ORNL Makes Significant Progress in Detecting Flaws in Metal 3D Printing – 3DPrinting.com

Share this story

Hello there, readers! Today, we have an exciting research breakthrough to share with you from the Oak Ridge National Laboratory (ORNL). Researchers at ORNL have made significant improvements in flaw detection in laser powder bed fusion 3D printing, which is a widely used technique in the manufacturing industry.

Now, you might be wondering why this research is important. Well, industries like aerospace, defense, and energy often face challenges when adopting 3D printing technology due to difficulties in inspecting printed parts for hidden flaws. Flaws in 3D printed metal parts could compromise their integrity and safety, so it is crucial to detect and address these issues.

Fortunately, ORNL’s new approach tackles this problem head-on by combining post-build inspection data with real-time sensor data collected during the printing process. By merging these datasets, a machine-learning algorithm is trained to identify flaws in the printed parts. This method consistently detects flaws as small as half a millimeter with an impressive success rate of 90%.

This in-process flaw detection technique is just as reliable as traditional methods, but it is much more efficient and less labor-intensive. Laser powder bed fusion 3D printing involves using a high-energy laser to melt metal powder layer by layer, creating the desired object. As with any manufacturing process, flaws are expected, but ORNL’s approach offers a more quantitative and accurate way to detect and address these flaws.

To develop and test this method, ORNL collaborated with aerospace and defense company RTX. They utilized CT scans and near-infrared cameras to monitor the printing process, gathering critical data for the machine-learning algorithm. As the algorithm continues to learn and improve over time, human involvement in the inspection process will be reduced, making it even more efficient.

This breakthrough by ORNL has immense potential for mass production applications, allowing for the creation of more diverse 3D printed parts while ensuring quality control. As the industry moves towards larger print sizes and faster rates, this technique will be instrumental in addressing inspection challenges for larger and more complex parts.

If you’re interested in learning more about this research, you can read the full research paper titled “Scalable in situ non-destructive evaluation of additively manufactured components using process monitoring, sensor fusion, and machine learning” in the Additive Manufacturing journal, available at this link.

We would love to hear your thoughts on this exciting development! Join the conversation on our Facebook, Twitter, and LinkedIn pages. And don’t forget to sign up for our weekly additive manufacturing newsletter to stay updated with the latest stories delivered right to your inbox.

Thank you for reading, and stay tuned for more groundbreaking research in the field of 3D printing!

Original source


Share this story

Leave a Reply

Your email address will not be published. Required fields are marked *