USC Viterbi School of Engineering scientists have developed new machine learning algorithms and a software tool, PrintFixer, to improve 3D printing accuracy by more than 50%.
Despite its many advantages, 3D printing has a high degree of error, especially in the form of shape distortion.
Each printer is different, and the printed material can shrink and expand in unexpected ways. Manufacturers often need to try many iterations of a print before they get it right.
Now a team of PhD students – led by associate professor Qiang Huang – has found a way to make 3D printing a lot more accurate, economical and sustainable.
The scientists have so far received $1.4 million in funding to built an AI model that accurately predicts shape deviations for all types of 3D printing.
“What we have demonstrated so far is that in printed examples the accuracy can improve around 50% or more,” says Huang.
“In cases where we are producing a 3D object similar to the training cases, overall accuracy improvement can be as high as 90%.”
According to Huang, it can actually take industry eight iterative builds to get one part correct, for various reasons.
Every 3D printed object results in some slight deviation from the design, whether this is due to printed material expanding or contracting when printed, or due to the way the printer behaves.
PrintFixer fixes such issues just by gleaning data from past 3D printing jobs to train its AI to predict where the shape distortion will happen, helping fix print errors before they occur.
“From just five to eight selected objects, we can learn a lot of useful information,” contends Huang. “We can leverage small amounts of data to make predictions for a wide range of objects.”
The team has trained the model to work with the same accuracy across a variety of applications and materials – from metals for aerospace manufacturing, to thermal plastics for commercial use.
They hope to make the software tool available to everyone, from large scale commercial manufacturers to 3D printing hobbyists.
Users from around the world will also be able to contribute to improving the software AI through sharing of print output data in a database.
Image and content: PXHERE/USC Viterbi School of Engineering
