Frequency response tests are used widely in system identification, parameter estimation and system analysis. This paper studies the parameter estimation problem for dynamical systems based on the sinusoidal frequency response experiment. Because the output response is a nonlinear function with respect to the parameters to be estimated, a nonlinear criterion function is constructed for finding the parameter estimates. Using the nonlinear optimization technique, we present an iterative algorithm for estimating the system parameters. In order to overcome the problems of singular and ill-conditioned matrix during the iterative process, we put forward a damping iterative algorithm. Finally, an example is provided and the simulation results indicate that the proposed method has good performance.