Scientists say they can use artificial intelligence to analyze atomic-level images of rechargeable batteries in a quest to figure out why they wear out over time. By studying materials that compose the battery extremely close up, they hope to streamline the process of studying and improving battery designs—which could eventually lead to an “indestructible” battery.
Specifically, the researchers looked at a type of rechargeable lithium-ion battery called “lithium iron phosphate” (LFP), which is fast becoming a popular option among electric car manufacturers due to its relatively low cost, low toxicity, and long lifespan. Because LFP electrodes do not contain cobalt or nickel, which are common (but difficult to procure) elements in many commercially-available batteries, they were the perfect medium for study. Improving outcomes for LFP batteries would probably accelerate the electric car industry, the scientists say, because they don’t require chemicals with constrained supply chains.
🔋You’re obsessed with energy. So are we. Let’s nerd out over it together.
But to improve these batteries, you have to butt up against the laws of physics and chemistry, themselves. “Constitutive laws underlie most physical processes in nature. However, learning such equations in heterogeneous solids (for example, due to phase separation) is challenging. One such relationship is between composition and eigenstrain, which governs the chemo-mechanical expansion in solids,” the researchers explain in their paper, published in the peer-reviewed journal Nature Materials last month.
In other words, the performance of any material boils down to both its chemistry and its physical interactions at the atomic scale. But the smaller you go, the harder it gets to predict how the material with behave. Understanding those interactions could theoretically help us achieve an “indestructible” battery, William Chueh, associate professor of materials science and engineering at Stanford University and senior author of the paper, posits in a prepared statement from Stanford.
That’s in contrast to the current crop of rechargeable lithium-ion batteries, which usually wear out after 1,000 cycles per the industry standard. That’s one phone or laptop charge every day or two for three to five years.
Basically, the scientists are identifying a point of figurative friction in the study of solid materials, like those that make up rechargeable lithium-ion batteries. Composition, or what materials are made of, must contend with “eigenstrain,” an umbrella term for factors that affect materials from the inside, rather than from outside mechanical forces. To learn more about LFP battery decomposition, researchers had to use the latest tools.
“Think of a battery as a ceramic coffee cup that expands and contracts when it heats up and cools off. Those changes eventually lead to flaws in the ceramic,” Chueh says in the statement. “These new high-resolution microscopy techniques allow us to see it, and AI helps us understand what is happening. For the first time, we can visualize and measure these forces at the single nanometer scale.”
Image analysis in this application is kind of like an MRI machine but for battery parts. Technologies like X-rays and electron microscopes allow scientists to take penetrative real-time images of batteries, and now, artificial intelligence is helping scientists analyze what they see.