基于神经网络的MBR仿真预测的研究
|
摘要
该文在分析MBR膜污染形成机制、膜污染影响因素的基础上,首先利用主元分析法对影响膜污染的各种参数实现输入变量的降维和去相关,求出影响膜污染最为明显的三大因素:混合液悬浮固体(MLSS)、总阻力和操作压力(TMP),进而运用BP和RBF人工神经网络建立了这三大参数与表征膜污染程度大小的膜通量之间关系的MBR智能仿真系统模型,并分析了两种神经网络模型对MBR污水处理膜污染过程的适应能力。实验结果表明:l)神经网络模型可以准确地反映出实际情况,具有很好的自适应能力;2)PCA-RBF神经网络模型的收敛精度高而且速度快于PCA-BP神经网络模型。
In this paper,based on the analysis of the MBR membrane fouling formation mechanism and the impact factors of membrane fouling,first of all,authors used principal component analysis on various parameters affecting the membrane fouling to achieve dimensionali ty reduction and decorrelation of the input variables and obtain the most obvious three factors affecting membrane fouling: the mixed li quor suspended solids(MLSS),the total resistance and the operating pressure(TMP),second,established the MBR intelligent simulation system model reflecting the relationship between the three parameters and the membrane flux characterizing the size of the extent of mem brane fouling with BP and RBF neural network,and then analyzed the adaptability of the two neural network models with MBR wastewa ter treatment membrane fouling process.The experimental results show: l) the neural network model can accurately reflect the actual situa tion,with a good adaptive capacity;2) the convergence precision and the approximation rate of the RBF neural network model are better than BP neural network model.
In this paper,based on the analysis of the MBR membrane fouling formation mechanism and the impact factors of membrane fouling,first of all,authors used principal component analysis on various parameters affecting the membrane fouling to achieve dimensionali ty reduction and decorrelation of the input variables and obtain the most obvious three factors affecting membrane fouling: the mixed li quor suspended solids(MLSS),the total resistance and the operating pressure(TMP),second,established the MBR intelligent simulation system model reflecting the relationship between the three parameters and the membrane flux characterizing the size of the extent of mem brane fouling with BP and RBF neural network,and then analyzed the adaptability of the two neural network models with MBR wastewa ter treatment membrane fouling process.The experimental results show: l) the neural network model can accurately reflect the actual situa tion,with a good adaptive capacity;2) the convergence precision and the approximation rate of the RBF neural network model are better than BP neural network model.
引文
[1]张燕,膜生物反应器处理印染污水及膜污染的研究[D].西安:西安工程科技学院,2003.
[2]高宏宇.不确定系统的神经网络控制研究[D].黑龙江:大庆石油学院,2006.
[3]余颖.基于神经网络的污水处理过程建模的研究[C].第五届全球智能控制与自动化大会会议论文集,Hangzhou,P.R.China,2004.
[4]张健,等.基于组合不变矩与神经网络的卫星目标识[J].海军航空工程学院学报,2008,23(1):29-32.
[5]迟明杰,SBR法污水处理过程建模与控制技术研究[D].济南:山东轻工业学院,2010.
[6]毛宗武,基于试验模型的MBR三维仿真系统的研究[D].天津:天津工业大学,2011.
[7]Wang Weibin,Zheng Pie,Li Jinyong.Application of BP-NN and RBF-NN in Modeling Activated Sludge System[J].Transaction of TianjinUniversity,2003,3(9):235-240.
[8]王米娜.电子鼻动态特征信息处理方法研究[D].西北工业大学,2005.
[9]熊煜,邵慧娟.地震数据处理中基于RBF网络的函数逼近[J].计算机仿真,2005(07).
[10]田丽.基于小波神经网络的语音识别的研究[D].大庆:大庆石油学院,2005.
[11]贺清碧.BP神经网络及应用研究[D].重庆:重庆交通学院,2007.
[12]刘臣辉,吕信红,范海燕.主成分分析法用于环境质量评价的探讨[J].环境科学与管理,2011,36(3):183-186.
[13]沈悦啸,王利政.膜生物反应器的最新研究进展[J].中国给水排水,2010(12).
[14]马艳芳,周冰.RBF神经网络的研究与应用[J].电脑知识与技术,2009(25).
[2]高宏宇.不确定系统的神经网络控制研究[D].黑龙江:大庆石油学院,2006.
[3]余颖.基于神经网络的污水处理过程建模的研究[C].第五届全球智能控制与自动化大会会议论文集,Hangzhou,P.R.China,2004.
[4]张健,等.基于组合不变矩与神经网络的卫星目标识[J].海军航空工程学院学报,2008,23(1):29-32.
[5]迟明杰,SBR法污水处理过程建模与控制技术研究[D].济南:山东轻工业学院,2010.
[6]毛宗武,基于试验模型的MBR三维仿真系统的研究[D].天津:天津工业大学,2011.
[7]Wang Weibin,Zheng Pie,Li Jinyong.Application of BP-NN and RBF-NN in Modeling Activated Sludge System[J].Transaction of TianjinUniversity,2003,3(9):235-240.
[8]王米娜.电子鼻动态特征信息处理方法研究[D].西北工业大学,2005.
[9]熊煜,邵慧娟.地震数据处理中基于RBF网络的函数逼近[J].计算机仿真,2005(07).
[10]田丽.基于小波神经网络的语音识别的研究[D].大庆:大庆石油学院,2005.
[11]贺清碧.BP神经网络及应用研究[D].重庆:重庆交通学院,2007.
[12]刘臣辉,吕信红,范海燕.主成分分析法用于环境质量评价的探讨[J].环境科学与管理,2011,36(3):183-186.
[13]沈悦啸,王利政.膜生物反应器的最新研究进展[J].中国给水排水,2010(12).
[14]马艳芳,周冰.RBF神经网络的研究与应用[J].电脑知识与技术,2009(25).
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心