MIT engineers have created a new aluminium alloy that can be 3D printed, tolerates extreme heat, and reaches strength levels far beyond conventional aluminium.
Tests show the material is five times stronger than aluminium made using standard manufacturing technique
The alloy is produced by combining aluminium with several other elements, chosen through a process that blends computer simulations with machine learning. This approach dramatically narrowed the search for the right recipe.
Traditional methods would have required evaluating more than one million possible material combinations, but the machine learning model reduced that number to just 40 promising options before identifying the optimal formula.
When the researchers printed the alloy and put it through mechanical testing, the results matched their predictions.
The printed metal performed on par with the strongest aluminium alloys currently produced through traditional casting.
A lighter metal with big industrial potential
The team believes the new printable aluminium could lead to stronger, lighter, and more heat-resistant components, including fan blades for jet engines.
Today, those blades are typically made from titanium, which is more than 50 percent heavier and can cost up to 10 times more than aluminum, or from advanced composite materials.
"If we can use lighter, high-strength material, this would save a considerable amount of energy for the transportation industry," says Mohadeseh Taheri-Mousavi, who led the research/
John Hart, the Class of 1922 Professor and head of MIT's Department of Mechanical Engineering, says the benefits extend well beyond aviation. "Because 3D printing can produce complex geometries, save material, and enable unique designs, we see this printable alloy as something that could also be used in advanced vacuum pumps, high-end automobiles, and cooling devices for data centres."
Using machine learning to redesign aluminium
In the study, Taheri-Mousavi applied machine learning methods to search for a stronger aluminium alloy. These tools sifted through data on elemental properties to uncover patterns and relationships that traditional simulations often miss.
By analysing only 40 candidate compositions, the machine learning system identified an alloy design with a much higher proportion of small precipitates than previous attempts.
This structure translated directly into greater strength, surpassing results obtained from more than one million simulations conducted without machine learning.
To create the alloy, the researchers turned to 3D printing rather than conventional casting, which involves pouring molten aluminium into a mould and allowing it to cool slowly. Longer cooling times allow precipitates to grow larger, which reduces strength.
The team showed that additive manufacturing, also known as 3D printing, allows the metal to cool and solidify much faster.
They focused on laser bed powder fusion (LBPF), a process in which layers of metal powder are selectively melted by a laser and rapidly solidify before the next layer is added. This rapid freezing preserves the fine precipitate structure predicted by the machine learning model.
"Sometimes we have to think about how to get a material to be compatible with 3D printing," says Hart.
"Here, 3D printing opens a new door because of the unique characteristics of the process – particularly, the fast cooling rate.
“Very rapid freezing of the alloy after it's melted by the laser creates this special set of properties."
Testing confirms record strength
To validate their design, the researchers ordered a batch of printable metal powder based on the new alloy formula.
The powder – made from aluminium combined with five additional elements – was sent to collaborators in Germany, who printed small test samples using their LPBF equipment.
Those samples were then shipped back to MIT for mechanical testing and microscopic analysis. The results confirmed the machine learning predictions.
The printed alloy was five times stronger than a cast version of the same material and 50 percent stronger than aluminium alloys designed using conventional simulations alone.
Microscopic imaging revealed a dense population of small precipitates, and the alloy remained stable at temperatures up to 400°C – an unusually high threshold for aluminium-based materials.
The research team is now applying the same machine learning techniques to refine other properties of the alloy.
"Our methodology opens new doors for anyone who wants to do 3D printing alloy design," Taheri-Mousavi says.
"My dream is that one day, passengers looking out their airplane window will see fan blades of engines made from our aluminium alloys."