Printpal was pleased to announce the official launch of the PrintWatch software and API used for monitoring 3D print jobs in real time using Artificial Intelligence.
More from the Company
PrintWatch is a software and API that will monitor 3D prints in real-time to detect defects that begin to develop during a print job. When the software detects a defect, it tracks the defect and if it gets worse, actions are taken. Some of the actions include stopping the print, turning off the heat, and sending a notification to the owner of the printer. These actions prevent the printer from continuing a defective print for hours, and the user is notified right away. This saves time and material in addition to reducing the risk of damage or fire to the printer and its surroundings.
In addition to detecting defects in real-time, PrintWatch has an Anomaly Detection System running in the background. The Anomaly Detection System detects and flags anomalies in a printer. The system can detect very subtle issues so the user can schedule maintenance for the printer to reduce downtime. For example, the system may be able to detect there is something slightly wrong with one of the axis of a printer and signals the user to check on the printer.
Download the 3rd issue of AM Chronicle for Free
In order to detect defects in real-time, PrintWatch takes the video stream of a camera fixed onto the printer’s print area and runs it through a Machine Learning model that can detect defects of various sizes, shapes, colors, materials, lightings, and settings. When a defect is positively identified, PrintWatch then begins to track the defect to see how it develops. If it is clear that the defect is getting worse, PrintWatch takes action. This tracking system helps prevent any false-positives from triggering action from the software.
PrintWatch runs the computationally heavy Machine Learning models on the cloud meaning any device with internet is able to access the API. Run the software with as little as a Raspberry Pi Zero. PrintWatch is made easily available via OctoPrint as a plugin which can be found here. Additionally, users may create a custom integration of PrintWatch for builds that are not using OctoPrint in less than 5 lines of python code.
A locally running version of PrintWatch is being developed and tested giving the user the ability to run PrintWatch in house without having to connect to the internet. This is best suited for larger print operations or industrial settings where the user may have security concerns. It is built to run on any CUDA enabled devices, including the NVIDIA Jetson platform. The product is extremely scalable and can service any amount of printers.
Subscribe to AM Chronicle Newsletter to stay connected: https://bit.ly/3fBZ1mP
Follow us on LinkedIn: https://bit.ly/3IjhrFq
Visit for more interesting content on additive manufacturing: https://amchronicle.com/
