Modeling the Dynamic of SCARA Robot Using Nonlinear Autoregressive Exogenous Input Neural Network Model

Abstract

One of the most useful robots in industrial is SCARA robot. Knowing dynamic of this robot is important for understating behavior of robot and designing a controller. A good way to model dynamic of robot is system identification based on data. In this paper, nonlinear Autoregressive exogenous input (NARX) neural network has been used for modeling and identification the direct dynamic of Ferdowsi university of Mashhad (FUM) SCARA robot. Results show that the proposed method work.