MIT engineers team up to revolutionize rocket engines with new alloy and AI

A team of researchers from MIT, Carnegie Mellon University, and Lehigh University has received an award from the Defense Advanced Research Projects Agency (DARPA) to revolutionize the design of aerospace components.

The project is part of DARPA’s Multiobjective Engineering and Testing of Alloy Structures (METALS) program.

The focus of their research is on creating advanced design tools powered by artificial intelligence (AI). These tools aim to improve both the shape and material choices for complex aerospace structures.

Addressing traditional limitations

The research aims to address the limitations of traditional design methods, which typically use a single material for an entire component.

“Although a one-material approach may be optimal for a singular location in a component, it may leave other locations exposed to failure or may require a critical material to be carried throughout an entire part when it may only be needed in a specific location,” said the researchers in a press release.

For instance, the bladed disks (blisks) used in jet engines experience a wide range of temperatures and stresses, with some areas needing high strength while others require resistance to creep or fatigue.

“Currently, with standard manufacturing and design procedures, one must come up with a single magical material, composition, and processing parameters to meet ‘one part-one material’ constraints,” added Zachary Cordero, the project’s lead principal investigator and Associate Professor in MIT’s Department of Aeronautics and Astronautics.

“Desired properties are also often mutually exclusive prompting inefficient design tradeoffs and compromises.”

Compositionally graded alloys

The research team aims to solve these issues by using “compositionally graded alloys,” where the material composition changes gradually across the structure. This allows properties to be tailored to specific locations and needs.

“With the rapid advancement of additive manufacturing processes that are enabling voxel-based composition and property control, the team sees unique opportunities for leap-ahead performance in structural components are now possible,” mentioned the press release.

To design these complex structures, the researchers will combine their expertise in areas like machine learning, topology optimization, and generative modeling.

They aim to develop AI-driven design tools that can optimize both the shape and material composition of a component simultaneously.

Potential impact and implications

This innovative approach has the potential to significantly improve the performance of aerospace components. It could lead to engines that are lighter, more efficient, and more durable, which could expand possibilities in space exploration and advanced aircraft.

“This project merges classical mechanics analyzes with cutting-edge generative AI design technologies to unlock the plastic reserve of compositionally graded alloys,” highlighted Cordero. “This allows safe operation in previously inaccessible conditions.”

The implications of this research extend beyond aerospace, potentially spurring innovation across industries facing similar material demands. By demonstrating the potential of AI-driven design and advanced manufacturing, the researchers hope to inspire a new wave of innovation in engineering and materials science.

“It is a truly unique opportunity to build breakthrough capabilities that could underlie propulsion systems of the future, leveraging digital design and manufacturing technologies,” concluded A. John Hart, Professor and head of MIT’s Department of Mechanical Engineering.