Title :
Predicting K/S Value of the Reactive Dyes Based on RBF Neural Network
Author :
Jiang, HuiYu ; Dong, Min ; Li, Wei
Author_Institution :
Inst. of Chem. & Eng., Wuhan Univ. of Sci. & Eng., Wuhan, China
Abstract :
The traditional determination method of K/S value is testing the CIEL*a*b* value of each dyeing fabric fistly by the color chromatic aberration SC-80, and then, based on the CIEL*a*b* value, they calculate the K/S value scoping 10 nm within 400 nm-700 nm the visible region. These are finished with the help of the software Hyper Choshoku-Senka TX.The RBF neural network is used in this paper to estimate the K/S value. The correlation coefficient reaches 1.000 between the estimated value and tested one. Prediction error´s biggest absolute value is 0.004, the rest is under 0.002. It shows the feasibility of the artificial neural network applied to the reactive dyes dyeing. It is a good forecast mode of K/S value of the reactive dyes.
Keywords :
aberrations; chemical engineering computing; dyes; radial basis function networks; CIEL*a*b* value; K/S value; RBF neural network; SC-80; artificial neural network; color chromatic aberration; correlation coefficient; dyeing fabric; prediction error; reactive dyes; software hyper Choshoku-Senka TX; Artificial neural networks; Chemical engineering; Chemical processes; Educational institutions; Fabrics; Information processing; Network topology; Neural networks; Radial basis function networks; Testing; K/S value; RBF neural network; predicting; reactive dyes;
Conference_Titel :
Information Processing, 2009. APCIP 2009. Asia-Pacific Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-0-7695-3699-6
DOI :
10.1109/APCIP.2009.31
