A fuzzy neural network model to determine axial strain measured by a long-period fiber grating sensor

Abstract

The paper reports an adaptive-network-based fuzzy inference system for the measurement of axial strain using long-period fiber grating sensors. The long-period fiber grating sensor supports optical resonances, which are sensitive to the change of axial strain. The axial strain can be quantified based on the wavelength shift and amplitude changes of the optical resonance. To improve the accuracy of axial strain quantification, this paper proposes the adaptive-network-based fuzzy inference system model. The adaptive-network-based fuzzy inference system model is trained using the strain data measured with long-period fiber grating sensors. The parameters of the membership functions used in the adaptive-network-based fuzzy inference system are set adaptively. In the adaptive-network-based fuzzy inference system–based method, the maximum relative error was found to be 1.5%, which is about one-ninth of that when the data fitting method was used. The R-squared statistics using the adaptive-network-based fuzzy inference system model is 0.9872, while that using the linear fitting algorithm is 0.8815. Compared with the conventional data fitting methods, the proposed approach is highly adaptive and versatile with the capability of improving the accuracy of strain quantification.