Detecting anomalies in melt-extruded 3D printed parts using in situ data

The data in this repository was gathered from a study to collect real-time, in situ data from polymer melt extrusion (ME) 3D printing, using a set of sensors to non-destructively identfy printed parts that contain defects. The data underwent variance analysis to determine an \"acceptable\" range of filament diameters and non-destructivley identify spatial regions of printed cylinders in multi-part builds that contain defects.
The data consists of two folders and a log meant to track procedural adherence for each cylinder printed, the introduced defects, or lack thereof, and the pressurization of the part. The \"Final Build Logs\" spreadsheet contains information regarding the two locations of the deformations along the 56 meters of filament needed to have no more than three anomalous cylinders out of the six printed cylinders, the date of the applied deformations to the filament, the initials of the researcher applying the deformations, the date that the build was printed along with the ini..., The methodology involved an introduction of a material defect by varying the filament diameter of PETG filament and measuring the filament diameter values for the length of filament needed (9m) for a full cylinder three times before and after the defect was introduced using two orthogonally-positioned hall-effect sensors and a digital rotary encoder used to track the position along the filament of the cross-sectional diameter measurements. The data collected from the aforementioned process is not included in this repository, but the process preceded the creation of a defect that was both detectable in the in situ data and resulted in a printed cylinder with a statistically significant increase in its pressure decay rate.
Following this, six cylinders were printed on the same build plate and real-time in situ data from various sensors equipped on the desktop printer were gathered with the objective to map sensor data onto 3D coordinates to identify on which parts the identified anomalies..., , # Detecting anomalies in melt-extruded 3D printed parts using in situ data

The AMNOW contest objective was to demonstrate evidence of the benefits of using *in-situ* data to enable users of melt extrusion to evaluate the quality of a part without expensive or destructive testing, increase the visibility of the power in using in situ data to discover anomalies and trends in melt extruded parts, make feasible the possibilities of simulating development and discussion of artificial intelligence algorithms for finding anomalies in in situ data sets within the melt extrusion 3D printing community, and create motivation for industry machine providers to incorporate data collection and monitoring features in their products.

Improved understanding of critical parameters in the 3D printing process, such as filament diameter and filament feed slippage opens the door for developing corrective intervention and improving the success rate of 3D printing processes.

The work in collecting the data i...