Interactive parameter estimation for output error moving average systems

In this paper we study parameter estimation problems for the output error moving average systems. In order to reduce calculation loads of the existing identification methods, an interactive stochastic gradient (ISG) algorithm is presented to estimate the parameters of the system model and the noise model, respectively, based on the interactive estimation theory. Since the ISG algorithm possesses a slow convergence rate and poor estimation accuracy, interactive gradient-based and interactive least-squares-based iterative algorithms are derived to enhance the parameter estimation performances of the ISG algorithm. The simulation results illustrate the effectiveness of the proposed algorithms.