In this paper, we present an interferometry method for refractive index determination in membranes of fuel cells. This technique is based on the use of an improved laser heterodyne interferometer. The photocurrents of the avalanche photodiodes, resulting from reflected beams of the optical head, are led to the signal conditioner and digital signal processing sections. The optical path difference between the target and reference paths is fixed, and as a result, the phase shift is calculated in terms of the refractive index shift. In addition, nonlinearity of this system is analyzed and modeled with different neural networks and adaptive filter algorithms. For neural networks, the radial basis function (RBF), the multi-layer perceptron (MLP), and the stacked generalization method are simulated. In adaptive filter algorithms, the least mean square (LMS), the normalized least mean square (NLMS), the recursive least squares (RLS), and the affine projection algorithm (APA) are applied. The simulation results indicate that the RLS method is faster and contains minimum mean square error (MSE) compared to the other approaches. Also, comparison between two main approaches shows that the nonlinearity of refractive index determination can be effectively modeled with adaptive filter algorithms. Copyright (C) 2010, Hydrogen Energy Publications, LLC. Published by Elsevier Ltd. All rights reserved.