Neural network ARMAX model for a Furuta pendulum

Abstract

The rotational inverted pendulum or Furuta Pendulum is a mechatronic system used by control engineers to explore a various dynamic modeling and control schemes. Due to its nonlinear nature, open-loop instability, and because it is an under-actuated system (more degrees of freedom than actuators), which is the basis for the design of vehicles such as the Segway, the self-balancing scooter, hoverboard, or selfbalancing board, among others. The authors present a model for the Furuta Pendulum using the equations of Euler-Lagrange and the methodology to identify a black-box model by training an NNARMAX (Neural Network Auto-Regressive Moving Average with exogenous inputs). The results show that two interconnected MISO-NNARMAX estimates 10-step-ahead predictions accurately for the horizontal and vertical angles.