When it comes to creating new materials for our modern needs, materials science engineers are confronted with a fundamental challenge: designing a material to be strong in one direction may result in structural weaknesses when facing stress from a different direction.
Assistant Professors Mir Jalil Razavi and Dehao Liu of Binghamton University are on a mission to tackle this challenge by harnessing the power of artificial intelligence and machine learning. Their goal? To propose innovative composite materials that not only meet but exceed specific mechanical behavior requirements.
“When we look at materials now, we usually tune mechanical properties in one direction,” Razavi said. “For example, they can absorb the shock in the ‘x’ direction, but they don’t pay attention to what will happen to the ‘y’ or ‘z’ direction. While we strengthen in one direction, maybe we’ll compromise their mechanical properties in the other directions.”
A recent $313,087 grant from the National Science Foundation is set to revolutionize the development of composite materials. The grant will fund the creation of a cutting-edge deep-learning model that integrates the fundamental principles of physical laws. This innovative model aims to customize the microarchitecture of composite materials, enabling precise tailoring of their properties.
“Imagine trying to mix two types of materials,” Liu said. “One is very solid and stiff. One is very soft, like if you mix stone and gel and then glue them together. How can you design the distribution of the stone and the gel? They can show different mechanical properties in different directions.”
Under the leadership of Razavi and Liu, the project will involve the development of thousands of mechanical computational models to train deep learning algorithms in the design of tailored composite materials. The team will evaluate and refine numerous suggestions to identify the most promising ones.
Furthermore, their collaborator, Associate Professor Yanyu Chen from the University of Louisville (Kentucky), will conduct validation experiments using advanced techniques such as additive manufacturing (3D printing), X-ray imaging, and stress testing.
This ambitious and groundbreaking project holds the promise of transforming the field of material science and engineering, paving the way for the development of next-generation composite materials with unprecedented performance and versatility.
“With this research, the goal would be that you give the material properties you are seeking in that different direction, and I inversely fabricate the material for you,” Razavi said.
The project originated from Razavi’s groundbreaking research on the human brain. His goal is to map the development of brain folds as the outer layer of faster-growing grey matter, responsible for higher-level thinking, expands over the inner layer of white matter, facilitating communication within the brain and with the rest of the body.
“Because brain tissue has different fiber tracts, it shows different mechanical properties in different directions,” he said. “When we want to fully characterize brain tissue, we need multiple loading cases to analyze that.”
The Binghamton team is confident that this machine learning research has the potential to revolutionize materials design. It could lead to the rapid development of new materials with tailored properties, opening doors to applications such as designing lighter structures, effective shock absorbers, and aerospace components.
“It could be used not just in advanced areas like the brain but also everyday materials like helmets and shoes,” Liu said. “If your shoes don’t feel comfortable, you can design your own personal pair using materials with different mechanical properties.”