Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Mechanical Engineering | en_US |
| dc.contributor.advisor | Shi, S. Q. (ME) | en_US |
| dc.creator | Liu, Guanhong | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/10801 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Application of machine learning method in the study of stacking fault energy of steel | en_US |
| dcterms.abstract | Stacking fault energy (SFE) has an important influence on various properties of steel. Since the 1950s until now, scientists have been searching for measurement methods of stacking fault energy and factors influencing stacking fault energy. But for many reasons, it usually takes a long time to discover. And through the traditional material research paradigm, the stacking fault energy of the unknown steel model can be determined and the elements affected by it have different conclusions with different steel models. In the past eight years, the development of material informatics and the introduction of the material genome project have enabled statistical algorithms and artificial intelligence to be widely used in materials research. In this research, machine learning (ML) method is applied in the research of SFE of steel. Genetic algorithm (GA) and lasso algorithm are used to build models to analyze the database which contains 474 sets of SFE data which contains the content of 17 elements in order to filter out the features which affect SFE. Then classification algorithms (decision tree, random forest and naïve Bayes) are used to build models in order to predict the SFE. Pearson correlation coefficient is used to measure the models set up by the classification algorithms to select the best one. The performances of models are shown in the scatter plots of measured value and predicted value. Combining the results of GA and lasso algorithm, carbon, phosphorus, titanium, manganese and copper are proved to have effects on the SFE of steel. The prediction model set up by decision tree algorithm shows the best performance. This work indicates the great potential of ML in advanced materials design with target properties. | en_US |
| dcterms.extent | x, 87 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2020 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Steel -- Analysis | 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 | |
|---|---|---|---|---|
| 5238.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.96 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/200/10801