A licensing agreement between the U.S. Department of Energy’s Oak Ridge National Laboratory and research partner ZEISS will enable industrial X-ray computed tomography (CT) to perform rapid assessments of 3D-printed components using ORNL’s Simurgh machine learning algorithm.
Traditional quality inspection methods, such as visual inspection, are often inadequate for the unique geometries and materials used in 3D printing. Here, CT scans offer a non-destructive way to identify internal defects such as cracks or pores.
“CT is a standard nondestructive technique used in a multitude of different industries to ensure the quality of the component that is being produced,” said ORNL researcher Amir Ziabari. “But CT is traditionally an expensive and time-consuming process. The challenge is how can we leverage what we know of physics and technology to speed up the CT process to allow it to be more broadly adopted by industry.”
To address this problem, the machine-learning-based algorithm Simurgh was developed to significantly speed up the CT process.
The project is part of a five-year research collaboration between ORNL and ZEISS, supported by the Department of Energy’s Advanced Materials and Manufacturing Technologies Office.
“ZEISS and ORNL have a long partnership that has led to the development of innovative solutions for automated analysis and qualification,” said Paul Brackman, additive manufacturing manager at ZEISS. “We are now looking to further improve process development and qualification for additive manufacturing, to enable large-scale adoption and the shift from prototyping to manufacturing.”
The research team is working at ORNL’s Manufacturing Demonstration Facility, where the first 3D-printed components have already been successfully tested for use in extreme conditions such as nuclear plants and turbines.
“Understanding what type of defects might be present is incredibly important for understanding material behavior,” said MDF Director Ryan Dehoff, who led the nuclear bracket development. “In these types of parts, any defect or tiny pore in the material could result in a catastrophic failure.”
With the new approach, industries such as microelectronics and battery manufacturing could also benefit from CT technology. In addition, ORNL and ZEISS plan to optimize the technology so that it can be integrated into production lines.
“My ultimate goal, what I would like to achieve, is to make this so fast that we can put this in a production line so every part can be CT scanned rapidly and reliably,” Ziabari said. “If we can get there, that would be a game-changing development that would allow 3D printing to really fulfill its potential.”
This partnership could thus represent an important milestone for quality assurance in additive manufacturing by making inspection processes more efficient and reliable.