3D print quality improves when machines share data

Departments - 1 Last Look

Researchers are improving 3D printing technology by teaching machines to learn from each other.

July 27, 2022

Hui Wang, left, associate professor of industrial engineering and An-Tsun Wei, a Ph.D. student, are the co-authors of a paper detailing how learning cloud data collected from interconnected 3D printers improves quality control and printing accuracy.

In a new study published in the IEEE (Institute of Electrical and Electronics Engineers) Transactions on Automation Science and Engineering, researchers at the Florida Agricultural and Mechanical University and Florida State University (FAMU-FSU) College of Engineering showed how data from one printer can be used by other machines to improve efficiency and quality.

“Cloud manufacturing, along with the Internet of Things (IoT), is a newly emerging technology,” says Hui Wang, associate professor at the FAMU-FSU College of Engineering. “The technology demonstrates that data generated from multiple production machines can be shared with each in a timely manner, and manufacturing can be enclosed as online services for meeting diverse market demands.”

According to Hubs’ “2021 3D Printing Trends Report,” the 3D printing market grew 21% in 2020, despite the pandemic. The industry prints everything from metal to biological materials, and the race is on to optimize these processes.

Wang and his colleagues are developing new learning algorithms and ways to control the printing process. Tiny differences in a printer’s nozzle movement can cause variations in processing and flaws in finished structure. Their technique uses data shared among machines to reduce printing defects.

The researchers connected printers on a cloud platform, and shared data about accurate processing, decreasing the time needed to prepare.

The researchers developed a mathematical model to better understand the printing process, says An-Tsun Wei, a doctoral student in the college’s Department of Industrial and Mechanical Engineering.

“We can estimate geometric print quality and the related defects that might occur with the model,” she notes. “The information can be used to calculate adjustments needed in the input printing parameters to compensate for those errors.”

Traditional machine learning (ML) requires difficult to collect experimental data and printers must be quickly adjusted to cope with new tasks. Transfer learning technology allows different printing processes to share experiences, which speeds up the process. The research demonstrates the feasibility of using shared data from interconnected 3D printers to reduce testing time and improve the product.

“With reduced testing, we can improve quality control faster and thereby quickly recalibrate the printing processes,” Wang says. “This is particularly suitable for mass production of personalized products, a manufacturing paradigm envisioned for the future.”

Wang calls this transfer learning a way to achieve group intelligence by which multiple learning agents (learners) collaborate to outperform a single learner. The technology can be applied to products using different materials.

The investigation is partially supported by two grants from the National Science Foundation totaling more than $1.3 million. One engages the NSF’s Research Infrastructure for Science and Engineering program (RISE) and Research Experiences for Undergraduates (REU) at the High-Performance Materials Institute. The platform aims to establish learning methodologies leading to high-performance lightweight composite structures in various size scales. The other NSF grant supports research on flexible manufacturing to meet diverse market demands.