Artificial intelligence designs batteries that charge faster than humans can imagine

The AI, called ‘Dragonfly’, can combine chemicals together in a way that out-performed existing solutions

Adam Smith
Tuesday 04 October 2022 10:04 BST
Comments
Related: New Battery For Electric Cars Charges In Just 3 Minutes

Your support helps us to tell the story

From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.

At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.

The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.

Your support makes all the difference.

An artificial intelligence known as ‘Dragonfly’ has been used by researchers to design more efficient batteries.

Scientists at Carnegie Mellon have used the tool to design better electrolytes for lithium-ion batteries, which would allow the batteries to charge faster.

An electrolyte moves ions – atoms that have been charged by either gaining or losing an electron – between the two electrodes in a battery. Lithium ions are created at the negative electrode, the anode, and flow to the cathode where they gain electrons. When a battery charges, the ions move back to the anode.

Battery innovations can take years to come to fruition because there are so many different chemicals involved in their production. Working out the ratio of chemicals and optimising them for peak use can be an arduous task.

However, when the research team used an automated arrangement of pumps, valves, vessels, and other lab equipment to mix together three potential solvents and one salt, and then fed those results through ‘Dragonfly’, they found that the AI delivered six solutions that out-performed an existing electrolyte solution.

This gave the test cell a 13 per cent improvement over what is currently commercially available.

Electrolyte ingredients can be “mix[ed] and match[ed] in billions of ways,” Venkat Viswanathan, an associate professor at Carnegie Mellon, told Technology Review, but the Dragonfly artificial intelligence can make the work more efficient without much bias – as the system is not equipped with knowledge about chemistry.

It is hoped that Dragonfly can be improved so that it can run experiments with multiple goals, rather than a single one.

Researchers also believe that quantum batteries, which use a quantum mechanical system known as the micromaser to store energy charged through a stream of qubits, while simultaneously protecting against the risk of overcharging, could make batteries charge instantly.

The South Korean researchers have already calculated that quantum battery technology could reduce the home charging times of electric cars from 10 hours to just three minutes, while supercharger stations could fully recharge a vehicle in just 90 seconds.

In a study published earlier this year, the scientists noted how a quantum battery’s charging time actually decreases as the battery’s size gets bigger.

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in