Artificial intelligence (AI) can be used to “accurately predict” the remaining useful life of lithium-ion batteries before they start to wane, according to new research.
Scientists at the Massachusetts Institute of Technology, Stanford University and the Toyota Research Institute, said their work could speed up battery development and improve manufacturing to help new designs get to market faster.
Report co-lead author Peter Attia said potential applications of the research included shortening the validation time for new chemistries.
Attia said manufacturers could also use a sorting technique to grade batteries— using those with longer lifetimes in more demanding applications, such as electric vehicles, and selling them at higher prices.
“The standard way to test new battery designs is to charge and discharge the cells until they fail. Since batteries have a long lifetime, this process can take many months and even years. It’s an expensive bottleneck in battery research.”
Attia said the researchers’ approach could benefit the last step of battery manufacturing— formation— to “significantly shorten and lower the production cost”.
The scientists used “comprehensive experimental data and artificial intelligence” to reveal the key for accurately predicting the useful life of lithium-ion batteries before their capacities start to fade.
To generate the training dataset, the team charged and discharged batteries until each one reached the end of its useful life, which they defined as capacity loss of 20%.
Predictions were within 9% of the number of cycles the cells actually lasted, according to the team. “Separately, the algorithm categorised batteries as either long or short life expectancy based on just the first five charge/discharge cycles. Here, the predictions were correct 95% of the time.”
In this project, the team said the batteries lasted “anywhere from 150 to 2,300 cycles”. That variation was partly the result of testing different methods of fast charging but also due to manufacturing variability among batteries.
Details of the research are online.