A research team at Arizona State University (ASU) is working on a new approach to make the additive manufacturing of metal components more efficient and predictable through the targeted use of artificial intelligence. The focus is on developing a system that can use physically informed models to precisely predict the microstructure of stainless steel components during the 3D printing process.
The “CompAM: Enabling Computational Additive Manufacturing” project is funded by the US National Science Foundation and combines expertise from computer science and industrial manufacturing. The aim is to control the manufacturing process of components such as a complex-shaped ship’s propeller made of 316L stainless steel in such a way that specific material properties – in particular the grain size – can be reproducibly generated. The aim is to achieve grain diameters of less than one micrometer, which significantly influences the mechanical behavior.
“When we do metal printing, the quality of metal is actually dependent on the cooling curve,” said Aviral Shrivastava, a professor of computer science and engineering. “We want to control cooling so we can achieve the desired properties.”
“For many processes, there are actually a lot of studies that have been done. Physics is just a set of rules that are obeyed in the real world. What we’re doing is we taking these equations and combining them with data-driven learning to make the system learn better and faster.”
A major problem in metal processing is the dependence of material properties on thermal boundary conditions during printing. Conventional simulations to predict the material structure are computationally intensive and take weeks. The new system combines physical equations with data-driven learning to predict relevant parameters with less computational effort. This should make time-consuming trial-and-error procedures superfluous.
“The real value of this work is its ability to bridge research and industrial need,” Iquebal says. “In industries like aerospace, defense and energy, the performance of metal components isn’t negotiable — it’s mission-critical. By giving manufacturers faster, more accurate tools to predict and control material properties, we’re enabling a new era of precision manufacturing and reducing the costly guesswork that often slows innovation.”
“This project represents exactly what we strive for — innovation that’s deeply relevant to industry,” Ross Maciejewski, director of the School and Computing and Augmented Intelligence, says. “By combining artificial intelligence with materials science, our faculty members are charting a new course for advanced manufacturing. It’s a demonstration of how our research is propelling the future of engineering.”
The results are not only tested on an industrial scale, but are also made available for academic teaching and open source applications. The approach is exemplary for the increasing integration of AI in materials science-oriented manufacturing technology.
Metal Binder Jetting: The Key to Efficient Tool Manufacturing? - Exclusive Insights from INDO-MIM
Fill out the form and get instant access to an exclusive webinar on HP's Metal Binder Jetting 3D printing technology with exciting insights from INDO-MIM.Subscribe to our Newsletter
3DPresso is a weekly newsletter that links to the most exciting global stories from the 3D printing and additive manufacturing industry.
