Abstract
A single long period grating is used for simultaneous measurement of temperature and strain in this article. To decrease the effect of cross-sensitivity effectively, a support vector regression (SVR) method is proposed due to its characteristics to approximate nonlinear function in the whole region. By detecting the shifts of LPG’s different loss peaks’ resonant wavelength, the temperature and strain were obtained by way of regression prediction where proper parameters were chosen. Some comparisons between the SVR and a standard matrix inversion method were made; the root-mean-square errors of two methods are 0.1746°C, 3.82 με and 2.981°C, 28.61 με, respectively. The experimental results show that SVR has advantages such as excellent learning performance of small samples, good generalization ability, small errors, high calculation accuracy, etc.
Keywords
Get full access to this article
View all access options for this article.
