Title :
Prediction of molar fractions in two-component gas mixtures using pulse-echo ultrasound and PLS regression
Author :
Carlson, Johan E. ; Carlson, Rolf
Author_Institution :
Dept. of Comput. Sci. & Electr. Eng., Lulea Univ. of Technol., Sweden
fDate :
3/1/2006 12:00:00 AM
Abstract :
The composition, and thus the energy content and monetary value of natural gas and biogas, vary considerably depending on the source. Present energy measurement techniques are riot suitable for online use. We show with experiments on mixtures of ethane (C/sub 2/H/sub 6/) and oxygen (O/sub 2/) how partial least squares regression (PLSR) can be used to predict the molar fraction of ethane in the mixtures, given spectral data from ultrasonic pulse-echo measurements. The PLSR technique is compared with the standard principal component regression (PCR), and we show that PLSR yields better predictive performance.
Keywords :
echo; gas mixtures; least squares approximations; regression analysis; PLS regression; biogas; ethane; molar fraction; molar fractions; natural gas; partial least squares regression; principal component regression; pulse-echo ultrasound; spectral data; two-component gas mixtures; Acoustic propagation; Attenuation; Energy measurement; Gases; Natural gas; Physics; Predictive models; Pulse measurements; Ultrasonic imaging; Ultrasonic variables measurement;
Journal_Title :
Ultrasonics, Ferroelectrics, and Frequency Control, IEEE Transactions on
DOI :
10.1109/TUFFC.2006.1610569
