Application of Machine Vision for in-situ Process Monitoring for Additive Manufacturing

Faculty Mentor

Hossein Taheri

Location

Russell Union Ballroom

Type of Research

Completed

Session Format

Poster Presentation

College

Allen E. Paulson College of Engineering & Computing

Department

Manufacturing Engineering

Abstract

The rise in 3D printer availability and its applications over the past decade, compared to traditional manufacturing, has revealed a lack of in-situ and post-manufacturing quality control. Developers have looked towards automated machine-vision algorithms, which can be effective in developing such additive manufacturing (AM) technologies for industry-wide adoption. Currently, most research has explored in-situ monitoring methods, which aim to detect printing errors during manufacturing. A significant limitation is the single, fixed monitoring angle and low resolution, which fail to identify small or hidden defects due to part geometry. Therefore, we are proposing a strategy that uses the advantages of machine vision to address the limitations; specifically, the viability of image-recognition algorithms, and how such algorithms can be integrated into the current infrastructure by automatically classifying surface faults in printed parts. An ML-based vision model, YOLO, will be adapted and trained by scanning for prescribed defect categories in a sample of AM parts to identify the strengths of this method for in-situ monitoring. The performance will be assessed according to the percentage of accurate defect predictions, in comparison with other measurement methods.

Program Description

.

Start Date

4-23-2026 2:00 PM

End Date

4-23-2026 4:00 PM

This document is currently not available here.

Share

COinS
 
Apr 23rd, 2:00 PM Apr 23rd, 4:00 PM

Application of Machine Vision for in-situ Process Monitoring for Additive Manufacturing

Russell Union Ballroom

The rise in 3D printer availability and its applications over the past decade, compared to traditional manufacturing, has revealed a lack of in-situ and post-manufacturing quality control. Developers have looked towards automated machine-vision algorithms, which can be effective in developing such additive manufacturing (AM) technologies for industry-wide adoption. Currently, most research has explored in-situ monitoring methods, which aim to detect printing errors during manufacturing. A significant limitation is the single, fixed monitoring angle and low resolution, which fail to identify small or hidden defects due to part geometry. Therefore, we are proposing a strategy that uses the advantages of machine vision to address the limitations; specifically, the viability of image-recognition algorithms, and how such algorithms can be integrated into the current infrastructure by automatically classifying surface faults in printed parts. An ML-based vision model, YOLO, will be adapted and trained by scanning for prescribed defect categories in a sample of AM parts to identify the strengths of this method for in-situ monitoring. The performance will be assessed according to the percentage of accurate defect predictions, in comparison with other measurement methods.