Georgia Institute of Technology
Foundation model for time series analysis in ALD process and automated semiconductor characterization
Abstract
dc:description.abstractThis thesis focuses on the application of AI in semiconductor fabrication, including two different stages of research projects. The first project developed a foundation model framework for time series analysis in atomic layer deposition (ALD) processes, specifically targeting high-K dielectrics such as HfO2 and ZrO2. By integrating time-series sensor data with multimodal datasets, including engineering logs and recipes, this project aims to predict material properties, improve process efficiency. The second project demonstrated a practical implementation through an automated semiconductor characterization system for ferroelectric devices. This work focuses on leakage detection in semiconductor devices measurements, which transforms the traditional, manual, and time-consuming process of analyzing polarization voltage (P-V) loops into an automated machine learning pipeline. These projects both lay the theoretical foundation for AI driven semiconductor process optimization and provide practical experience for the effectiveness of deep learning in semiconductor fabrication.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Electrical and Computer Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Li, Congrui
- Advisor dc:contributor.advisor
-
- Khan, Asif I.
- Committee members dc:contributor.committeemember
-
- Vogel, Eric
- Yu, Shimeng
Subjects
dc:subject × 7Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/77935