Researchers from Idaho National Laboratory are using machine learning and other advanced analysis to reduce electric vehicle charging times without damaging the battery, a press release revealed.

Despite the growing popularity of electric vehicles, many consumers hesitate to make the switch. One of the primary reasons is that it takes so much longer to power up an electric car than to gas up a vehicle powered up by an internal combustion engine. This hesitation is a reflection of range anxiety, and the solution for this anxiety is to get yourself a long-range electric vehicle, which can be a bit pricey.

Since speeding up the charging process can damage the battery and reduce its lifespan, scientists keep working on super-fast charging methods explicitly tailored to power each different type of electric vehicle battery in 10 minutes or less without damaging them.

Charging the lithium-ion batteries that fuel electric vehicles is a delicate balancing act. Drivers want to power up as quickly as possible to get back on the road, but with current technology, speeding up the process damages the batteries.

When a lithium-ion battery is being charged, lithium ions migrate from the cathode and anode sides of the device.

The batteries can be charged more quickly by making the lithium ions migrate faster, but sometimes the lithium ions don't fully move from the cathode to the anode. By doing so, lithium metal can build up, triggering early battery failure. It can also cause the cathode to wear and crack. All of these issues will reduce the battery's lifetime and the vehicle's effective range.

One solution to this enigma is to tailor the charging protocol to optimize speed while avoiding damage to various types of battery designs. But developing optimal protocols requires massive data on how different methods affect these devices' lifetimes, efficiencies, and safety.

The design and condition of batteries and the feasibility of applying a given charging protocol with the current electric grid infrastructure are vital variables in the studies.

"Fast charging is the key to increasing consumer confidence and overall adoption of electric vehicles," said Eric Dufek, Ph.D. from Idaho National Laboratory's Energy Storage & Electric Transportation Department, at the fall meeting of the American Chemical Society (ACS). "It would allow vehicle charging to be very similar to filling up at a gas station," he added.

Such an advance could help the U.S. reach its goal of making half of all vehicles sold powered by an electric or hybrid engine.

Dufek and his research team at Idaho National Laboratory have started using machine learning techniques that incorporate charging data to create unique charging protocols. By inputting information about the condition of many lithium-ion batteries during their charging and discharging cycles, the scientists trained the machine learning analysis to predict lifetimes and how different designs would eventually fail. The team then fed that data into the analysis to identify and optimize new protocols they test on actual batteries.

"We've significantly increased the amount of energy that can go into a battery cell in a short amount of time," says Dufek. "Currently, we're seeing batteries charge to over 90 percent in 10 minutes without lithium plating or cathode cracking."

Powering a nearly dead battery to 90 percent power in mere 10 minutes is not so impressive, as it means that it can get an electric vehicle to full charge in about half an hour. While many researchers are looking for methods to achieve this sort of super-fast charging, Dufek says that one advantage of their machine learning model is that it ties the protocols to the physics of what happens in a battery.

The researchers plan to use their model to develop even better methods and help design new lithium-ion batteries that are optimized for fast charging. Dufek says that the ultimate goal is for electric vehicles to be able to "tell" charging stations how to power up their specific batteries quickly and safely.

Powering each electric vehicle battery with a different charging method can be challenging to achieve, as many types of batteries might need to utilize other kinds of charging devices or methods.

Range anxiety is seen as a key limitation by many consumers looking to purchase an electric vehicle. The two routes to alleviate this anxiety are through the development of higher energy batteries and batteries capable of charging in 10 minutes or less. Achieving either target is difficult and presents a suite of challenges spanning from material degradation through cell and electrode design. When performing extreme fast charging, many types of degradation emerge including Li deposition and cathode cracking. Early detection and understanding using electrochemical methods are complicated, but possible if using a multitude of different signatures. Here we describe recent efforts to jointly align electrochemical methods with targeted characterization and advanced analysis to detect failure modes. Specifically, machine learning and other advanced analysis approaches show promise to reduce the time and effort needed to predict life, delineate failure modes, and provide input to electrochemical models. Here we discuss the use of machine learning to perform early failure mode classification on cells used for fast charge applications. Using this information, it is then possible to feedback information for the refinement of advanced charging protocols designed to minimize specific aging pathways.