The healthcare, automotive and aerospace industries have not widely adopted additive manufacturing (AM) due to the high cost and lengthy process of testing and inspecting the parts, but that may change through the efforts of the
University of Central Florida (UCF) researcher Dazhong Wu, an associate professor of mechanical and aerospace engineering in the College of Engineering and Computer Science. Here he manages the Additive Manufacturing and Intelligent Systems Lab, where he and his team ‘develop smart manufacturing techniques’.
He has received a
Young Faculty Award from the Defence Advanced Research Projects Agency (DARPA) for his project artificial intelligence-enabled affordable and scalable AM part qualification. The award will include nearly $500,000 of funding for the two-year project with an optional $500,000 for a third year of work, depending on how the research progresses.
The goal of the project is to develop an efficient and cost-effective machine learning model that can predict the defects and mechanical performance of 3-D printed materials. Current metal AM processes use digital models and costly materials to build complex parts layer-by-layer; these then often undergo lengthy trial-and-error testing cycles that result in the destruction of parts. Mr Wu’s method mixes AI with AM to minimise the need for destructive testing and reduce inspection costs.
Mr Wu’s aim is that once his AI model is built, it can be implemented in various industries to transform how they manufacture critical components. He said: “I am hopeful that this AI-enabled AM qualification framework will be used across many industries, including aerospace and many more.
“Bringing costs down is crucial to the AM industry, but to do that we need to make sure every part consistently meets performance requirements. Using AI, we can predict the mechanical performance of 3-D printed parts with small amounts of destructive and non-destructive testing data. With this, we can ensure every part is consistent, reliable and less costly.”