A new method for COD analysis with full-spectrum based on Artificial Neural Network

Wei-wei Feng; Dan Li; Zong-qi Cai; Fu-guo Hao

doi:10.1117/12.2242629

27 September 2016 A new method for COD analysis with full-spectrum based on Artificial Neural Network

Wei-wei Feng, Dan Li, Zong-qi Cai, Fu-guo Hao

Proceedings Volume 9684, 8th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test, Measurement Technology, and Equipment; 96842K (2016) https://doi.org/10.1117/12.2242629
Event: Eighth International Symposium on Advanced Optical Manufacturing and Testing Technology (AOMATT2016), 2016, Suzhou, China

Abstract

A new on-line monitoring system was developed for the determination of chemical oxygen demand (COD) in water based on full-spectrum analysis. In this system, Artificial Neural Net (ANN) work was used to obtain the transmission equation between absorbance and COD value by measuring absorption spectra of water with known COD value, and then the established equation could inverse the COD values of the unknown water samples. For the COD determination of simulated complicated water samples, the instrumental reliability was well validated by a comparison made between the ANN method and the PLS method. The monitoring system of the ANN method provided advantages of simplicity, rapidity, high precision, no consumption of reagent. And it was demonstrated an ideal alternative to real-time and on-line monitoring of COD in water.

Citation Download Citation

Wei-wei Feng, Dan Li, Zong-qi Cai, and Fu-guo Hao "A new method for COD analysis with full-spectrum based on Artificial Neural Network", Proc. SPIE 9684, 8th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test, Measurement Technology, and Equipment, 96842K (27 September 2016); https://doi.org/10.1117/12.2242629

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available