基于改进BP神经网络的中药水提液陶瓷膜污染预测研究
|
摘要
目的为防治中药水提液陶瓷膜纯化过程中的膜污染问题,探索预测污染度的新方法。方法对BP神经网络模型进行改进,利用隐含层最佳神经元数目的快速确定方法、BP神经网络权值和阈值的快速寻优算法,建立中药水提液陶瓷膜污染预测模型,对207组中药水提液数据进行网络训练和预测。结果与多元回归分析、基本BP神经网络、RBF神经网络等模型相比,应用改进BP神经网络模型进行预测实验的拟合误差更小,均方误差仅为0.005 7;此外,改进BP神经网络模型的性能更加稳定,在20次随机运行实验中达到预设目标的成功率高达95%。结论改进模型具有很好的网络性能、拟合效果和预测能力,能够稳定准确地预测膜污染度。
Objective To prevent and treat of ceramic membrane purification of membrane fouling process of TCM extracts; To explore new methods of forecasting membrane fouling degree. Methods BP neural network model was improved. Methods to fast determine the optimal number of neurons in the hidden layer and fast algorithm for optimizing the weight and threshold of BP neural network were studied. Data of 207 groups of TCM extracts were under network training and prediction. Results Compared with the models of multiple regression analysis, basic BP neural network and RBF neural network, the error of the improved BP neural network model was less than that of the BP neural network model, and the mean square error was only 0.005 7. In addition, the improved BP neural network model performance was more stable. In the 20 random running experiments, the goal of the success rate achieved up to 95%. Conclusion The improved model has a good network performance, the fitting effect and prediction ability, and can forecast the fouling degree of membrane stably and accurately.
Objective To prevent and treat of ceramic membrane purification of membrane fouling process of TCM extracts; To explore new methods of forecasting membrane fouling degree. Methods BP neural network model was improved. Methods to fast determine the optimal number of neurons in the hidden layer and fast algorithm for optimizing the weight and threshold of BP neural network were studied. Data of 207 groups of TCM extracts were under network training and prediction. Results Compared with the models of multiple regression analysis, basic BP neural network and RBF neural network, the error of the improved BP neural network model was less than that of the BP neural network model, and the mean square error was only 0.005 7. In addition, the improved BP neural network model performance was more stable. In the 20 random running experiments, the goal of the success rate achieved up to 95%. Conclusion The improved model has a good network performance, the fitting effect and prediction ability, and can forecast the fouling degree of membrane stably and accurately.
引文
[1]SISKENS C A M.Fundamental of inorganic membrane science and technology[M].Holland:Elsevier Science B V,1996:619-639.
[2]刘忠洲,续曙光,李锁定.微滤超滤过程中的膜污染与清洗[J].水处理技术,1997(4):3-9.
[3]樊文玲,郭立玮,林瑛.不同预处理方法对陶瓷膜澄清中药水提液过程的影响研究[J].中成药,2008,30(11):1709-1710.
[4]贺立中.药液超滤过程中的膜污染及其防治[J].膜科学与技术,2000,20(5):49-54.
[5]刘春艳,凌建春,寇林元,等.GA-BP神经网络与BP神经网络性能比较[J].中国卫生统计,2013,30(2):173-176.
[6]HOLLAND J H.Adaptation in natural and artificial systems:an introductory analysis with applications to biology,control,and artificial intelligence[M].Cambridge:MIT Press,1992:89.
[7]王元章,吴春华,周笛青,等.基于BP神经网络的光伏阵列故障诊断研究[J].电力系统保护与控制,2013(16):108-114.
[8]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.
[9]郝晓弘,段晓燕,李恒杰.基于BP神经网络的迭代学习初始控制策略研究[J].计算机应用,2009,29(4):1025-1027,1031.
[10]夏玫,陈立潮,王新波.一种提高BP神经网络泛化能力的改进算法[J].计算机技术与发展,2009,19(9):62-64,68.
[11]CHEN T,CHEN H,LIU R W.Approximation capability in C(Rn)by multilayer feedforward networks and related problems[J].IEEE Transactions on Neural Network,1995,6(1):25-30
[12]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(S1):109-113.
[13]沈花玉,王兆霞,高成耀,等.BP神经网络隐含层单元数的确定[J].天津理工大学学报,2008,24(5):13-15.
[14]褚辉,赖惠成.一种改进的BP神经网络算法及其应用[J].计算机仿真,2007,24(4):75-77.
[15]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.
[16]张雨浓,李巍,蔡炳煌,等.切比雪夫正交基神经网络的权值直接确定法[J].计算机仿真,2009,26(1):157-161.
[17]范青武,王普,高学金.一种基于有向交叉的遗传算法[J].控制与决策,2009,24(4):542-546.
[18]庄健,杨清宇,杜海峰,等.一种高效的复杂系统遗传算法[J].软件学报,2010,21(11):2790-2801.
[19]洪弘.数据挖掘技术在中药水提液膜分离中的应用研究[D].南京:南京中医药大学,2012.
[20]郭立玮,付廷明,李玲娟.面向中药复杂体系的陶瓷膜污染机理研究思路与方法[J].膜科学与技术,2009,29(1):1-7.
[21]李玲娟,郭立玮.基于特征提取的中药水提液膜分离预测系统[J].计算机工程与设计,2010,31(9):2023-2026.
[2]刘忠洲,续曙光,李锁定.微滤超滤过程中的膜污染与清洗[J].水处理技术,1997(4):3-9.
[3]樊文玲,郭立玮,林瑛.不同预处理方法对陶瓷膜澄清中药水提液过程的影响研究[J].中成药,2008,30(11):1709-1710.
[4]贺立中.药液超滤过程中的膜污染及其防治[J].膜科学与技术,2000,20(5):49-54.
[5]刘春艳,凌建春,寇林元,等.GA-BP神经网络与BP神经网络性能比较[J].中国卫生统计,2013,30(2):173-176.
[6]HOLLAND J H.Adaptation in natural and artificial systems:an introductory analysis with applications to biology,control,and artificial intelligence[M].Cambridge:MIT Press,1992:89.
[7]王元章,吴春华,周笛青,等.基于BP神经网络的光伏阵列故障诊断研究[J].电力系统保护与控制,2013(16):108-114.
[8]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.
[9]郝晓弘,段晓燕,李恒杰.基于BP神经网络的迭代学习初始控制策略研究[J].计算机应用,2009,29(4):1025-1027,1031.
[10]夏玫,陈立潮,王新波.一种提高BP神经网络泛化能力的改进算法[J].计算机技术与发展,2009,19(9):62-64,68.
[11]CHEN T,CHEN H,LIU R W.Approximation capability in C(Rn)by multilayer feedforward networks and related problems[J].IEEE Transactions on Neural Network,1995,6(1):25-30
[12]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(S1):109-113.
[13]沈花玉,王兆霞,高成耀,等.BP神经网络隐含层单元数的确定[J].天津理工大学学报,2008,24(5):13-15.
[14]褚辉,赖惠成.一种改进的BP神经网络算法及其应用[J].计算机仿真,2007,24(4):75-77.
[15]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.
[16]张雨浓,李巍,蔡炳煌,等.切比雪夫正交基神经网络的权值直接确定法[J].计算机仿真,2009,26(1):157-161.
[17]范青武,王普,高学金.一种基于有向交叉的遗传算法[J].控制与决策,2009,24(4):542-546.
[18]庄健,杨清宇,杜海峰,等.一种高效的复杂系统遗传算法[J].软件学报,2010,21(11):2790-2801.
[19]洪弘.数据挖掘技术在中药水提液膜分离中的应用研究[D].南京:南京中医药大学,2012.
[20]郭立玮,付廷明,李玲娟.面向中药复杂体系的陶瓷膜污染机理研究思路与方法[J].膜科学与技术,2009,29(1):1-7.
[21]李玲娟,郭立玮.基于特征提取的中药水提液膜分离预测系统[J].计算机工程与设计,2010,31(9):2023-2026.