An inverse analysis algorithm is proposed to identify the material parameters of functional graded materials (FGMs). The inverse analysis of the material parameters is formulated as the problem of minimizing the objective function defined as a square sum of differences between the measured displacement and the computed displacement by a finite element model. Levenberg-Marquardt method is used to solve the minimization problem. The sensitivities of displacements with respect to the material parameters are based on the finite difference approximation method. A numerical example is given to demonstrate the effectiveness of the proposed algorithm.