Please use this identifier to cite or link to this item: https://doi.org/10.1109/ACC.1998.703016
Title: Critical implementation issues in compensation for nonlinearities in industrial robot manipulators by adaptive multilayer neural networks
Authors: Lou, Y.
Holtz, J.
Lee, T.H. 
Issue Date: 1998
Source: Lou, Y.,Holtz, J.,Lee, T.H. (1998). Critical implementation issues in compensation for nonlinearities in industrial robot manipulators by adaptive multilayer neural networks. Proceedings of the American Control Conference 4 : 2200-2202. ScholarBank@NUS Repository. https://doi.org/10.1109/ACC.1998.703016
Abstract: To improve the performance of an industrial robot manipulator with linear individual-joint controllers, an adaptive feedforward Multilayer Neural Network (MNN) is proposed as an addition to the existing linear control structure at each joint to compensate the nonlinearity. System stability is guaranteed by three measures: the initialization of the MNN, which ensures that the MNN's learning start from a reasonable point; a Lyapunov-based adaptive law, in which the MNN is linearized and the residual error is tolerated by a dead-zone or a leakage term; and a contribution function, which manipulates the contribution of the MNN to the system. The MNN and the control algorithm are implemented on a TMS320C30 digital signal processor. The realization on a two-link manipulator demonstrates the effectiveness of the proposed scheme. © 1998 AACC.
Source Title: Proceedings of the American Control Conference
URI: http://scholarbank.nus.edu.sg/handle/10635/72549
ISBN: 0780345304
ISSN: 07431619
DOI: 10.1109/ACC.1998.703016
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

26
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.