Open Access. Powered by Scholars. Published by Universities.®
Operations Research, Systems Engineering and Industrial Engineering Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Institution
- Publication
Articles 1 - 3 of 3
Full-Text Articles in Operations Research, Systems Engineering and Industrial Engineering
Quality And Productivity Improvements In Additive Manufacturing, Huseyin Kose
Quality And Productivity Improvements In Additive Manufacturing, Huseyin Kose
Doctoral Dissertations
Additive manufacturing (AM) is a relatively new manufacturing technology compared to the traditional manufacturing methods. Even though AM processes have many advantages, they also have a series of challenges that need to be addressed to adapt this technology for a wide range of applications and mass production.
AM faces a number of challenges, including the absence of methods/models for determining whether AM is the best manufacturing process for a given part. The first study of this thesis proposes a framework for choosing specific AM processes by considering the complexity level of a part. It has been proven that the method …
Minimizing Leakage In Thin Walled Structures Printed Through Selective Laser Melting, Andrew Spencer Yap
Minimizing Leakage In Thin Walled Structures Printed Through Selective Laser Melting, Andrew Spencer Yap
Master's Theses
In this project, the scan strategy of selective laser melting (SLM) for thin walled structures was investigated by changing laser parameters and tool path. Producing thin walled structures is difficult due to defects such as warpage and porosity. A layer on the SLM 125 consists of hatch volume, fill contours, and borders, however, for thin walls, hatch volume can become unavailable, resulting in a solely border/fill contour laser tool path.
Three central composite designs (CCD) were created to optimize the laser parameters of borders to minimize leakage rate and porosity. The two factors changed were border laser power and scanning …
Transfer Learning Approach To Powder Bed Fusion Additive Manufacturing Defect Detection, Michael Wu
Transfer Learning Approach To Powder Bed Fusion Additive Manufacturing Defect Detection, Michael Wu
Master's Theses
Laser powder bed fusion (LPBF) remains a predominately open-loop additive manufacturing process with minimal in-situ quality and process control. Some machines feature optical monitoring systems but lack automated analytical capabilities for real-time defect detection. Recent advances in machine learning (ML) and convolutional neural networks (CNN) present compelling solutions to analyze images in real-time and to develop in-situ monitoring.
Approximately 30,000 selective laser melting (SLM) build images from 31 previous builds are gathered and labeled as either “okay” or “defect”. Then, 14 open-sourced CNN were trained using transfer learning to classify the SLM build images. These models were evaluated by F1 …