Neural network control of non minimum phase systems based on a noncausal inverse

Show full item record

Please use this identifier to cite or link to this item: http://hdl.handle.net/1853/39066

Title: Neural network control of non minimum phase systems based on a noncausal inverse
Author: Register, Andrew H. ; Book, Wayne John ; Alford, Cecil Orie
Abstract: A new approach for feedforward ANN control of nonminimum phase mechanical systems is proposed. A standard backpropagation-of-errors ANN is used to form an inverse model controller which is applied to simulated nonminimum phase systems. Learning in the new approach is based on the convolution between a noncausal impulse response and a desired tip trajectory. Selection of the proper input set, input scaling and the ANN structure are investigated. Once the input and structure are specified, the ANN is trained over a single trajectory. After training, the ANN is used to drive the system in an open-loop configuration. Plots of the system states resulting from the ideal excitation and from ANN excitation are compared. The results obtained by varying both the number of units and the input set are presented. The results demonstrate the effectiveness of the proposed ANN inverse model approach.
Description: ©1996 ASME Presented at the 1996 International Mechanical Engineering Congress and Exposition (IMECE), November 17-22, 1996, Atlanta, Georgia.
Type: Proceedings
Post-print
URI: http://hdl.handle.net/1853/39066
Citation: Register, A., W. Book and C. O. Alford, “Neural Network Control of Nonminimum Phase Systems Based on a Noncausal Inverse,” Proceedings of the ASME Dynamic Systems and Control Division, DSC Vol. 58, at the 1996 International Mechanical Engineering Congress and Exposition (IMECE), November 17-22, 1996, Atlanta, GA, pp 781-788.
Date: 1996-11
Contributor: Georgia Institute of Technology. School of Mechanical Engineering
Georgia Institute of Technology. Center for Robotics and Intelligent Machines
Publisher: Georgia Institute of Technology
American Society of Mechanical Engineers
Subject: Neural networks
Feedforward control systems
Mechanical systems

All materials in SMARTech are protected under U.S. Copyright Law and all rights are reserved, unless otherwise specifically indicated on or in the materials.

Files in this item

Files Size Format View
NEURAL NETWORK ... ON A NONCASUAL INVERSE.pdf 480.7Kb PDF View/ Open

This item appears in the following Collection(s)

Show full item record