Researchers developed a method to detect defects in 3D-printed components using deep machine learning.
The model was trained using computer simulations with synthetic defects.
Tests on physical parts showed high accuracy in defect detection.
Additive Manufacturing: New Technology for Defect Detection through Machine Learning
Researchers at the University of Illinois Urbana-Champaign have developed a new method for detecting defects in additively manufactured components. In manufacturing, it is crucial to ensure that a produced component is free of defects. This is particularly challenging in additive manufacturing (3D printing) because the components often have complex three-dimensional shapes and important internal features that are difficult to observe.
The novel technology uses deep machine learning to significantly ease the identification of defects in additively manufactured components. To build their model, the researchers used computer simulations to generate tens of thousands of synthetic defects that exist only in the computer. Each computer-generated defect had different sizes, shapes, and locations, allowing the machine learning model to train on a wide variety of possible defects and recognize the difference between defective and non-defective components.
The algorithm was then tested on physical parts, some of which were defective and some defect-free. The algorithm was able to correctly identify hundreds of defects in real physical parts that had not previously been seen by the machine learning model.
"This technology addresses one of the toughest challenges in additive manufacturing," said William King, Professor of Mechanical Science and Engineering at Illinois and the project leader. "Using computer simulations, we can very quickly build a machine learning model that identifies defects with high accuracy. Deep learning allows us to accurately detect defects that were never previously seen by the computer."
The research, published in the Journal of Intelligent Manufacturing in a paper titled "Detecting and classifying hidden defects in additively manufactured parts using deep learning and X-ray computed tomography," used X-ray computed tomography to inspect the interior of 3D components with internal features and defects that are hidden from view. Three-dimensional components can be easily made with additive manufacturing but are difficult to inspect when important features are hidden.
