文献类型：会议论文

英文题名：The study of soft sensor modeling method based on wavelet neural network for sewage treatment

作者：Gao, Mei-Juan[1,2];Tian, Jing-Wen[1,2];Li, Kai[2]

第一作者：Gao, Mei-Juan;高美娟

通讯作者：Gao, MJ[1]

机构：[1]Beijing Union Univ, Dept Automat Control, Beijing 100101, Peoples R China;[2]Beijing Univ Chem Technol, Sch Informat Sci, Beijing 100029, Peoples R China

第一机构：北京联合大学城市轨道交通与物流学院

通讯机构：[1]corresponding author), Beijing Union Univ, Dept Automat Control, Beijing 100101, Peoples R China.|[1141751]北京联合大学城市轨道交通与物流学院;[11417]北京联合大学;

会议论文集：5th International Conference on Wavelet Analysis and Pattern Recognition

会议日期：NOV 02-04, 2007

会议地点：Beijing, PEOPLES R CHINA

语种：英文

外文关键词：wavelet neural network; sewage treatment; soft sensor; modeling

摘要：Considering the issues that the sewage treatment process is a complicated and nonlinear system, it is very difficult to found the process model to describe it, and the key parameter of sewage treatment quality can not he detected on-line, a soft sensor Modeling method based on wavelet neural network is presented. The wavelet network structure for soft sensor of sewage treatment quality is established. We adopt a method of reduce the number of the Wavelet basic function by analysis the sparse property of sample data, the learning algorithm bayed on the gradient descent was used to train network. With the ability of strong function approach and fast convergence of wawelet network the soft sensor modeling method can truly detect and assess the quality of sewage treatment in real time by learning the sewage treatment parameter information of sensors acquired. The defection results show that this method is feasible and effective.