Title :
Soft sensor model based on improved fuzzy neural network
Author :
Jun, Wang ; Hong, Peng ; Jian, Xiao
Author_Institution :
Coll. of Electr. Eng., Southwest Jiaotong Univ., Sichuan
Abstract :
By changing the consequents of the fuzzy rules using wavelet basis function, an improved fuzzy neural network is introduced for soft sensor. In order to improve the system convergence, an efficient initialization is used by the selection of wavelet base and the orthogonal least-square (OLS) algorithm. The parameters of the model are trained by the steepest gradient decent method and least-square estimation. Finally a soft sensor model of the concentration of hydrochloric acid for a chemical plant based on the proposed method is presented which has fast convergence and prediction precision
Keywords :
chemical engineering computing; chemical industry; chemical sensors; convergence; fuzzy neural nets; gradient methods; hydrogen compounds; industrial plants; least squares approximations; wavelet transforms; chemical plant; efficient initialization; fuzzy neural network; fuzzy rules; hydrochloric acid; least-square estimation; orthogonal least-square algorithm; soft sensor model; steepest gradient decent method; system convergence; wavelet basis function; Chemical sensors; Clustering algorithms; Convergence; Educational institutions; Equations; Fuzzy neural networks; Fuzzy sets; Multiresolution analysis; Predictive models; Process control;
Conference_Titel :
Industrial Technology, 2005. ICIT 2005. IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7803-9484-4
DOI :
10.1109/ICIT.2005.1600725
