Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, has developed a deep-learning framework which is said to be speeding up the process of inspecting additively manufactured parts using X-ray computed tomography (CT) while increasing result accuracy.
The framework, developed by ORNL lead researcher Amir Ziabari and his team, is already incorporated into software used by commercial partner Zeiss Group, Oberkochen, Germany, within its machines at DOE’s Manufacturing Demonstration Facility at ORNL, where companies develop their Additive Manufacturing processes.
ORNL researchers had previously developed technology that can analyse the quality of a part while it is being manufactured. Adding a high level of imaging accuracy after manufacture provides an additional level of trust in Additive Manufacturing, while potentially increasing production, it was stated.
“With this, we can inspect every single part coming out of 3D printing machines,” said Pradeep Bhattad, ZEISS business development manager for Additive Manufacturing. “Currently, CT is limited to prototyping. But this one tool can propel Additive Manufacturing toward industrialisation.”
X-ray CT scanning is important for certifying the soundness of an additively manufactured part without damaging it. The process is similar to medical X-ray CT; in this case, an object set inside a cabinet is slowly rotated and scanned at each angle by powerful X-rays. Computer algorithms use the resulting stack of two-dimensional projections to construct a 3D image showing the density of the object’s internal structure. X-ray CT can be used to detect defects, analyse failures or certify that a product matches the intended composition and quality.
However, X-ray CT is not used at large scale in Additive Manufacturing because current methods of scanning and analysis are time-intensive and imprecise. Metals can totally absorb the lower-energy X-rays in the X-ray beam, creating image inaccuracies that can be further multiplied if the object has a complex shape, resulting flaws in the image can obscure cracks or pores the scan is intended to reveal. A trained technician can correct for these problems during analysis, but the process is time- and labour-intensive.
Amir Ziabari’s approach is intended to provide a leap forward by generating realistic training data without requiring extensive experiments to gather it. A generative adversarial network (GAN) method is used to synthetically create a realistic-looking data set for training a neural network, leveraging physics-based simulations and computer-aided design. GAN is a class of machine learning that utilises neural networks competing with each other as in a game. It has rarely been used for practical applications like this, Ziabari said.
Because this X-ray CT framework needs scans with fewer angles to achieve accuracy, it has reduced imaging time by a factor of six, according to Ziabari – from about one hour to ten minutes or less. Working that quickly with so few viewing angles would normally add significant ‘noise’ to the 3D image, but the ORNL algorithm taught on the training data corrects this, even enhancing small flaw detection by a factor of four or more.
The framework developed by Ziabari’s team would allow manufacturers to rapidly fine-tune their builds, even while changing designs or materials. With this approach, Pradeep Bhattad anticipates that sample analysis can be completed in a day instead of six to eight weeks.
“If I can very rapidly inspect the whole part in a very cost-effective way, then we have 100% confidence,” he said. “We are partnering with ORNL to make CT an accessible and reliable industry inspection tool.”
ORNL researchers evaluated the performance of the new framework on hundreds of samples additively manufactured with different scan parameters, using complicated, dense materials. These results were said to be good, and ongoing trials at MDF are working to verify that the technique is equally effective with any type of metal alloy, Bhattad said.
That’s important, because the approach developed by Ziabari’s team could make it far easier to certify parts made from new metal alloys.
“People don’t use novel materials because they don’t know the best printing parameters,” Ziabari said. “Now, if you can characterise these materials so quickly and optimise the parameters, that would help move these novel materials into Additive Manufacturing.”
In fact, per Ziabari, the technology can be applied in many fields, including defence, auto manufacturing, aerospace and electronics printing, as well as nondestructive evaluation of electric vehicle batteries.