| About this Abstract |
| Meeting |
2024 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2024)
|
| Symposium
|
2024 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2024)
|
| Presentation Title |
Mitigating Overspray in Aerosol Jet Printing: A Deep Learning Approach for Process Optimization |
| Author(s) |
Hasnaa Ouidadi, Md Shihab Shakur, Shubham Chetan Shah, Shenghan Guo, Srikanthan Ramesh |
| On-Site Speaker (Planned) |
Shenghan Guo |
| Abstract Scope |
Aerosol jet printing (AJP) is a micro-scale additive manufacturing technique for producing flexible electronics. The use of AJP for manufacturing electronics serving mission-critical needs is hindered by variability in printed features due to prevalent overspray. Overspray is the result of small droplets being deposited outside their intended area due to alterations in their trajectory. Although well-documented, understanding the origins of overspray and their relationships with process parameters is still ongoing. This study correlates morphological attributes of overspray to process parameters, establishing a basis for its mitigation. We introduce a deep learning-based method to analyze overspray type, location, and severity, relative to process parameters. A pretrained YOLO-V8 model was used to segment images of AJ-printed features to delineate regions corresponding to overspray. A correlation analysis was performed to evaluate overspray attributes relative to process parameters. Experiments involved AJ printing of conductive features with a PEDOT:PSS ink on a flexible substrate. |
| Proceedings Inclusion? |
Definite: Post-meeting proceedings |