524.
[28]Frank P M. Analytical and Qualitative Model-based Fault Diagnosis-A Survey and SomeNew Results [J]. European Journal of Control 1996,2(1):6-28.
[29]Venkatasubramanian V, Rengaswamy R, Yin K, et al. A review of process fault detection and diagnosis PartⅠ:Quantitative model-based methods [J]. Computers and Chemical Engineering,2003,27:293-311.
[30]Venkatasubramanian V, Rengaswamy R, Kavuri S N. A review of process fault detection and diagnosis Part II:Qualitative models and search strategies [J]. Computers and Chemical Engineering,2003,27:313-326.
[31]Venkatasubramanian V, Rengaswamy R, Kavuri S N. A review of process fault detection and diagnosis Part III:Process history based methods[J]. Computers and Chemical Engineering,2003,27:327-346.
[32]Lapointe J, Marcos B, Veillette M, et al. BIOEXPERT-An Expert System for Wastewater Treatment Process Diagnosis [J] Computers and Chemical Engineering, 1989,13(6):619-630.
[33]Barnett M W. Expert systems for anaerobic digestion process operation [J]. Journal of Environmental Engineering,1992,118(6):949-963.
[34]Genovesi A, Harmand J, Steyer J-P. A fuzzy logic based diagnosis system for the on-line supervision of an anaerobic digestor pilot-plant [J]. Biochemical Engineering Journal,1999,3:171-183.
[35]Carrasco E F, Rodriguez J, Punal A, et al. Rule-based diagnosis and supervision of a pilotscale wastewater treatment plant using fuzzy logic techniques. Expert Systems with Applications,2002,22:11-20.
[36]Comas J, Rodriguez-Roda I, Sanchez-Marre M, et al. A knowledge-based approach to the deflocculation problem:integrating on-line, off-line, and heuristic information [J]. Water Research,2003,37:2377-2387.
[37]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.
[38]郑上闽,孙进生.污水处理工艺系统的故障诊断专家系统[J].河北理工学院学,2001,23(3)：42-47.
[39]彭芳,黄大贵.用C++Builder开发污水处理故障诊断专家数据库系统[J].中国测试技术,2004,4(30)：81-83.
[40]李振宇,杨昌柱.污水生物处理故障诊断专家咨询系统[J].化学与生物工程,2005,3：39-41.
[41]曹晓莉,江朝元,甘思源.基于聚类支持向量机的船用污水处理装置故障诊断[J].计算机应用,2008,28(10)：2648-2651.
[42]李晓东,曾光明,蒋茹,等.改进支持向量机对污水处理厂运行状况的故障诊断[J].湖南大学学报(自然科学版),2007,34(12)：68-71.
[43]徐丽婕,王志强,施汉昌.污水处理厂全程模型化的软件选择[J].中国给水排水,2004,20(5)：21-23.
[44]郭亚萍,陈士才,张宇坤,等.ASMs仿真软件在污水处理厂中的应用[J].中国给水排水,2010,26(14)：23-29.
[45]葛守飞,濮文虹,李振宇,等.污水处理工艺选择决策支持系统的开发与应用[J].工业用水与废水,2005,36(5)：4-7.
[46]朱文斌,任洪强,魏翔.工业废水处理工艺设计专家系统的设计和实现[J].工业用水与废水,2007,38(4)：62-65.
[47]Olden J D, Jackson D A. Illuminating the "black box":a randomization approach for understanding variable contributions in artificial neural networks [J]. Ecological Modelling,2002,154(1):135-150.
[48]Gevrey M, Dimopoulos I, Lek S. Review and comparison of methods to study the contribution of variables in artificial neural network models [J]. Ecological Modelling,2003,160(2):249-264.
[49]Kemp S J, Zaradic P, Hansen F. An approach for determining relative input parameter importance and significance inartificial neural networks [J]. Ecological modeling, 2007,204:326-334.
[50]张德丰MATLAB神经网络应用设计[M].北京：机械工业出版社,2008.
[51]金峤,方帅,阎石,等.BP网络模型的改进方法综述[J].沈阳建筑工程学院学报(自然科学版),2001,17(3)：197-199.
[52]鲁娟娟,陈红.BP神经网络的研究进展[J].控制工程,2006,13(5)：449-451.
[53]余本国.BP神经网络局限性及其改进的研究[J].山西农业大学学报,2009,29(1)：89-93.
[54]张国翊,胡铮.改进BP神经网络模型及其稳定性分析[J].中南大学学报(自然科学版),2011,42(1)：115-124.
[55]张庆庆,贺兴时.BP神经网络结点数选取的改进方法及其应用[J].西安工程大学学报,2008,22(4)：502-505.
[56]范佳妮,王振雷,钱锋.BP人工神经网络隐层结构设计的研究进展[J].控制工程,2005,12(S0)：105-109.
[57]张德贤.前向神经网络合理隐含层结点个数估计[J].计算机工程与应用,2005,5：21-24.
[58]蔡兵.BP神经网络隐层结构的设计方法[J].通化师范学院学报,2007,28(2)：18-19.
[59]Huisken M, Jin Y, Sendhoff B. Structure optimization of neural networks for evolutionary design optimization. Soft Computing 2005,9:21-28.
[60]张立明.人工神经网络的模型及其应用[M].上海：复旦大学出版社.1993.
[61]袁曾任.人工神经元网络及其应用[M].北京：清华大学出版社,1999.
[62]戚德虎,康继昌.BP神经网络的设计[J].计算机工程与设计.1998,19(2)：48-50.
[63]高大启.线性基本函数前向三层神经网络结构研究[J].计算机学报,1998,21(1)：80-85.
[64]周红晓,蔡俊,张德官.一种优化多层前馈神经网络中隐节点数的算法[J].浙江师范大学(自然科学版),2002,25(3)：268-271.
[65]MezardM, Nadal J-P. Learning in feedforward layered networks:the tiling algorithm [J]. J. Phys. A:Math. Gen.22 (1989) 2191-2203.
[66]Fahlman S E, Lebiere C. The Cascade-Correlation Learning Architecture [C]// Advances in Neural Information Processing Systems 2, Touretzky D S. (ed.), Morgan-Kaufmann, Los Altos CA,1990.
[67]Littmann E, Ritter H. Generalization Abilities of Cascade Network Architecture [C]//Proceedings of NIPS.1992:188-195.
[68]叶东毅.前馈神经网络隐层结点设计的一个学习算法[J].电子学报,1997,25(11)：126-128.
[69]赵林明,魏德华.优选人工神经网络隐层神经元数目的方法[J].华北水利水电学院学报,1999,20(4)：44-48.
[70]Lee H J, Park H, Lee Y. Network Optimization through Learning and Pruning in Neuromanifold [J]. Lecture Notes in Computer Science,2002,24(17):169-177.
[71]Henderson C E, Potter W D, McClendon R W, Hoogenboom G. Predicting aflatoxin contamination in peanuts:A genetic algorithm/neural network approach [J]. Applied Intelligence 2000,12:183-192.
[72]李智勇,童调生.基于多物种进化遗传算法的神经网络结构学习方法[J].计算机工程及应用,2003,22(8)：87-90.
[73]朱海燕,朱晓莲,黄螟.基于动态BP神经网络的预测方法及其应用[J].计算机与信息技术.2007,Z1：3-6.
[74]吴永明,吴晟.改进的遗传算法在神经网络结构优化中的应用[J].微型机与应用.2011,30(3)：79-81.
[75]杨伟,倪黔东,吴军基.BP神经网络权值初始值与收敛性问题研究[J].电力系统及其自动化学报,2002,14(1)：20-22.
[76]谢富强,唐耀庚.多层前向神经网络权值初始化的研究进展[J].南华大学学报(自然科学版),2006,20(3)：98-101.
[77]武妍,王守觉.权值初始化与激励函数调整相结合的学习算法[J].计算机工程与应用,2004(30)：23-26.
[78]蒋蓉蓉.一种基于遗传算法的BP网络改进方法[J].微计算机信息,2007,23(11)：234-236.
[79]王静伟.BP神经网络改进算法的研究[J].中国水运,2008,8(1)：157-158.
[80]覃光华,王顺久,缪韧.基于卡尔曼滤波技术的人工神经网络权重估算及应用[J].四川大学学报：自然科学版,2008,25(4)：25-28.
[81]李翱翔,陈健.BP神经网络参数改进方法综述[J].数字通信世界,2009,(1)：62-64.
[82]潘吴,钟珞,陈杰.BP神经网络训练的函数变步长搜索调整法[J].湖北工学院学报,1997,12(2)：1-4.
[83]许廷发,张敏,顾海军,等.改进的BP算法在多目标识别中的应用[J].光学精密程,2003,11(5)：513-515.
[84]候彦东,方惠敏,杨国胜,等.一种改进的可变学习速率的BP神经网络算法[J].河南大学学报(自然科学版),2008,38(3)：309-312.
[85]武妍,张立明.神经网络的泛化能力与结构优化算法研究[J].计算机应用研究,2002,6：21-25.
[86]王恺,杨巨峰,王立,等.人工神经网络泛化问题研究综述[J].计算机应用研究,2008,25(12)：3525-3533.
[87]周志华,陈世福.神经网络规则抽取[J].计算机研究与发展,2002,39(4)：398-405.
[88]胡包钢,王泳,杨双红,曲寒冰.如何增加人工神经元网络的透明度?[J].模式识别与人工智能,2007,20(1)：72-84.
[89]Ozesmi S L, Ozesmi U. An artificial neural network approach to spatial habitat modeling with interspecific interaction [J]. Ecol. Model.1999,116,15-31.
[90]Tzeng F Y, Ma K L. Opening the black box-data driven visualization of neural networks[C]. In:Proceedings of IEEE Visualization'05 Conference.2005,383-390.
[91]Weckman G R, Millie D F, Ganduri C, Rangwala M, Young W, Rinder M, Fahnenstiel GL. Knowledge Extraction from the Neural'Black Box'in Ecological Monitoring [J]. Journal of Industrial and Systems Engineering,2009,3(1):38-55.
[92]Garson G D. Interpreting neural network connection weights [J]. Artificial Intelligence Expert 1991,6(4):47-51.
[93]Towell G G, Shavlik J W. Extracting Refined Rules from Knowledge Based Neural Networks[J]. Machine Learning,1993,13(1):71-101.
[94]Setiono R. Extracting Rules from Neural Networks by Pruning and Hidden-Unit Splitting[J]. Neural Computation,1997,9(1):205-225.
[95]Setiono R, Leow W K. FERNN:An algorithm for Fast Extraction of Rules from Neural Networks[J]. Applied Intelligence,2000,12(1-2):15-25.
[96]Craven M, Shavlik J. Using Sampling and Queries to Extract Rules from Trained Neural Networks[C] In Proceeding of the Eleventh International Conference on Machine Learning,1994,37-45.
[97]陈清后.影响生物脱氮除磷的因素[J].污染防治技术,2007,20(1)：41-42.
[98]Vapnik V N. The Nature of Statistical Learning Theory [M]. New York:Springer-Verlag, 1995.
[99]Ivanciuc 0. Applications of Support Vector Machines in Chemistry. In:Reviews in Computational Chemistry, Volume 23, Eds.:Lipkowitz K. B. and Cundari T. R. Wiley-VCH, Weinheim,2007, pp.291-400.
[100]Mattera D, Haykin S. Support Vector Machines for Dynamic Reconstruction of a Chaotic System [M] In Advances in Kernel Methods-Support Vector Learning. Scholkopf B, Burges CJC, Smola AJ. (Eds.) Cambridge, MA:MIT Press.1999. ISBN 0-262-19416-3.
[101]Cherkassky V, Ma YQ. Practical Selection of SVM Parameters and Noise Estimation for SVM Regression [J]. Neural Networks,2004,17(1):113-126.
[102]Kwok JT, Tsang IW. Linear Dependency between Epsilon and the Input Noise in Epsilon-Support Vector Regression [J]. IEEE Trans. Neural Networks,2003,14(3): 544-553.
[103]Chalimourda A, Scholkopf B, Smola AJ. Experimentally Optimal v in Support Vector Regression for Different Noise Models and Parameter Settings [J]. Neural Networks, 2004,17(1):127-141.
[104]王鹏,朱小燕.基于RBF核的SVM的模型选择及其应用[J].计算机工程与应用,2003,39(24)：72-73.
[105]刘靖旭,蔡怀平,谭跃进.支持向量回归参数调整的一种启发式算法[J].系统仿真学报.2007,19(7)：1540-1547.
[106]Chan YJ, Chong MF, Law CL, et al. A review on anaerobic-aerobic treatment of industrial and municipal wastewater[J]. Chemical Engineering Journal,2009, 155(1-2):1-18.
[107]Ahn YT, Kang ST, Chae SR, et al. Simultaneous high-strength organic and nitrogen removal with combined anaerobic upflow bed filter and aerobic membrane bioreactor [J]. Desalination 2007,202:114-121.
[108]Bodik I, Kratochvil K, Gasparikovd E, et al. Nitrogen removal in an anaerobic baffled filter reactor with aerobic post-treatment [J]. Bioresource Technology 2003,86:79-84.
[109]Tartakovsky B, Manuel MF, Guiot SR. Degradation of trichloroethylene in a coupled anaerobic-aerobic bioreactor:Modeling and experiment [J]. Biochemical Engineering Journal 2005,26:72-81.
[110]Wang RM, Wang Y, Ma GP, et al. Efficiency of porous burnt-coke carrier on treatment of potato starch wastewater with an anaerobic-aerobic bioreactor [J]. Chemical Engineering Journal 2009,148:35-40.
[111]周集体,童健,王栋,等.垂直折流生化反应器污水厌氧一好氧串联处理工艺：中国,CNl289730[P].2001.
[112]王冠一,周集体VTBR反应器对对石油炼制废水的生物脱氮研究[J].西安公路交通大学学报,199919(S)：94-96.
[113]周集体,曹同川,杨桦,等.新乡白鹭化纤集团棉浆黑液废水处理工程设计[J].环境工程,2002,20(1)：22-23.
[114]田博VTBR反应器加微电解工艺处理生活污水[J].辽宁化工,2004,33(3)：170-171.
[115]周涛,周集体.垂直折流反应器一超滤膜水处理技术的实验研究[J].工业水处理,2002,22(3)：23-25.
[116]姜素君,毕岩松VTBR生化处理污水技术在锦州港的应用[J].水运工程,2003,356(9)：39-41.
[117]付咭VTBR生化反应器+ME微电解工艺在生活污水处理及回用工程中的应用[J].辽宁城乡环境科技,2004,24(2)：31-33.
[118]周集体,邢礼娜,张劲松.多级A/0 VTBR组合工艺处理焦化废水[J].环境工程,2010,28(3)：26-29.
[119]杨松林.水处理工程CAD技术应用及实例[M].北京：化学工业出版社,2002.
[120]杨松林,秦乐乐.环境工程CAD技术应用及实例[M].北京：化学工业出版社,2004.
[121]陈扬,李硕文,同帜.水处理工程计算机辅助设计[J].西北纺织工学院学报,1997,11(2)：169-171.
[122]罗程亮,张明泉,桑学峰.用Visual Basic语言实现污水处理平流式沉淀池的计算机辅助设计[J].甘肃科技,2005,21(2)：44-47.
[123]沈耀良,王宝贞.循环活性污泥系统(CASS)处理城市废水[J].给水排水,1999,25(11)：10-13.
[124]张胜华,宋丰明,孙勇.循环式活性污泥法的优化设计及应用[J].中国给水排水,2006,22(2)：52-55.
[125]熊红权,李文彬CASS工艺在国内的应用现状[J].中国给水排水,2003,19(2)：34-35.
[126]刘丹Visual C++从入门到精通(第2版)[M].北京：化学工业出版社,2011.
[127]王浩,马玉军,陈连山,等Visual Basic从入门到精通(第2版)[M].北京：化学工业出版社,2011.
[128]曾全,崔勇彬,何晓媛.中文版AutoCAD 2010新手到高手之路[M].北京：电子工业出版社,2010.
[129]高成慧,李燕.关于AutoCAD二次开发工具的探讨[J].现代计算机,2002,(2)：31-33.
[130]张良均,韦永乐.用VBA开发工程勘察CAD绘图系统[J].广西工学院学报,2001,12(1)56-59.
[131]黄亚平,周一飞AutoCAD二次开发[J].微机发展,2003,13(3)：84-87.
[132]马伏波.用VBA开发在AutoCAD中实现参数化绘图的系统[J].机床与液压,2004(1)：95-96.
[133]秦永乐,江新清.基于数据库应用的AutoCAD二次开发的教学思考[J].武汉电力职业技术学院学报,2010,8(3)：26-28.
[134]董袁泉.基于VBA和ActiveX的AutoCAD二次开发[J].沙洲职业工学院学报,2010,13(1)：14-18.
[135]席世亮.运用ObjectARX进行AutoCAD二次开发实例[J].工程建设与设计,2010,11：88-91.
[136]陈文峰,刘祚秋,钟志辉,等AutoCAD二次开发在工程计算软件中的应用[J].科学技术与工程,2011,11(24)：5844-5848.
[137]范小鸥.用VB实现AutoCAD二次开发新探[J].吉林建筑工程学院学报,2011,28(4)：68-70.
[138]周雹,周丹,张礼文,等.活性污泥工艺的设计计算方法探讨[J].中国给水排水,2001,17(5)：45-49.
[139]白生云,李亚新CAST的工作原理与设计计算[J].山西建筑,2005,31(13)：1-3.
[140]李颖,郭爱军,赵国华CASS工艺处理高氨氮污水的脱氮设计[J].给水排水,2006,32(5)：5-8.
[141]高俊发,王社平.污水处理厂工艺设计手册[M].北京：化学工业出版社,2003.
[142]张正祥.运用VB对AutoCAD二维实体的参数化设计[J].计算机与网络,2006,3：131.
[143]张忠祥,钱宜.废水生物处理新技术[M].北京：清华大学出版社,2004.
[144]沈耀良,王宝贞.废水生物处理新技术——理论与应用(第二版)[M].北京：中国环境科学出版社,2006.
[145]北京市市政工程设计研究总院.给水排水设计手册(第5册)城镇排水[M].北京：中国建筑工业出版社,2004.
[146]区岳州,胡勇有.氧化沟污水处理技术及工程实例[M].化学工业出版社,2005.
[147]邓荣森.氧化沟污水处理理论与技术[M].北京：化学工业出版社,2006.
[148]环境保护部.HJ 578-2010氧化沟活性污泥法污水处理工程技术规范[S].2010.
[149]北京市市政工程设计研究总院.给水排水设计手册(第六册)工业排水[M].北京：中国建筑工业出版社,2002.
[150]北京市市政设计研究院.简明排水设计手册[M].北京：中国建筑工业出版社,1994.
[151]崔玉川,刘振江,张绍怡.城市污水厂处理设施设计计算(第2版)[M].北京：化学工业出版社,2011.
[152]国家城市给水排水工程技术研究中心.给水排水工程概预算与经济评价手册[M].北京：中国建筑工业出版社,1993.
[153]王富康,王曙光,李小平.工业废水和城市污水处理技术经济手册[M].北京：清华大学出版社,1992.
[154]余健,陈治安,杨青山,等.给水排水工程概预算与概预算[M].北京：化学工业出版社,2002.
[155]建设部标准定额研究所.市政工程投资估算指标(第四册)排水工程[M].北京：中国计划出版社,2008.
[156]李小平.用数量化理论(Ⅰ)建立工业废水处理的投资费用函数[J].中国环境科学,1987,7(5)：60-64.
[157]黄楚豫,张兰生,张天柱,等.系列设计法建立污水处理厂的费用函数[J].中国环境科学,1985,5(5)：68-72.
[158]王曙光,王富康,陆景宣.工业废水处理费用函数的建立和分析[J].城市环境与城市生态,1988,1(4)：33-39.
[159]何秉宇,阿屯古丽,白山,等.干旱区水污染控制工程费用函数研究——以新疆为例[J].干旱区地理,2001,24(1)：90-92.
[160]李俊奇,张颖夏,向璐璐,等.中小型城市污水处理厂技术经济调查与分析[J].中国给水排水,2006,22(10)：13-16.
[161]汪志祥,徐磊.城市污水处理厂工艺方案选择技术经济分析[J].工业安全与环保,2008,34(2)：23-25.
[162]刘杰,郑西来,高超.城镇污水处理厂用地、运行及建设费用研究[J].环境工程学报,2010,4(11)：2522-2526.
[163]吴惠彪,马春燕,戎静,等.印染废水污染控制投资和运行费用函数研究[J].环境科学与管理,2010,35(2)：110-114.
[164]赵斯思.Visual Basic数据库编程技术与实例[M].北京：人民邮电出版社,2004.
[2]中投顾问.2011-2015年中国污水处理行业投资分析及前景预测报告[R].2011.7.
[3]张文巧.浅谈我国城市污水处理的紧迫性[J].山西建筑,2010,36(11)：174-175.
[4]陈中颖,刘爱萍,刘永,许振成.中国城镇污水处理厂运行状况调查分析[J].环境污染与防治,2009,3l(9)：99-102.
[5]杜彬,侯宏良.我国城市污水处理面临的问题及解决对策[J].环境保护与循环经济,2011,4： 73-75.
[6]王宝贞.水污染控制工程[M].北京：高等教育出版社,1990.
[7]高廷耀,顾国维.水污染控制工程(第三版)[M].北京：高等教育出版社,2007.
[8]Henze M, Gujer W, Mino T, et al. Activated sludge models ASM1, ASM2, ASM2d and ASM3 [M]. London:IWA Publishing,2002.
[9]Gernaey K V, van Loosdrecht M C M, Henze M, et al. Activated sludge wastewater treatment plant modelling and simulation:state of the art [J]. Environmental Modelling & Software,2004,19:763-783.
[10]李峰,吴敏,杨哲.活性污泥数学模型在我国的研究进展[J].中国资源综合利用,2007,25(11)：21-23.
[11]黄明智,马邕文,万金泉等.污水处理中人工神经网络应用研究的探讨[J].环境科学与技术,2008,31(3)：131-135.
[12]苏书惠,张绍德,谭敬辉.基于支持向量机的污水处理软测量算法的研究[J].自动化与仪器仪表,2009,146(6)：6-9.
[13]宋岩,潘丰.基于SVM软测量技术的污水处理控制系统设计[J].自动化与仪表,2008,29(11)：5-7,22.
[14]赖惠鸽,朱学军,俞金寿.基于智能算法的污水处理软测量技术及其展望[J].化工自动化与仪表,201l,3：241-244.
[15]Ye H T, Luo F, Xu Y G. Application of RBF Network Based on Immune Algorithm to Predicting of Wastewater Treatment [J]. Lecture Notes in Computer Science,2009, 5553(3):1197-1202.
[16]Pai T Y. Gray and neural network prediction of effluent from the wastewater treatment plant of industrial park using influent quality [J]. Environ Eng Sci, 2008,25(5):757-765.
[17]郭劲松,龙腾锐,高旭,等.间歇曝气活性污泥系统神经网络水质模型[J].中国给水排水,2000,16(11)：15-18.
[18]易赛莉,雒文生.人工神经网络在UASB反应器处理生活污水中的模拟预测与应用[J].武汉大学学报(工学版),2004,37(1)：46-50.
[19]Hamed M M, Khalafallah M G, Hassanien E A. Prediction of wastewater treatment plant performance using artificial neural networks[J]. Environmental Modelling & Software,2004,19:919-928.
[20]胡坚,严敏,刘俊萍,等.径向基函数人工神经网络预测污水处理厂出水水质[J].浙江工业大学学报.2006,34(6)：633—636,
[21]朱启兵,黄敏,崔宝同.基于小波神经网络的污水处理厂出水水质预测[J].计算机工程与应用,2007,43(28)：15-17,33.
[22]Mjalli F S, Al-Asheh S, Alfadala H E. Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance [J]. Journal of Environmental Management,2007,83:329-338.
[23]Raduly B, Gernaey K V, Capodaglio A G, et al. Artificial neural networks for rapid WWTP performance evaluation:Methodology and case study[J]. Environmental Modelling & Software 2007,22:1208-1216.
[24]万金泉,黄明智,马邕文.基于模糊神经网络的工业废水处理预测研究[J].中国造纸学报,2008,23(2)：96-99.
[25]宋贤民,衷卫声.基于RS-SVM的TN软测量建模研究[J].制造业自动化,2007,29(1)：90-92.
[26]黄银蓉,张绍德MIMO最小二乘支持向量机污水处理在线软测量研究[J].自动化与仪器仪表,2010,4：15-17.
[27]张杰,张建秋,冯辉,等.支持向量机和神经网络联合软测量SBR污水处理中COD的方法[J].传感技术学报,2009,22(10)：1519-1524.
[28]Frank P M. Analytical and Qualitative Model-based Fault Diagnosis-A Survey and SomeNew Results [J]. European Journal of Control 1996,2(1):6-28.
[29]Venkatasubramanian V, Rengaswamy R, Yin K, et al. A review of process fault detection and diagnosis PartⅠ:Quantitative model-based methods [J]. Computers and Chemical Engineering,2003,27:293-311.
[30]Venkatasubramanian V, Rengaswamy R, Kavuri S N. A review of process fault detection and diagnosis Part II:Qualitative models and search strategies [J]. Computers and Chemical Engineering,2003,27:313-326.
[31]Venkatasubramanian V, Rengaswamy R, Kavuri S N. A review of process fault detection and diagnosis Part III:Process history based methods[J]. Computers and Chemical Engineering,2003,27:327-346.
[32]Lapointe J, Marcos B, Veillette M, et al. BIOEXPERT-An Expert System for Wastewater Treatment Process Diagnosis [J] Computers and Chemical Engineering, 1989,13(6):619-630.
[33]Barnett M W. Expert systems for anaerobic digestion process operation [J]. Journal of Environmental Engineering,1992,118(6):949-963.
[34]Genovesi A, Harmand J, Steyer J-P. A fuzzy logic based diagnosis system for the on-line supervision of an anaerobic digestor pilot-plant [J]. Biochemical Engineering Journal,1999,3:171-183.
[35]Carrasco E F, Rodriguez J, Punal A, et al. Rule-based diagnosis and supervision of a pilotscale wastewater treatment plant using fuzzy logic techniques. Expert Systems with Applications,2002,22:11-20.
[36]Comas J, Rodriguez-Roda I, Sanchez-Marre M, et al. A knowledge-based approach to the deflocculation problem:integrating on-line, off-line, and heuristic information [J]. Water Research,2003,37:2377-2387.
[37]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.
[38]郑上闽,孙进生.污水处理工艺系统的故障诊断专家系统[J].河北理工学院学,2001,23(3)：42-47.
[39]彭芳,黄大贵.用C++Builder开发污水处理故障诊断专家数据库系统[J].中国测试技术,2004,4(30)：81-83.
[40]李振宇,杨昌柱.污水生物处理故障诊断专家咨询系统[J].化学与生物工程,2005,3：39-41.
[41]曹晓莉,江朝元,甘思源.基于聚类支持向量机的船用污水处理装置故障诊断[J].计算机应用,2008,28(10)：2648-2651.
[42]李晓东,曾光明,蒋茹,等.改进支持向量机对污水处理厂运行状况的故障诊断[J].湖南大学学报(自然科学版),2007,34(12)：68-71.
[43]徐丽婕,王志强,施汉昌.污水处理厂全程模型化的软件选择[J].中国给水排水,2004,20(5)：21-23.
[44]郭亚萍,陈士才,张宇坤,等.ASMs仿真软件在污水处理厂中的应用[J].中国给水排水,2010,26(14)：23-29.
[45]葛守飞,濮文虹,李振宇,等.污水处理工艺选择决策支持系统的开发与应用[J].工业用水与废水,2005,36(5)：4-7.
[46]朱文斌,任洪强,魏翔.工业废水处理工艺设计专家系统的设计和实现[J].工业用水与废水,2007,38(4)：62-65.
[47]Olden J D, Jackson D A. Illuminating the "black box":a randomization approach for understanding variable contributions in artificial neural networks [J]. Ecological Modelling,2002,154(1):135-150.
[48]Gevrey M, Dimopoulos I, Lek S. Review and comparison of methods to study the contribution of variables in artificial neural network models [J]. Ecological Modelling,2003,160(2):249-264.
[49]Kemp S J, Zaradic P, Hansen F. An approach for determining relative input parameter importance and significance inartificial neural networks [J]. Ecological modeling, 2007,204:326-334.
[50]张德丰MATLAB神经网络应用设计[M].北京：机械工业出版社,2008.
[51]金峤,方帅,阎石,等.BP网络模型的改进方法综述[J].沈阳建筑工程学院学报(自然科学版),2001,17(3)：197-199.
[52]鲁娟娟,陈红.BP神经网络的研究进展[J].控制工程,2006,13(5)：449-451.
[53]余本国.BP神经网络局限性及其改进的研究[J].山西农业大学学报,2009,29(1)：89-93.
[54]张国翊,胡铮.改进BP神经网络模型及其稳定性分析[J].中南大学学报(自然科学版),2011,42(1)：115-124.
[55]张庆庆,贺兴时.BP神经网络结点数选取的改进方法及其应用[J].西安工程大学学报,2008,22(4)：502-505.
[56]范佳妮,王振雷,钱锋.BP人工神经网络隐层结构设计的研究进展[J].控制工程,2005,12(S0)：105-109.
[57]张德贤.前向神经网络合理隐含层结点个数估计[J].计算机工程与应用,2005,5：21-24.
[58]蔡兵.BP神经网络隐层结构的设计方法[J].通化师范学院学报,2007,28(2)：18-19.
[59]Huisken M, Jin Y, Sendhoff B. Structure optimization of neural networks for evolutionary design optimization. Soft Computing 2005,9:21-28.
[60]张立明.人工神经网络的模型及其应用[M].上海：复旦大学出版社.1993.
[61]袁曾任.人工神经元网络及其应用[M].北京：清华大学出版社,1999.
[62]戚德虎,康继昌.BP神经网络的设计[J].计算机工程与设计.1998,19(2)：48-50.
[63]高大启.线性基本函数前向三层神经网络结构研究[J].计算机学报,1998,21(1)：80-85.
[64]周红晓,蔡俊,张德官.一种优化多层前馈神经网络中隐节点数的算法[J].浙江师范大学(自然科学版),2002,25(3)：268-271.
[65]MezardM, Nadal J-P. Learning in feedforward layered networks:the tiling algorithm [J]. J. Phys. A:Math. Gen.22 (1989) 2191-2203.
[66]Fahlman S E, Lebiere C. The Cascade-Correlation Learning Architecture [C]// Advances in Neural Information Processing Systems 2, Touretzky D S. (ed.), Morgan-Kaufmann, Los Altos CA,1990.
[67]Littmann E, Ritter H. Generalization Abilities of Cascade Network Architecture [C]//Proceedings of NIPS.1992:188-195.
[68]叶东毅.前馈神经网络隐层结点设计的一个学习算法[J].电子学报,1997,25(11)：126-128.
[69]赵林明,魏德华.优选人工神经网络隐层神经元数目的方法[J].华北水利水电学院学报,1999,20(4)：44-48.
[70]Lee H J, Park H, Lee Y. Network Optimization through Learning and Pruning in Neuromanifold [J]. Lecture Notes in Computer Science,2002,24(17):169-177.
[71]Henderson C E, Potter W D, McClendon R W, Hoogenboom G. Predicting aflatoxin contamination in peanuts:A genetic algorithm/neural network approach [J]. Applied Intelligence 2000,12:183-192.
[72]李智勇,童调生.基于多物种进化遗传算法的神经网络结构学习方法[J].计算机工程及应用,2003,22(8)：87-90.
[73]朱海燕,朱晓莲,黄螟.基于动态BP神经网络的预测方法及其应用[J].计算机与信息技术.2007,Z1：3-6.
[74]吴永明,吴晟.改进的遗传算法在神经网络结构优化中的应用[J].微型机与应用.2011,30(3)：79-81.
[75]杨伟,倪黔东,吴军基.BP神经网络权值初始值与收敛性问题研究[J].电力系统及其自动化学报,2002,14(1)：20-22.
[76]谢富强,唐耀庚.多层前向神经网络权值初始化的研究进展[J].南华大学学报(自然科学版),2006,20(3)：98-101.
[77]武妍,王守觉.权值初始化与激励函数调整相结合的学习算法[J].计算机工程与应用,2004(30)：23-26.
[78]蒋蓉蓉.一种基于遗传算法的BP网络改进方法[J].微计算机信息,2007,23(11)：234-236.
[79]王静伟.BP神经网络改进算法的研究[J].中国水运,2008,8(1)：157-158.
[80]覃光华,王顺久,缪韧.基于卡尔曼滤波技术的人工神经网络权重估算及应用[J].四川大学学报：自然科学版,2008,25(4)：25-28.
[81]李翱翔,陈健.BP神经网络参数改进方法综述[J].数字通信世界,2009,(1)：62-64.
[82]潘吴,钟珞,陈杰.BP神经网络训练的函数变步长搜索调整法[J].湖北工学院学报,1997,12(2)：1-4.
[83]许廷发,张敏,顾海军,等.改进的BP算法在多目标识别中的应用[J].光学精密程,2003,11(5)：513-515.
[84]候彦东,方惠敏,杨国胜,等.一种改进的可变学习速率的BP神经网络算法[J].河南大学学报(自然科学版),2008,38(3)：309-312.
[85]武妍,张立明.神经网络的泛化能力与结构优化算法研究[J].计算机应用研究,2002,6：21-25.
[86]王恺,杨巨峰,王立,等.人工神经网络泛化问题研究综述[J].计算机应用研究,2008,25(12)：3525-3533.
[87]周志华,陈世福.神经网络规则抽取[J].计算机研究与发展,2002,39(4)：398-405.
[88]胡包钢,王泳,杨双红,曲寒冰.如何增加人工神经元网络的透明度?[J].模式识别与人工智能,2007,20(1)：72-84.
[89]Ozesmi S L, Ozesmi U. An artificial neural network approach to spatial habitat modeling with interspecific interaction [J]. Ecol. Model.1999,116,15-31.
[90]Tzeng F Y, Ma K L. Opening the black box-data driven visualization of neural networks[C]. In:Proceedings of IEEE Visualization'05 Conference.2005,383-390.
[91]Weckman G R, Millie D F, Ganduri C, Rangwala M, Young W, Rinder M, Fahnenstiel GL. Knowledge Extraction from the Neural'Black Box'in Ecological Monitoring [J]. Journal of Industrial and Systems Engineering,2009,3(1):38-55.
[92]Garson G D. Interpreting neural network connection weights [J]. Artificial Intelligence Expert 1991,6(4):47-51.
[93]Towell G G, Shavlik J W. Extracting Refined Rules from Knowledge Based Neural Networks[J]. Machine Learning,1993,13(1):71-101.
[94]Setiono R. Extracting Rules from Neural Networks by Pruning and Hidden-Unit Splitting[J]. Neural Computation,1997,9(1):205-225.
[95]Setiono R, Leow W K. FERNN:An algorithm for Fast Extraction of Rules from Neural Networks[J]. Applied Intelligence,2000,12(1-2):15-25.
[96]Craven M, Shavlik J. Using Sampling and Queries to Extract Rules from Trained Neural Networks[C] In Proceeding of the Eleventh International Conference on Machine Learning,1994,37-45.
[97]陈清后.影响生物脱氮除磷的因素[J].污染防治技术,2007,20(1)：41-42.
[98]Vapnik V N. The Nature of Statistical Learning Theory [M]. New York:Springer-Verlag, 1995.
[99]Ivanciuc 0. Applications of Support Vector Machines in Chemistry. In:Reviews in Computational Chemistry, Volume 23, Eds.:Lipkowitz K. B. and Cundari T. R. Wiley-VCH, Weinheim,2007, pp.291-400.
[100]Mattera D, Haykin S. Support Vector Machines for Dynamic Reconstruction of a Chaotic System [M] In Advances in Kernel Methods-Support Vector Learning. Scholkopf B, Burges CJC, Smola AJ. (Eds.) Cambridge, MA:MIT Press.1999. ISBN 0-262-19416-3.
[101]Cherkassky V, Ma YQ. Practical Selection of SVM Parameters and Noise Estimation for SVM Regression [J]. Neural Networks,2004,17(1):113-126.
[102]Kwok JT, Tsang IW. Linear Dependency between Epsilon and the Input Noise in Epsilon-Support Vector Regression [J]. IEEE Trans. Neural Networks,2003,14(3): 544-553.
[103]Chalimourda A, Scholkopf B, Smola AJ. Experimentally Optimal v in Support Vector Regression for Different Noise Models and Parameter Settings [J]. Neural Networks, 2004,17(1):127-141.
[104]王鹏,朱小燕.基于RBF核的SVM的模型选择及其应用[J].计算机工程与应用,2003,39(24)：72-73.
[105]刘靖旭,蔡怀平,谭跃进.支持向量回归参数调整的一种启发式算法[J].系统仿真学报.2007,19(7)：1540-1547.
[106]Chan YJ, Chong MF, Law CL, et al. A review on anaerobic-aerobic treatment of industrial and municipal wastewater[J]. Chemical Engineering Journal,2009, 155(1-2):1-18.
[107]Ahn YT, Kang ST, Chae SR, et al. Simultaneous high-strength organic and nitrogen removal with combined anaerobic upflow bed filter and aerobic membrane bioreactor [J]. Desalination 2007,202:114-121.
[108]Bodik I, Kratochvil K, Gasparikovd E, et al. Nitrogen removal in an anaerobic baffled filter reactor with aerobic post-treatment [J]. Bioresource Technology 2003,86:79-84.
[109]Tartakovsky B, Manuel MF, Guiot SR. Degradation of trichloroethylene in a coupled anaerobic-aerobic bioreactor:Modeling and experiment [J]. Biochemical Engineering Journal 2005,26:72-81.
[110]Wang RM, Wang Y, Ma GP, et al. Efficiency of porous burnt-coke carrier on treatment of potato starch wastewater with an anaerobic-aerobic bioreactor [J]. Chemical Engineering Journal 2009,148:35-40.
[111]周集体,童健,王栋,等.垂直折流生化反应器污水厌氧一好氧串联处理工艺：中国,CNl289730[P].2001.
[112]王冠一,周集体VTBR反应器对对石油炼制废水的生物脱氮研究[J].西安公路交通大学学报,199919(S)：94-96.
[113]周集体,曹同川,杨桦,等.新乡白鹭化纤集团棉浆黑液废水处理工程设计[J].环境工程,2002,20(1)：22-23.
[114]田博VTBR反应器加微电解工艺处理生活污水[J].辽宁化工,2004,33(3)：170-171.
[115]周涛,周集体.垂直折流反应器一超滤膜水处理技术的实验研究[J].工业水处理,2002,22(3)：23-25.
[116]姜素君,毕岩松VTBR生化处理污水技术在锦州港的应用[J].水运工程,2003,356(9)：39-41.
[117]付咭VTBR生化反应器+ME微电解工艺在生活污水处理及回用工程中的应用[J].辽宁城乡环境科技,2004,24(2)：31-33.
[118]周集体,邢礼娜,张劲松.多级A/0 VTBR组合工艺处理焦化废水[J].环境工程,2010,28(3)：26-29.
[119]杨松林.水处理工程CAD技术应用及实例[M].北京：化学工业出版社,2002.
[120]杨松林,秦乐乐.环境工程CAD技术应用及实例[M].北京：化学工业出版社,2004.
[121]陈扬,李硕文,同帜.水处理工程计算机辅助设计[J].西北纺织工学院学报,1997,11(2)：169-171.
[122]罗程亮,张明泉,桑学峰.用Visual Basic语言实现污水处理平流式沉淀池的计算机辅助设计[J].甘肃科技,2005,21(2)：44-47.
[123]沈耀良,王宝贞.循环活性污泥系统(CASS)处理城市废水[J].给水排水,1999,25(11)：10-13.
[124]张胜华,宋丰明,孙勇.循环式活性污泥法的优化设计及应用[J].中国给水排水,2006,22(2)：52-55.
[125]熊红权,李文彬CASS工艺在国内的应用现状[J].中国给水排水,2003,19(2)：34-35.
[126]刘丹Visual C++从入门到精通(第2版)[M].北京：化学工业出版社,2011.
[127]王浩,马玉军,陈连山,等Visual Basic从入门到精通(第2版)[M].北京：化学工业出版社,2011.
[128]曾全,崔勇彬,何晓媛.中文版AutoCAD 2010新手到高手之路[M].北京：电子工业出版社,2010.
[129]高成慧,李燕.关于AutoCAD二次开发工具的探讨[J].现代计算机,2002,(2)：31-33.
[130]张良均,韦永乐.用VBA开发工程勘察CAD绘图系统[J].广西工学院学报,2001,12(1)56-59.
[131]黄亚平,周一飞AutoCAD二次开发[J].微机发展,2003,13(3)：84-87.
[132]马伏波.用VBA开发在AutoCAD中实现参数化绘图的系统[J].机床与液压,2004(1)：95-96.
[133]秦永乐,江新清.基于数据库应用的AutoCAD二次开发的教学思考[J].武汉电力职业技术学院学报,2010,8(3)：26-28.
[134]董袁泉.基于VBA和ActiveX的AutoCAD二次开发[J].沙洲职业工学院学报,2010,13(1)：14-18.
[135]席世亮.运用ObjectARX进行AutoCAD二次开发实例[J].工程建设与设计,2010,11：88-91.
[136]陈文峰,刘祚秋,钟志辉,等AutoCAD二次开发在工程计算软件中的应用[J].科学技术与工程,2011,11(24)：5844-5848.
[137]范小鸥.用VB实现AutoCAD二次开发新探[J].吉林建筑工程学院学报,2011,28(4)：68-70.
[138]周雹,周丹,张礼文,等.活性污泥工艺的设计计算方法探讨[J].中国给水排水,2001,17(5)：45-49.
[139]白生云,李亚新CAST的工作原理与设计计算[J].山西建筑,2005,31(13)：1-3.
[140]李颖,郭爱军,赵国华CASS工艺处理高氨氮污水的脱氮设计[J].给水排水,2006,32(5)：5-8.
[141]高俊发,王社平.污水处理厂工艺设计手册[M].北京：化学工业出版社,2003.
[142]张正祥.运用VB对AutoCAD二维实体的参数化设计[J].计算机与网络,2006,3：131.
[143]张忠祥,钱宜.废水生物处理新技术[M].北京：清华大学出版社,2004.
[144]沈耀良,王宝贞.废水生物处理新技术——理论与应用(第二版)[M].北京：中国环境科学出版社,2006.
[145]北京市市政工程设计研究总院.给水排水设计手册(第5册)城镇排水[M].北京：中国建筑工业出版社,2004.
[146]区岳州,胡勇有.氧化沟污水处理技术及工程实例[M].化学工业出版社,2005.
[147]邓荣森.氧化沟污水处理理论与技术[M].北京：化学工业出版社,2006.
[148]环境保护部.HJ 578-2010氧化沟活性污泥法污水处理工程技术规范[S].2010.
[149]北京市市政工程设计研究总院.给水排水设计手册(第六册)工业排水[M].北京：中国建筑工业出版社,2002.
[150]北京市市政设计研究院.简明排水设计手册[M].北京：中国建筑工业出版社,1994.
[151]崔玉川,刘振江,张绍怡.城市污水厂处理设施设计计算(第2版)[M].北京：化学工业出版社,2011.
[152]国家城市给水排水工程技术研究中心.给水排水工程概预算与经济评价手册[M].北京：中国建筑工业出版社,1993.
[153]王富康,王曙光,李小平.工业废水和城市污水处理技术经济手册[M].北京：清华大学出版社,1992.
[154]余健,陈治安,杨青山,等.给水排水工程概预算与概预算[M].北京：化学工业出版社,2002.
[155]建设部标准定额研究所.市政工程投资估算指标(第四册)排水工程[M].北京：中国计划出版社,2008.
[156]李小平.用数量化理论(Ⅰ)建立工业废水处理的投资费用函数[J].中国环境科学,1987,7(5)：60-64.
[157]黄楚豫,张兰生,张天柱,等.系列设计法建立污水处理厂的费用函数[J].中国环境科学,1985,5(5)：68-72.
[158]王曙光,王富康,陆景宣.工业废水处理费用函数的建立和分析[J].城市环境与城市生态,1988,1(4)：33-39.
[159]何秉宇,阿屯古丽,白山,等.干旱区水污染控制工程费用函数研究——以新疆为例[J].干旱区地理,2001,24(1)：90-92.
[160]李俊奇,张颖夏,向璐璐,等.中小型城市污水处理厂技术经济调查与分析[J].中国给水排水,2006,22(10)：13-16.
[161]汪志祥,徐磊.城市污水处理厂工艺方案选择技术经济分析[J].工业安全与环保,2008,34(2)：23-25.
[162]刘杰,郑西来,高超.城镇污水处理厂用地、运行及建设费用研究[J].环境工程学报,2010,4(11)：2522-2526.
[163]吴惠彪,马春燕,戎静,等.印染废水污染控制投资和运行费用函数研究[J].环境科学与管理,2010,35(2)：110-114.
[164]赵斯思.Visual Basic数据库编程技术与实例[M].北京：人民邮电出版社,2004.