Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Multi-disciplinary Studies | en_US |
| dc.creator | Sin, Kan-yuen | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/4193 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Fuzzy knowledge system for machine maintenance | en_US |
| dcterms.abstract | This report describes the application of fuzzy knowledge-based neural network system to the area of machine maintenance for the Mass Transit Railway Corporation (MTRC) of Hong Kong. A model known as fuzzy knowledge system which combines the advantages of fuzzy knowledge and artificial neural network for industrial application is presented in this dissertation. The model utilizes expert's knowledge and transforms them into fuzzy membership functions through control rules. Error back-propagation network is selected for the network training by means of a software package called NeuroForecaster. The fuzzy membership functions are trained and finetuned through various activation functions. After extensive training, the use of FastProp with hyperbolic tangent is recommended. Decomposition of input pattern to facilitate training is also suggested to overcome the long training time of back-propagation network and eliminate the effect of local minima. Thus, the application of this model can be further extended. The learning of proposed model is performed using two months operational data of March and July 1995. Both the test and forecast results indicate that it is an excellent network for machine maintenance planning since there are difficulties to be programed mathematically. The result shows with 20.08% improvement than the existing maintenance methodology. Also its knowledge base is human understandable as compared with other intelligent systems. The network can even learn in a noisy environment and can maintain reasonable performance with damaged or missing input data. The strength of network output is being proved by Logistic Regression method. Apart from 20.08% improvement, there could exponentially generate resultant benefits towards MTRC in terms of customer service and image. Integrating above features, the proposed model can smoothly handle more types of industrial machine maintenance planning problems. | en_US |
| dcterms.extent | 1 v. (various pagings) : ill. ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 1996 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Machinery -- Maintenance and repair | en_US |
| dcterms.LCSH | Fuzzy systems | en_US |
| dcterms.LCSH | Mass Transit Railway Corporation | 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 | |
|---|---|---|---|---|
| b1230671x.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 9.38 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/200/4193