Author: | Shing, Wai-kit |
Title: | Comparison between two neural networks related controllers |
Degree: | M.Sc. |
Year: | 1996 |
Subject: | Neural networks (Computer science) Automatic control Back propagation (Artificial intelligence) Hong Kong Polytechnic University -- Dissertations |
Department: | Multi-disciplinary Studies |
Pages: | 86 leaves : ill. (some col.) ; 31 cm |
Language: | English |
Abstract: | Recently, artificial neural networks have been of interests to the control community. There have been numerous research results showing the potential of neural networks based control systems and some have proven the capabilities of such networks in control. The aim of this dissertation is to implement two different neural network based controllers and compare their performance by using the simulation results. They are direct neural network controller and IMC based neural network controller. Direct neural network controller is used to generate the proper control signal to the plant to achieve the desired performance in the plant output and not necessary to explicitly identify or learn the plant dynamics as conventional neural network controller. In IMC neural network controller, a neural model is used to identify unknown systems and neural controller, which is the inverse of the model, is then trained directly on line. Backpropagation algorithm is used to train the networks and the effect of training parameters to networks is investigated. In the simulation program, the results of the above control systems for a system specified by user can be obtained after inputting the control and system parameters, and then it is compared with those of conventional PID controller, which is designed by Z&N's method. |
Rights: | All rights reserved |
Access: | restricted access |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
b12339441.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 6.5 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/5183