Engineers at the Massachusetts Institute of Technology (MIT) (Cambridge, Massachusetts, USA) are working to develop a rapid screening system to test fracture resistance in billions of potential materials. MIT researchers hope the system could be used to develop stronger protective coatings or structural materials in the future.1
The research was financially supported by the U.S. Office of Naval Research and the Army Research Office.
For engineers developing new materials or protective coatings, there usually are billions of different possibilities to sort through. Lab tests or detailed computer simulations to determine their exact properties, such as toughness, can take hours, days, or more for each variation.
However, the researchers believe their artificial intelligence-based approach could reduce that to a matter of milliseconds, making it practical to screen vast arrays of candidate materials.
Atom-by-Atom Simulations
The focus of the MIT work was on predicting the way a material would break or fracture by analyzing the propagation of cracks through the material’s molecular structure.
Led by Environmental Engineering Professor and Department Head Markus J. Buehler, the research team spent years studying fractures and other failure modes in great detail.
“One of the specialties of my lab is to use what we call molecular dynamics simulations, or basically atom-by-atom simulations” of such processes, Buehler says.
These simulations provide a chemically accurate description of how fracturing happens, he says. But the process is slow, because it requires solving equations of motion for every single atom. “It takes a lot of time to simulate these processes,” he adds. As a result, the team decided to explore ways of streamlining that process by using a machine-learning system.
“We’re kind of taking a detour,” Buehler says. “We’ve been asking, what if you had just the observation of how fracturing happens [in a given material], and let computers learn this relationship itself?”
To do that, artificial intelligence (AI) systems need a variety of examples to use as a training set, to learn about the correlations between the material’s characteristics and its performance.
In this case, the researchers were looking at a variety of composite, layered coatings made of crystalline materials. The variables included the composition of the layers and the relative orientations of their orderly crystal structures, and the way those materials each responded to fracturing based on the molecular dynamics simulations. “We basically simulate, atom by atom, how materials break, and we record that information,” Buehler says.
They generated hundreds of such simulations with a wide variety of structures before subjecting each one to many different simulated fractures. Then, they fed large amounts of data about all these simulations into their AI system to see if it could discover the underlying physical principles and predict the performance of a new material that was not part of the training set.
Learning How Materials Fail
Ultimately, it did. “That’s the really exciting thing,” Buehler says. “Because the computer simulation through AI can do what normally takes a very long time using molecular dynamics, or using finite element simulations, which are another way that engineers solve this problem, and it’s very slow as well. So, this is a whole new way of simulating how materials fail.”
How materials fail is crucial information for any engineering project, Buehler emphasizes. Materials failures, such as fractures, are “one of the biggest reasons for losses in any industry.”
“For inspecting planes or trains or cars, or for roads or infrastructure, or concrete, or steel corrosion, or to understand the fracture of biological tissues, such as bone, the ability to simulate fracturing with AI, and doing that quickly and very efficiently, is a real game changer,” he says.
The improvement in speed produced by using this method is significant, according to Yu-Chuan Hsu, a research contributor from National Taiwan University (Taipei, Taiwan). “For single simulations in molecular dynamics, it has taken several hours to run the simulations,” Hsu says. “But in this artificial intelligence prediction, it only takes 10 milliseconds to go through all the predictions from the patterns, and show how a crack forms step by step.”
“Over the past 30 years or so, there have been multiple approaches to model crack propagation in solids, but it remains a formidable and computationally expensive problem," adds Pradeep Guduru, a professor of engineering at Brown University (Providence, Rhode Island, USA) who was not involved in the work. "By shifting the computational expense to training a robust machine-learning algorithm, this new approach can potentially result in a quick and computationally inexpensive design tool, which is always desirable for practical applications.”
Applications Beyond Fracturing
The method they developed is quite generalizable, Buehler says. “Even though in our paper we only applied it to one material with different crystal orientations, you can apply this methodology to much more complex materials,” he says. And while they used data from atomistic simulations, the system could also be used to make predictions on the basis of experimental data, such as images of a material undergoing fracturing.
“If we had a new material that we’ve never simulated before… if we have a lot of images of the fracturing process, we can feed that data into the machine-learning model as well,” Buehler says. Whatever the input, simulated or experimental, the AI system essentially goes through the evolving process frame by frame, noting how each image differs from the one before to learn the underlying dynamics, according to the researchers.
For example, as researchers use new facilities at MIT for fabricating and testing materials at nanoscale, vast amounts of new data about a variety of synthesized materials will be generated.
“As we have more and more high-throughput experimental techniques that can produce a lot of images very quickly, in an automated way, these kind of data sources can immediately be fed into the machine-learning model,” Buehler says. “We really think that the future will be one where we have a lot more integration between experiment and simulation, much more than we have in the past.”
The system could be applied not just to fracturing, as the team did in this initial demonstration, but to a wide variety of processes unfolding over time, he says, such as the diffusion of one material into another, or corrosion processes. The method could be a boon "any time where you have evolutions of physical fields, and we want to know how these fields evolve as a function of the microstructure,” Buehler says.
Source: MIT, news.mit.edu.
Reference
1 “Machine-Learning Tool Could Help Develop Tougher Materials,” MIT News, May 20, 2020, http://news.mit.edu/2020/machine-learning-develop-materials-0520 (June 18, 2020).