DocumentCode :
1572803
Title :
A new multi-wavelength analysis method for estimation of total organic carbon in urban wastewater using UV/Vis spectrometry
Author :
Wu, Xiaoli ; Wu, Tiejun
Author_Institution :
Nat. Lab. of Ind. Control Technol., Zhejiang Univ., Hangzhou, China
Volume :
4
fYear :
2004
Firstpage :
3362
Abstract :
Total organic carbon (TOC) is an important parameter to evaluate the organic pollution of water. A novel method to rapidly detect TOC of wastewater with UV/Vis spectroanalysis is presented in this paper. UV/Vis absorption spectra in the range of 250∼450 nm were utilised for regression and prediction. Multi-wavelength regression procedure was discussed, and boosting method was used to improve the accuracy of prediction. Experiments show that better prediction result can be gained by this adaptive method than by the traditional regression algorithms, such as PLS, non-linear PLS and RBF neural network. Meanwhile, the improved regression model shows a good correlation between the estimated TOC values and the chemical analysis values.
Keywords :
carbon; learning (artificial intelligence); regression analysis; spectral analysis; wastewater; water pollution measurement; UV-Vis spectrometry; multiwavelength analysis; organic pollution; regression model; total organic carbon; urban wastewater; Boosting; Carbon dioxide; Decision making; Environmentally friendly manufacturing techniques; Industrial control; Industrial pollution; Intelligent systems; Laboratories; Spectroscopy; Wastewater;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on
Print_ISBN :
0-7803-8273-0
Type :
conf
DOI :
10.1109/WCICA.2004.1343164
Filename :
1343164
Link To Document :
بازگشت