Researcher Seeks to Add Longer Life to EV Batteries with New Algorithm
California state regulators agreed to ban the sale of any new gasoline-powered cars by 2035, but during a heatwave, the government asked people not to charge electric vehicles (EVs) until it ended, because it could drain the grid. Confusing, much?
Which begs the question of whether having all EVs on the road is even a good idea. Menwhile, a group of researchers at the University of Cambridge are looking deeper into expanding a battery’s life in electric vehicles using a new algorithm that relies on machine learning to help preserve battery health in EVs. They hope it will extend to every type of battery, according to azorobotics.com.
How You Drive Affects Longevity
Of course, the first battery one thinks of when it comes to listing batteries by importance is probably the lithium battery that powers most EVs for now. And basically, the researchers are measuring how the battery in your car is being used. How you drive affects the battery. Overall your driving methods will show up on the tests they are running. Like insurance companies give you a discount depending on how you drive while being monitored.
The algorithm is able to use pattern recognition and predictability models to see how various driving styles influence the performance of the vehicle’s battery. The researchers claim this could help extend battery life and charging cycles while also reducing charging times.
“This method could unlock value in so many parts of the supply chain, whether you’re a manufacturer, an end user, or a recycler, because it allows us to capture the health of the battery beyond a single number.” Dr. Alpha Lee, Group Leader, University of Cambridge
Monitoring Battery Health
The non-invasive probing method works by delivering a combination of electrochemical impedance spectroscopy measurements with probabilistic machine learning methods. The probe transmits high-dimensional pulses into the battery, then measures the electrical responses, which act as a biomarker and helps determine the health of a battery.
These electrical signals are converted into data which translates as the battery health before being entered into the algorithm, which could then use the data to make predictions about how the battery would perform.
After testing 88 commercially available batteries, the researchers found that their algorithm was accurate enough to make its predictions without any prior knowledge of battery usage history.
The team used lithium cobalt oxide (LCO) cells, but they report that the method could be applied across various battery chemistries in modern electric vehicles. This means that machine earning could not only optimize battery usage but also help ensure safer longer-lasting batteries.
“This method could unlock value in so many parts of the supply chain, whether you’re a manufacturer, an end user, or a recycler, because it allows us to capture the health of the battery beyond a single number, and because it’s predictive.” Dr. Alpha Lee, Group Leader, University of Cambridge
The technology will not only benefit EV drivers and manufacturers but could also be of use to companies with large EV fleets for distribution as well as helping address the climate crisis as it could encourage wider uptake of EV usage and support the energy transition away from fossil-based fuels.
It will be painful making the switch to the new technology for our transportation, just as it must have been for the horse and buggy business when the automobile became reliable and a better way to move people and things. But California’s grid will be improved enough to handle the charging needs.
read more at azorobotics.com