World Industrial Reporter

Innovation Delivered Daily

  • Innovation
    • Innovation Article Archive
    • Innovative Companies
    • Innovation Strategies
    • New Equipment Innovations
  • New Products
  • Additive Manufacturing
  • Markets
    • Market Trends
    • Tradeshow Reports
    • White Papers
  • Logistics
  • Newsletters
World Industrial Reporter » Innovation » Machine Learning Predicts Lifetime of Batteries

Machine Learning Predicts Lifetime of Batteries

May 9, 2022

battery 1688854 960 720

Argonne National Laboratory (ANL) scientists have adopted Machine Learning techniques to predict the lifetimes of a wide range of battery chemistries. 

According to the scientists, their new process requires just as little as a single cycle of experimental data to calculate battery lifetimes which should surely reduce battery development costs in the longer run.

In the current experiment, ANL utilized data from a set of 300 battery materials—including its patented nickel-manganese-cobalt (NMC)-based cathode—representing six different battery chemistries to accurately determine just how long different batteries will continue to cycle.

“For every different kind of battery application, from cell phones to electric vehicles to grid storage, battery lifetime is of fundamental importance for every consumer,” notes study author and computational scientist Noah Paulson.

​“Having to cycle a battery thousands of times until it fails can take years; our method creates a kind of computational test kitchen where we can quickly establish how different batteries are going to perform.”

“Right now, the only way to evaluate how the capacity in a battery fades is to actually cycle the battery,” adds co-author and ANL electrochemist Susan ​Babinec. ​“It’s very expensive and it takes a long time.”

According to Paulson, the process of establishing a battery lifetime can be tricky as batteries dont last forever and how long they last depends on the way that one uses them, as well as their design and their chemistry.

“Until now, there’s really not been a great way to know how long a battery is going to last. People are going to want to know how long they have until they have to spend money on a new battery.”

Talking about their new machine learning method, Paulson says: ​“One of the things we’re able to do is to train the algorithm on a known chemistry and have it make predictions on an unknown chemistry.”

“Say you have a new material, and you cycle it a few times. You could use our algorithm to predict its longevity, and then make decisions as to whether you want to continue to cycle it experimentally or not.”

“If you’re a researcher in a lab, you can discover and test many more materials in a shorter time because you have a faster way to evaluate them,” adds Babinec.

Image and content: Manuchi-Pixabay/ANL

Share on

Filed Under: Innovation

BRACE to Revitalize Old Concrete Structures
Ending Ammonia Leakages in Ships
Avatar

About Aruna Urs

Aruna is an industrial journalist. He writes on innovations that emanate at the intersection of science and engineering having a profound impact on the manufacturing sector.

Follow me
Suppliers

Beckhoff at Hannover Messe: Shaping Digital Transformation with PC-Based Control

Beckhoff is renowned for offering an extensive range of innovations that are now considered standard throughout the automation world. At Hannover Messe 2022, Beckhoff will be demonstrating how their New Automation Technology actively supports digital transformation with high-performance control and automation solutions for optimizing machines, plants, and buildings, as well as in the field of e-mobility.
View Supplier Email this Supplier

Track & Trace in Production and Logistics

From incoming goods through production to warehouse and shipping - seamless identification with RFID provides decision-relevant information in real time. With the intelligent linking of RFID information from production and intralogistics with MES and ERP systems, you increase your efficiency and gain the necessary transparency for lean processes and digitized supply chains.
View Supplier Email this Supplier

Distance and Position Measurements Up to 10 kHz

The optoNCDT 1900 laser sensors with integrated high-performance controller offer a unique combination of speed, compact design and accuracy. The intelligent surface control enables extremely stable measurement results even on challenging surfaces with changing reflections. Easy installation also in confined spaces.

View Supplier Email this Supplier

High Accuracy, Non-Contact, Absolute Linear Sensor

Santest Model GY series are high accuracy, non-contact, absolute type linear sensors employing magnetostrictive, Wiedemann effect. An ultra-sonic wave generated by a moving magnet near a magnetostrictive wave-guide on which the sonic wave propagates to the head of the transducer.
View Supplier Email this Supplier

Affordable and Fixed Installed IR Cameras

Our thermal imaging cameras with multiple wavelength options, automatic spot finder function and autonomous operation are ideal for condition monitoring of machines and plants up to 5432 °F.
View Supplier Email this Supplier

Subscribe

Get the latest WIR reports straight to your inbox.

Free Newsletter Subscription

Find us on the social web.

  • About Us
  • Contact Us
  • Advertise
  • Terms Of Use
  • Privacy Policy
FREE NEWSLETTER SUBSCRIPTION

Get the latest WIR reports straight to your inbox.

  • Innovation Article Archive
  • Innovation Strategies
  • Innovative Companies
  • New Products
  • Additive Manufacturing
  • Market Trends
  • Tradeshow Reports
  • White Papers
  • Logistics
  • Newsletters
  • Fun Stuff
  • Industry Links
Follow us

© 2022 Thomas Publishing Company. All rights reserved.

Posting....