eduzhai > Applied Sciences > Engineering >

Inverse NN Modelling of a Piezoelectric Stage with Dominant Variable

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 29 pages

Abstract: This paper presents an approach for developing a neural network inverse modelof a piezoelectric positioning stage, which exhibits rate-dependent, asymmetrichysteresis. It is shown that using both the velocity and the acceleration asinputs results in over-fitting. To overcome this, a rough analytical model ofthe actuator is derived and by measuring its response to excitation, thevelocity signal is identified as the dominant variable. By setting the inputspace of the neural network to only the dominant variable, an inverse modelwith good predictive ability is obtained. Training of the network isaccomplished using the Levenberg-Marquardt algorithm. Finally, theeffectiveness of the proposed approach is experimentally demonstrated.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×