New Method Developed for Detecting Defects in Additively Manufactured Components

Researchers at the University of Illinois have made a groundbreaking discovery in the field of additive manufacturing. They have developed a new method for detecting defects in additively manufactured components, which can be a challenging task due to the complex three-dimensional shapes and internal features of these components.

The innovative technology utilizes deep machine learning to identify defects in additively manufactured components with high accuracy. By using computer simulations to generate tens of thousands of synthetic defects, the researchers were able to train the deep learning model to recognize the difference between defective and defect-free components. The algorithm was then tested on physical parts, successfully identifying hundreds of defects that had not been previously seen by the 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 quickly build a machine learning model that accurately detects defects. Deep learning allows us to identify defects that were previously unseen by the computer.”

The research, published in the Journal of Intelligent Manufacturing, utilized X-ray computed tomography to inspect the interior of 3D components with hidden defects and features. This technology opens up new possibilities for quality control in additive manufacturing, ensuring that components are free of defects even when important features are hidden from view.

For more information on this groundbreaking research, visit www.mechse.illinois.edu.