| CAST工艺的BP和RBF人工神经网络仿真模型 |
| |
| 引用本文： | 刘俊萍,严敏,胡坚.CAST工艺的BP和RBF人工神经网络仿真模型[J].中国给水排水,2009,25(21). |
| |
| 作者姓名： | 刘俊萍 严敏 胡坚 |
| |
| 作者单位： | 1. 浙江工业大学,建筑工程学院,浙江,杭州,310032
2. 镇江水工业公司,排水管理处,江苏,镇江,212003 |
| |
| 基金项目： | 国家水体污染控制与治理科技重大项目 |
| |
| 摘 要： | 将误差反向传播前馈(BP)神经网络模型和径向基函数(RBF)神经网络模型应用到CAST工艺中,并采用多输入、双输出神经网络模拟处理过程中各变量之间的关系和预测出水水质.误差分析结果表明,训练阶段RBF神经网络模型的拟合精度比BP神经网络模型的高,但两者的预测精度相差不大;测试阶段BP神经网络模型和RBF神经网络模型预测出水COD的平均相对误差分别为6.35%、6.80%,预测出水TN的平均相对误差分别为7.19%、5.49%,均在8%以下,这说明两种神经网络模型均可用于模拟CAST污水处理工艺各变量之间的关系和预测出水水质,为污水厂的运行管理提供了理论依据.
|
| 关 键 词： | CAST工艺 BP人工神经网络 RBF人工神经网络 出水水质 预测 |
BP and RBF Neural Network Simulation Models for CAST Process |
| |
| LIU Jun-ping,YAN Min,HU Jian.BP and RBF Neural Network Simulation Models for CAST Process[J].China Water & Wastewater,2009,25(21). |
| |
| Authors: | LIU Jun-ping YAN Min HU Jian |
| |
| Affiliation: | LIU Jun-ping1,YAN Min1,HU Jian2(1.College of Civil Engineering and Architecture,Zhejiang University of Technology,Hangzhou 310032,China,2.Division of Sewerage Management,Zhenjiang Water Industry Company,Zhenjiang 212003,China) |
| |
| Abstract: | Cyclic activated sludge technology(CAST) was simulated using back propagation(BP) and radial basis function(RBF) neural network models,and the multiple input and dual-output neural networks were used to simulate the relationship between every variable in the treatment process and to predict the effluent quality.The error analysis shows that the fitting precision of RBF neural network model is higher than that of BP neural network model in the training phase,but their prediction accuracy is more or less the ... |
| |
| Keywords: | CAST process BP neural network RBF neural network effluent quality prediction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
