Detecting 3D Printing Failures Using Computer Vision

The Project

This project’s purpose is to detect 3D printer failures through machine learning, computer vision, and AI. Although 3D printing has a promising future, it inevitably malfunctions from time to time, whether it is a design or hardware problem. Furthermore, with the rising importance of cybersecurity, there needs to be additional monitoring to alert users of malicious actors such as hackers. This results in consequences including waste of energy and filament, which are not environmentally friendly. Additionally, it also forces the owner to start over again, which is frustrating since 3D printing extends for long periods and wasted filament and time leads to financial loss. My app aims to ameliorate this problem by taking pictures of the 3D printer while it's in use and notifying the user when a print failure occurs. The AI model is trained with thousands of images, labeled either as successful or failed prints. A Raspberry Pi using a camera and AI is set up to monitor the 3D printer. The pictures taken by the Raspberry Pi of the 3D printer are then uploaded to an online database, which our app accesses and notifies the user of the current state of the printer.

View this project on YouTube

Team Comments

I chose to make this project because I have friends and family who are familiar with 3D printers and regularly use them. I had a friend who complained that they came home to their 3D printed item a mess; thus I was inspired to code my app to help mitigate this problem.

It was difficult knowing where to start; I hadn't really worked with machine learning before this app and had to do heavy research on AI models.

With more time, I can train my model with more pictures, run more trials with different types of settings, notify on exactly how much the print failed, and improve on more specific detection (e.g. when the 3D printer isn’t moving, it should also state that).