Nonlinear predictive control with application to manipulator with flexible forearm

Author

Song, Bumjin J. ; Koivo, Antti J.

Author_Institution

Sch. of Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA

Volume

46

Issue

5

fYear

1999

fDate

10/1/1999 12:00:00 AM

Firstpage

923

Lastpage

932

Abstract

A neural network is constructed to represent the input-output relation of a dynamical model. The parameters are calculated by means of a second-order training algorithm. Then, a nonlinear predictive controller is designed on the basis of a neural network plant model using the receding-horizon control approach. Based on the neural model, the control is calculated by minimizing a projected cost function that penalizes future tracking errors. As an illustration of the approach, the nonlinear dynamics of a planar two-joint arm with a flexible forearm are modeled using a sigmoidal network and an offline estimation procedure for a range of motions. The applicability of the approach is illustrated through computer simulations

Keywords

control system analysis; control system synthesis; distributed parameter systems; flexible manipulators; learning (artificial intelligence); motion control; neurocontrollers; nonlinear control systems; predictive control; computer simulation; control design; control simulation; flexible forearm manipulator; input-output relation; motion control; neural network; nonlinear dynamics; nonlinear predictive control; offline estimation procedure; planar two-joint arm; projected cost function minimisation; receding-horizon control approach; second-order training algorithm; sigmoidal network; Computer errors; Cost function; Error correction; Manipulator dynamics; Motion estimation; Neural networks; Nonlinear dynamical systems; Nonlinear systems; Predictive control; Predictive models;

fLanguage

English

Journal_Title

Industrial Electronics, IEEE Transactions on

Publisher

ieee

ISSN

0278-0046

Type

jour

DOI

10.1109/41.793340

Filename

793340