MODELING NONLINEAR NEURAL OF TWO LINKS OF A ELECTROMECHANICAL ROBOT OF THREE DEGREES OF FREEDOM
Anrafel Silva Meira1; José Antônio Riul2; Paulo Henrique de Miranda Montenegro2
1 IFPB; 2 UFPB
doi:10.20906/CPS/COB-2015-0374
Resumo
The objective is the nonlinear neural modeling of two links of a robot manipulator electromechanical of three degrees of freedom (3 DOF). The manipulator comprises three rotary joints and three links, with two links driven by direct current motors, and an third link with motion controlled by a mechanical system that always keeps its the horizontal position. The measurements of angular positions of the joints are made by potentiometers. Manipulator robot models are obtained using equations of Newton-Euler or Lagrange; and are coupled and nonlinear. In this paper, a nonlinear neural model is obtained using the excitations and responses collected of the two links driven by direct current motors and of the an artificial neural network. Finally, we present results obtained from the generated model.
Palavras-chave: robotics; Nonlinear neural identification