Identification of Dynamical Systems Through the Structure of Auto-regression With Exogenous Variable by Decreasing Gradient and Least Squares

In this article was made the identification of dynamic systems first and second order more common in electronics such as low high pass filters order, pass-band filter direct current motor through structure auto-regression with exogenous variable. The proposed dynamical are initially modeled by a continuous-time transfer function using physical laws. Subsequently, step entry signal applied data for process recorded discrete time. estimation parameters performed method decreasing gradient least squares. It obtained result that squares could not find model first-order high-pass filter, but grade allowed to all systems.