Georgia Institute of Technology
Improving Part Quality in Wire Arc DED through Machining-Based Hybrid Manufacturing and Scientific Machine Learning
Abstract
dc:description.abstractWire Arc Directed Energy Deposition (DED) is a high-deposition-rate metal additive manufacturing process with significant potential for industrial use. However, challenges such as geometric inaccuracies, inconsistent microstructural and mechanical properties, and limitations in predictive modeling have hindered its wider adoption. This dissertation explores a Hybrid Wire Arc DED approach that integrates interlayer machining to improve geometric precision, surface quality, and microstructural consistency. Experimental results demonstrate that high strain-rate machining with specialized cutting tools refines grain structure, promotes microstructural uniformity, and enhances mechanical performance. Periodic machining also improves dimensional accuracy by reducing bead geometry variation and surface roughness. To further optimize the process, a coupled Physics-Informed Neural Network (PINN) framework is developed to predict bead geometry with high accuracy and computational efficiency, using a combination of fundamental process physics and optional low-fidelity data. These contributions advance the reliability, accuracy, and efficiency of Wire Arc DED, supporting its broader application in high-performance manufacturing.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Mechanical Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Rashid, Asif
- Advisor dc:contributor.advisor
-
- Melkote, Shreyes N.
- Committee members dc:contributor.committeemember
-
- Seepersad, Carolyn
- Joseph, Roshan
- Liang, Steven
- Kurfess, Thomas
Subjects
dc:subject × 4Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/81519