Prediction of water quality parameters using Artificial Neural Network & Hybrid model
Predicting the plant water quality parameters using conventional experimental techniques is a timeconsuming step and is also an obstacle in the way of efficient control of such processes. In this work，artificialneural network (ANN)and ANN&PCA (principal component analysis)hybrid model were used in order todevelop a model that was able to predict the water quality parameters，such as BOD，COD,SS，TN，TP. Here thefeed-forward back-propagation neural network (FBNN)model was chosen to model the wastewater treatmentplant，which is the South Vastewater Treatment Plant (WWTP)at Korea，Busan City. The tan-sigmoid functionwas used as activation function to transfer signal at the neural network. And the Levenberg-Marquart algorithmwas used as learning algorithm to train neural network. All the 357 data sets，which were collected from the plantduring 2005，divided into 200 data sets and other 157 data sets，were used for model training and validation,respectively. The ANN and the hybrid models for prediction of water quality parameters in the primary settlementtank (PST)effluent and secondary settlement tank (SST)effluent are presented here。
Artificial Neural Network Principal Component Analysis Wastewater Treatment Plant
ZhaoYongna
Department of Environmental Engineering, Pukyong National University, Korea
国内会议
全国水体污染控制、生态修复技术与水环境保护的生态补偿建设交流研讨会
上海
英文
34-36
2008-04-25（万方平台首次上网日期，不代表论文的发表时间）