| Author: | Cheng, Kai-hing |
| Title: | Process modelling, and optimisation, using neural networks |
| Degree: | M.Sc. |
| Year: | 1998 |
| Subject: | Plastics -- Molding Neural networks (Computer science) Hong Kong Polytechnic University -- Dissertations |
| Department: | Multi-disciplinary Studies Department of Manufacturing Engineering |
| Pages: | 92 leaves : ill. (some col.) ; 30 cm |
| Language: | English |
| Abstract: | Neural Network has a very strong ability to capture complex input-output relationships of complex functions under noisy environment make it a very good candidate to model Industrial Processes. In this paper, a training algorithm has been designed which used correlation coefficients, relative errors and absolute errors to measure the goodness of fit. The trained models were tested with testing data concurrently. In order to prove the effectiveness of the training algorithm, three known functions were trained without and with noise. Variables search techniques are used to find the significant factors. Conventional methods using fractional factorial designed, ANOVA, and regression Modelings were also used to compare the results. Lastly an optimization experiments to find out the optimum settings of the significant factors which confirmed with verification run to be very close to the actual. We concluded by suggesting ANN to be developed as the experimental analysis tools but requires to install faster speed computers as the training time is sometimes quite long. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b14535890.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 956.88 kB | 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/200/4587