Low cost and open-type Fused Deposition Modeling (FDM) 3D printers are widely available but can produce various defects. Parts slipping off the print bed, filament runout, warping, etc. are some of the common defects in such 3D printers. This can produce material and time losses. To minimize that, we researched several algorithms and developed DaR3D, a monitoring system to detect defects and alert the user. DaR3D’s detection algorithm periodically acquires images through a webcam with controlled lighting, removes the background, and applies a normalized mean square error method to compare successive images. If the images have noticeable differences, the algorithm determines that a defect has occurred. The system was able to correctly identify slippage in prints with 89.6% accuracy, using samples from two different 3D printers and many different printed models. Future work will involve expanding the algorithm to cover more defects during printing.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Forte, Mark
• Malkowski, Ryan
• Eisenhour, Madison

Publisher

• Worcester Polytechnic Institute

Identifier

• 67376
• E-project-050222-215419

Advisor

• Radhakrishnan, Pradeep
• Brown, David C.

Year

• 2022

Date created

• 2022-05-02

Resource type

• Major Qualifying Project

Major

• Computer Science
• Mechanical Engineering

Rights statement

• In Copyright

License

• Creative Commons BY-NC Attribution-NonCommercial 4.0 International