BATTERY DEVELOPMENT GETS FAST CHARGED

Researchers discover how to accurately predict the CYCLE LIFE OF LITHIUM-ION BATTERIES using early cycle data and machine learning

BATTERY DEVELOPMENT GETS FAST CHARGED

One of the biggest bottlenecks in the development in lithium-ion batteries has been identifying just how long a newly designed battery will last. The standard test is to charge and discharge the cells until they die, however, as batteries have a long lifetime, this process can take many months and even years. It’s an expensive bottleneck in battery research.
Now, thanks to breakthrough research done by researchers at the USA’s Massachusetts Institute of Technology (MIT), Stanford University and the Toyota Research Institute (TRI), we will be able to accurately predict the lifespan of a new battery design after only a few charging cycles.
By combining comprehensive experimental data and artificial intelligence into an algorithm, using voltage declines and a few other factors among the early cycles, researchers can now predict a new battery design’s lifespan to within 9% of the actual cycle life. Based on just the first five charge/discharge cycles, the algorithm can also categorise batteries as either long or short life expectancy. In other words, whether the battery type is better suited to a mobile phone with a two-year battery-life requirement, or an electric vehicle that requires a battery life of 10 years.

AND THAT ALSO MEANS…

SPEEDIER DEVELOPMENT By reducing one of the most time- consuming steps – battery testing – by an order of magnitude, this machine-learning method will accelerate the research and development of new battery designs.
LOWER COSTS The last step in manufacturing batteries is called “formation” which can take days to weeks. Using the algorithm could shorten that significantly and lower the production cost.
BETTER FAST-CHARGING RATES One focus in the project was to and a better way to charge batteries in ten minutes, a feature that could accelerate the mass adoption of electric vehicles. By using the algorithm, the optimisation time can be cut by more than a factor of ten, significantly accelerating research and development.

THANKS TO BREAKTHROUGH RESEARCH WE WILL BE ABLE TO ACCURATELY PREDICT THE LIFESPAN OF A NEW BATTERY DESIGN AFTER ONLY A FEW CHARGING CYCLES

TOYOTA RESEARCH INSTITUTE

With US offices in Los Altos, Cambridge, and Ann Arbor, Toyota Research Institute was established in 2015 with the aim of strengthening Toyota’s research structure and has four initial mandates:

  • Enhance the safety of automobiles
  • Increase access to cars to those who otherwise cannot drive
  • Translate Toyota’s expertise in creating products for outdoor mobility into products for indoor mobility
  • Accelerate scientific discovery by applying techniques from artificial intelligence and machine learning

This battery research is part of TRI’s Accelerated Materials Design and Discovery programme that collaborates with research entities, universities and companies to use artificial intelligence to accelerate the design and discovery of advanced materials.
tri.global