Georgia Institute of Technology
Automated Analysis of Differential Scanning Calorimetry Data for Shape Memory Alloys Using the Hough Transform
Abstract
dc:description.abstractModern materials research has been revolutionized by machine learning (ML) which uses large amounts of data to predict the properties of new materials. The analysis of this data represents a significant bottleneck in the development of ML models. This is especially true for shape memory alloys (SMAs), where phase transformations need to be characterized in addition to standard thermo-mechanical properties. Automating the data extraction process of database building can serve as a solution to this issue, allowing faster model deployment. Additionally, rapidly analyzing experimental data can allow databases to be established from larger and more densely populated search spaces, as these experiments can be easily performed if the desired data does not exist in literature. This work aims to develop a tool that will autonomously extract desired properties of SMAs from raw data collected from a differential scanning calorimetry (DSC) experiments for use in ML models
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Mechanical Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kennedy, Dylan T.
- Advisor dc:contributor.advisor
-
- Stebner, Aaron
- Committee members dc:contributor.committeemember
-
- Neu, Rick
- Qi, Jerry
- Kappes, Branden
- Benafan, Othmane
Subjects
dc:subject × 1Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/73105