Battery performance can make or break the electric vehicle experience, from driving range to charging time to the lifetime of the car. For decades, advances in electric vehicle batteries have been limited by a major bottleneck: evaluation times. At every stage of the battery development process, new technologies must be tested for months or even years to determine how long they will last.
A machine learning-based method was developed that slashes testing times by 98 percent. Although the method was tested on battery charge speed, it can be applied to numerous other parts of the battery development pipeline and even to non-energy technologies. The program, based on only a few charging cycles, predicts how batteries would respond to different charging approaches. The software also decides in real time what charging approaches to focus on or ignore. By reducing both the length and number of trials, the researchers cut the testing process from almost two years to 16 days.
Designing ultra-fast-charging batteries is a major challenge, mainly because it is difficult to make them last. The intensity of the faster charge puts greater strain on the battery, which often causes it to fail early. To prevent this damage to the battery pack — a component that accounts for a large chunk of an electric car’s total cost — battery engineers must test an exhaustive series of charging methods to find the ones that work best. The new research sought to optimize this process. At the outset, the team saw that fast-charging optimization amounted to many trial-and-error tests — something that is inefficient for humans but the perfect problem for a machine.
The team reduced the time per cycling experiment. In a previous study, they found that instead of charging and recharging every battery until it failed — the usual way of testing a battery’s lifetime — they could predict how long a battery would last after only its first 100 charging cycles. This is because the machine learning system, after being trained on a few batteries cycled to failure, could find patterns in the early data that presaged how long a battery would last.
Second, machine learning reduced the number of methods they had to test. Instead of testing every possible charging method equally or relying on intuition, the computer learned from its experiences to quickly find the best protocols to test. By testing fewer methods for fewer cycles, the team found an optimal ultra-fast-charging protocol for the battery. In addition to dramatically speeding up the testing process, the computer’s solution was also better — and much more unusual — than what a battery scientist would likely have devised.
The approach could accelerate nearly every piece of the battery development pipeline, from designing the chemistry of a battery to determining its size and shape, to finding better systems for manufacturing and storage. This would have broad implications not only for electric vehicles but for other types of energy storage — a key requirement for making the switch to wind and solar power on a global scale.
The potential of the method extends beyond the world of batteries. Other big data testing problems, from drug development to optimizing the performance of X-rays and lasers, could also be accomplished by using machine learning optimization.
For more information, contact Mark Golden, Stanford Precourt Institute for Energy, at