|About this Abstract
|MS&T23: Materials Science & Technology
|Additive Manufacturing: Design, Materials, Manufacturing, Challenges and Applications
|Real-time Binder Deposition Tracking and Modeling via Machine Learning Image Processing Methods
|Peter Warren, Md Shahjahan Hossain, Pranta Sarkar, Daniel Homa, Gary R. Pickrell, Ranajay Ghosh, Ramesh Subramanian, Jayanta Kapat, Navin Manjooran
|On-Site Speaker (Planned)
This paper presents an approach to track binder deposition, specifically wetted area tracking, using image segmentation techniques and subsequently modeling its behavior. The ability to accurately monitor and analyze the binder deposition process is crucial in both Binder Jetting Technology (BJT) and Additive Manufacturing (AM) processes. The proposed method aims to leverage image segmentation and machine learning techniques to facilitate the tracking and modeling of binder deposition. Image segmentation algorithms are employed to isolate and segment the wetted areas of interest from the captured images. By distinguishing the binder-affected regions, precise tracking of the wetted areas can be achieved throughout the deposition process. The segmented data serves as the foundation for subsequent analysis and modeling. By training the models on a comprehensive dataset, valuable insights can be obtained regarding the dynamics and characteristics of binder deposition. This information can subsequently be utilized for process optimization, defect detection, and quality control in BJT and AM. The proposed approach offers numerous benefits for BJT and AM processes.