Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Multi-disciplinary Studies | en_US |
| dc.creator | Tang, Kwok-ki | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/222 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Neural-network-based fuzzy control system in structural dynamics | en_US |
| dcterms.abstract | This report described the application of neural-network-based fuzzy system to the area of structural deformation control under a strong force vibration. A hybrid model known as neural-network-based fuzzy control or neuro-fuzzy control which combines the advantages of fuzzy control and artificial neural network is proposed. The model facilitates the learning of control rules and the adjustment of control parameters (fuzzy membership functions) through two stages of learning. Control rules are learnt from examples via a fast learning 'supervised competitive learning' algorithm making use of the initial fuzzy membership functions suggested by experts or obtained by other means. The fuzzy membership functions are then fine-tuned by an error back-propagation network. After learning, fuzzy control rules and membership functions are derived from the network. To overcome the long training time of the back-propagation network and to prevent the network from being trapped in local minima, a training plan is introduced to train the network. The training plan allocates more resources for the network to learn harder examples. The proposed network is evaluated with a structural dynamics problem. The test result indicates that the proposed network is a good estimator for problems that are difficult to be described by rigorous mathematical models. In addition, the knowledge encoded in the network is human understandable. The robustness of the network is also tested. The performance of the network is not significantly affected when some processing elements are damaged. This property suggests that the neuro-fuzzy controllers may beneficially be employed to work in adverse conditions. Submitted by Kwok-ki TANG for MSc in Information Technology at the Hong Kong Polytechnic University in February 1995 | en_US |
| dcterms.extent | vi, 135 leaves : ill. ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 1995 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Neural networks (Computer science) | en_US |
| dcterms.LCSH | Fuzzy systems | en_US |
| dcterms.LCSH | Structural dynamics | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b11835461.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.5 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/200/222