Abstract

The on-line measurement of chemical composition under different operating conditions is an important problem in many industries. An approach based on hybrid signal preprocessing and artificial neural network paradigms for estimating composition from chemometric data has been developed. The performance of this methodology was tested with the use of near-infrared (NIR) and Raman spectra from both laboratory and industrial samples. The sensitivity-of-composition estimation as a function of spectral errors, spectral preprocessing, and choice of parameter vector was studied. The optimal architecture of multilayer neural networks and the guidelines for achieving them were also studied. The results of applications to FT-Raman data and NIR data demonstrate that this methodology is highly effective in establishing a generalized mapping between spectral information and sample composition, and that the parameters can be estimated with high accuracy.

Subpixel microscopic deformation analysis using correlation and artificial neural networks

Mark C. Pitter, Chung W. See, and Michael G. Somekh
Opt. Express 8(6) 322-327 (2001)

Data analysis of stellar specklegrams with neural networks

Naoshi Baba, Akifumi Kishino, and Noriaki Miura
Appl. Opt. 35(5) 844-847 (1996)

Estimation of optical constants of thin film by the use of artificial neural networks

Yuan-sheng Ma, Xu Liu, Pei-fu Gu, and Jin-fa Tang
Appl. Opt. 35(25) 5035-5039 (1996)

Using artificial neural networks for open-loop tomography

James Osborn, Francisco Javier De Cos Juez, Dani Guzman, Timothy Butterley, Richard Myers, Andrés Guesalaga, and Jesus Laine
Opt. Express 20(3) 2420-2434 (2012)

Speckle reduction using an artificial neural network algorithm

Mohammad R. N. Avanaki, P. Philippe Laissue, Tae Joong Eom, Adrian G. Podoleanu, and Ali Hojjatoleslami
Appl. Opt. 52(21) 5050-5057 (2013)