AI techniques used to improve battery health and safety

April 06, 2020

Researchers have designed a machine learning method that can predict battery health with 10x higher accuracy than current industry standard, which could aid in the development of safer and more reliable batteries for electric vehicles and consumer electronics.

The researchers, from Cambridge and Newcastle Universities, have designed a new way to monitor batteries by sending electrical pulses into them and measuring the response. The measurements are then processed by a machine learning algorithm to predict the battery's health and useful lifespan. Their method is non-invasive and is a simple add-on to any existing battery system. The results are reported in the journal Nature Communications.

Predicting the state of health and the remaining useful lifespan of lithium-ion batteries is one of the big problems limiting widespread adoption of electric vehicles: it's also a familiar annoyance to mobile phone users. Over time, battery performance degrades via a complex network of subtle chemical processes. Individually, each of these processes doesn't have much of an effect on battery performance, but collectively they can severely shorten a battery's performance and lifespan.

Current methods for predicting battery health are based on tracking the current and voltage during battery charging and discharging. This misses important features that indicate battery health. Tracking the many processes that are happening within the battery requires new ways of probing batteries in action, as well as new algorithms that can detect subtle signals as they are charged and discharged.

"Safety and reliability are the most important design criteria as we develop batteries that can pack a lot of energy in a small space," said Dr Alpha Lee from Cambridge's Cavendish Laboratory, who co-led the research. "By improving the software that monitors charging and discharging, and using data-driven software to control the charging process, I believe we can power a big improvement in battery performance."

The researchers designed a way to monitor batteries by sending electrical pulses into it and measuring its response. A machine learning model is then used to discover specific features in the electrical response that are the tell-tale sign of battery aging. The researchers performed over 20,000 experimental measurements to train the model, the largest dataset of its kind. Importantly, the model learns how to distinguish important signals from irrelevant noise. Their method is non-invasive and is a simple add-on to any existing battery systems.

The researchers also showed that the machine learning model can be interpreted to give hints about the physical mechanism of degradation. The model can inform which electrical signals are most correlated with aging, which in turn allows them to design specific experiments to probe why and how batteries degrade.

"Machine learning complements and augments physical understanding," said co-first author Dr Yunwei Zhang, also from the Cavendish Laboratory. "The interpretable signals identified by our machine learning model are a starting point for future theoretical and experimental studies."

The researchers are now using their machine learning platform to understand degradation in different battery chemistries. They are also developing optimal battery charging protocols, powering by machine learning, to enable fast charging and minimise degradation.
-end-
This work was carried out with funding from the Faraday Institution. Dr Lee is also a Research Fellow at St Catharine's College.

University of Cambridge

Related Electric Vehicles Articles from Brightsurf:

Drop in pandemic CO2 emissions previews world of electric vehicles
When the SF Bay Area mandated shelter-in-place March 16, it created a natural experiment for UC Berkeley's Ron Cohen, who had established an inexpensive pollution sensor network in local neighborhoods.

Plugging in: Survey examines American perceptions of -- and resistance to -- electric vehicles
The latest installment of the Climate Insights 2020 report series finds that resistance to purchasing electric vehicles derives from a variety of sources -- and those reasons differ among some demographics.

New study shows converting to electric vehicles alone won't meet climate targets
Today there are more than 7 million electric vehicles (EVs) in operation around the world, compared with only about 20,000 a decade ago.

New composite material revs up pursuit of advanced electric vehicles
Scientists at Oak Ridge National Laboratory used new techniques to create a composite that increases the electrical current capacity of copper wires, providing a new material that can be scaled for use in ultra-efficient, power-dense electric vehicle traction motors.

Unmanned aerial vehicles help wheat breeders
Usually, breeders pick the best wheat lines by hand, but unmanned aerial vehicles that record certain measures of plant health can help breeders select wheat lines more efficiently.

Hydrogen vehicles might soon become the global norm
Roughly one billion cars and trucks zoom about the world's roadways.

Will automated vehicles cut parking revenue?
Benjamin Clark and Anne Brown of the University of Oregon used Seattle as a case study to find the association between TNC trips and on-street parking occupancy.

Influx of electric vehicles accelerates need for grid planning
A new PNNL report says the western US bulk power system can reliably support projected growth of up to 24 million electric vehicles through 2028, but challenges will arise as EV adoption grows beyond that threshold.

Battery breakthrough gives boost to electric flight and long-range electric cars
Researchers at the Department of Energy's Lawrence Berkeley National Laboratory (Berkeley Lab), in collaboration with Carnegie Mellon University, have developed a new battery material that could enable long-range electric vehicles that can drive for hundreds of miles on a single charge, and electric planes called eVTOLs for fast, environmentally friendly commutes.

Research determines financial benefit from driving electric vehicles
Motorists can save as much as $14,500 on fuel costs over 15 years by driving an electric vehicle instead of a similar one fueled by gasoline, according to a new analysis conducted by researchers at the U.S.

Read More: Electric Vehicles News and Electric Vehicles Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.