RESEARCH NEWS
AIDED framework for metal 3D printing
Researchers at the University of Toronto in Canada are leveraging machine learning to improve additive manufacturing( or 3D printing). Led by Yu Zou, a professor of materials and engineering in the Faculty of Applied Science & Engineering, the research team has developed a new framework dubbed the Accurate Inverse process optimisation framework in laser Directed Energy Deposition( AIDED).
By predicting how the metal will melt and solidify to find optimal printing conditions, the new AIDED framework, detailed in a paper published in‘ Additive Manufacturing’,“ enhances the accuracy and robustness of the finished product.” The researchers say that the approach can be used to produce higher quality metal parts for industries that include aerospace, automotive, nuclear and healthcare.
“ The wider adoption of directed energy deposition, a major metal 3D printing technology, is currently hindered by the high cost of finding optimal process parameters through trial and error,” said PhD candidate Xiao Shang, first author of the new study.“ Our framework quickly identifies the optimal process parameters for various applications based on industry needs.”
A metal component being fabricated by laser-based 3D printing.
Image: Laboratory for Extreme Mechanics & Additive Manufacturing, University of Toronto.
Metal additive manufacturing uses a highpowered laser to selectively fuse fine metallic powder, building parts layer by layer from a precise 3D digital model. Metal additive manufacturing creates complex, highly customised components with minimal material waste.
AIDED operates in a closed-loop system where a genetic algorithm( a method that mimics natural selection to find optimal solutions) first suggests combinations of process parameters, which machine-learning models then evaluate for printing quality. The genetic algorithm checks these predictions, repeating the process until the best parameters are found.
“ We have demonstrated that our framework can identify optimal process parameters from customisable objectives in as little as one hour, and accurately predicts geometries from process parameters,” confirmed Shang.“ It is also versatile and can be used with various materials.”
To develop the framework, the researchers conducted numerous experiments to collect their vast datasets. The team is now working to develop an enhanced autonomous, or‘ selfdriving’, additive manufacturing system that operates with minimal human intervention.
“ By combining cutting-edge, additive manufacturing methods with artificial intelligence, we aim to create a novel closed loop controlled self-driving laser system. This system will be capable of sensing potential defects in real-time, predicting issues before they occur and automatically adjusting processing parameters to ensure high-quality production. It will be versatile enough to work with different materials and part geometries, making it a game-changer for manufacturing industries,” said Yu Zou. n
www. utoronto. ca
Better control of materials in production
As part of a Fraunhofer flagship project, researchers are developing a digital ecosystem that collects data along the entire value chain for raw materials with the goal of ensuring a sustainable and resilient supply. This makes it possible to reuse and recycle materials energy-efficiently and with as little loss as possible, the German research specialists told ISMR. At the Hannover Messe 2025 trade show, the research team presented a demonstrator that showcased different options offered by this ecosystem.
Six Fraunhofer institutes have joined forces in Fraunhofer’ s ORCHESTER flagship project. They are developing a digital ecosystem for industry that aggregates all the data along the value chain— from production of raw materials to delivery and processing of materials, manufacturing of the finished product and beyond to disposal and recycling. This data is combined with further information from production, such as the results of material testing or sensor data, and incorporated into a single platform.
“ The interaction of information and data from diverse sources makes the raw material cycles transparent. That allows companies
Above: The magnets used.
Image: © Fraunhofer IWKS. to manage their supply of metals more effectively on a day-to-day basis and respond to fluctuations in the supply chain early on. [ They can also ] harness the data to conserve resources, reduce CO₂ emissions and make production and use of raw materials socially sustainable,” said Fraunhofer scientists.
Dirk Helm, from the Fraunhofer Institute for Mechanics of Materials IWM, cited three of the project’ s concrete goals in production:“ We aim to increase the percentage of recycled materials used by at least 50 percent, lower the percentage of rare earths by at least 25 per cent and quintuple the selection of materials suitable for production on the whole.”
The Fraunhofer researchers showed how the digital ecosystem developed in the project works in practice with a demonstrator focusing on recycling powerful permanent magnets made of neodymium, a metal with a silvery sheen that belongs to the group of elements known as rare earths. These kinds of magnets are used in applications such as electric motors and wind turbines. The researchers are working to significantly reduce the amount of neodymium used in production by adding secondary raw materials, such as scrap metal magnets.
To calculate the mixture ratios needed for this, the Fraunhofer researchers have developed a simulation tool called MagnetPredictor.
The ORCHESTER flagship project is developing three demonstrators in all. The third demonstrator aims to increase the amount of secondary raw materials used in aluminium alloys in components for hydrogen pipelines, fuel cells and heat pumps, minimising their energy footprint. n
www. iwm. fraunhofer. de / en. html
ISMR June 2025 | ismr. net | 19