Each time you easily drive from point A to point B, you are not just having fun with the convenience of your automobile, but in addition the delicate engineering that makes it secure and reliable. Beyond its comfort and protective features lies a lesser-known yet crucial aspect: the expertly optimized mechanical performance of microstructured materials. These materials, integral yet often unacknowledged, are what fortify your vehicle, ensuring durability and strength on every journey.
Luckily, MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) scientists have thought of this for you. A team of researchers moved beyond traditional trial-and-error methods to create materials with extraordinary performance through computational design. Their recent system integrates physical experiments, physics-based simulations, and neural networks to navigate the discrepancies often found between theoretical models and practical results. Probably the most striking outcomes: the invention of microstructured composites — utilized in all the pieces from cars to airplanes — which are much tougher and sturdy, with an optimal balance of stiffness and toughness.
“Composite design and fabrication is prime to engineering. The implications of our work will hopefully extend far beyond the realm of solid mechanics. Our methodology provides a blueprint for a computational design that could be adapted to diverse fields similar to polymer chemistry, fluid dynamics, meteorology, and even robotics,” says Beichen Li, an MIT PhD student in electrical engineering and computer science, CSAIL affiliate, and lead researcher on the project.
An open-access paper on the work was published in earlier this month.
In the colourful world of materials science, atoms and molecules are like tiny architects, always collaborating to construct the long run of all the pieces. Still, each element must find its perfect partner, and on this case, the main focus was on finding a balance between two critical properties of materials: stiffness and toughness. Their method involved a big design space of two varieties of base materials — one hard and brittle, the opposite soft and ductile — to explore various spatial arrangements to find optimal microstructures.
A key innovation of their approach was using neural networks as surrogate models for the simulations, reducing the time and resources needed for material design. “This evolutionary algorithm, accelerated by neural networks, guides our exploration, allowing us to search out the best-performing samples efficiently,” says Li.
Magical microstructures
The research team began their process by crafting 3D printed photopolymers, roughly the dimensions of a smartphone but slimmer, and adding a small notch and a triangular cut to every. After a specialized ultraviolet light treatment, the samples were evaluated using a regular testing machine — the Instron 5984 — for tensile testing to gauge strength and adaptability.
Concurrently, the study melded physical trials with sophisticated simulations. Using a high-performance computing framework, the team could predict and refine the fabric characteristics before even creating them. The largest feat, they said, was within the nuanced strategy of binding different materials at a microscopic scale — a technique involving an intricate pattern of minuscule droplets that fused rigid and pliant substances, striking the precise balance between strength and adaptability. The simulations closely matched physical testing results, validating the general effectiveness.
Rounding the system out was their “Neural-Network Accelerated Multi-Objective Optimization” (NMO) algorithm, for navigating the complex design landscape of microstructures, unveiling configurations that exhibited near-optimal mechanical attributes. The workflow operates like a self-correcting mechanism, continually refining predictions to align closer with reality.
Nevertheless, the journey hasn’t been without challenges. Li highlights the difficulties in maintaining consistency in 3D printing and integrating neural network predictions, simulations, and real-world experiments into an efficient pipeline.
As for the following steps, the team is targeted on making the method more usable and scalable. Li foresees a future where labs are fully automated, minimizing human supervision and maximizing efficiency. “Our goal is to see all the pieces, from fabrication to testing and computation, automated in an integrated lab setup,” Li concludes.
Joining Li on the paper are senior creator and MIT Professor Wojciech Matusik, in addition to Pohang University of Science and Technology Associate Professor Tae-Hyun Oh and MIT CSAIL affiliates Bolei Deng, a former postdoc and now assistant professor at Georgia Tech; Wan Shou, a former postdoc and now assistant professor at University of Arkansas; Yuanming Hu MS ’18 PhD ’21; Yiyue Luo MS ’20; and Liang Shi, an MIT graduate student in electrical engineering and computer science. The group’s research was supported, partly, by Baden Aniline and Soda Factory (BASF).