Acessibilidade / Reportar erro

Neural and vectorial controller for XY table

The proposal of this research is to present a new strategy of drive, called of Neural Vectorial Control, using a Multilayer Neural Network acting as a direct adaptive controller, that is based on the minimization of the error between the actual position vector and the vector of reference position. Two strategies of control are shown. The first strategy is based on the use of position neural controllers of independent axes. The second strategy, presented as the main contribution of this paper, is based on the use of the vectorial neural controller. The strategy proposal in this research is differentiated of the well known tracking controllers for not possessing individual closed loops of control for each axis. The XY table used for validation is a structure of two degrees of freedom, that it is considered as a manipulator with detached axes. Experimental and simulated results show the superior performance of the vectorial neural control. A lesser time of processing in the use of an only Neural Nework is an additional advantage of the use of the vectorial neural controller in relation to the independent controllers.

Adaptive control; Compounds table; Neural Network


Sociedade Brasileira de Automática Secretaria da SBA, FEEC - Unicamp, BLOCO B - LE51, Av. Albert Einstein, 400, Cidade Universitária Zeferino Vaz, Distrito de Barão Geraldo, 13083-852 - Campinas - SP - Brasil, Tel.: (55 19) 3521 3824, Fax: (55 19) 3521 3866 - Campinas - SP - Brazil
E-mail: revista_sba@fee.unicamp.br