Skip to Content
Find More Like This
Return to Search

Battery Condition Monitor

Method for assessing State of Health, State of Charge, Remaining Useful Life

Idaho National Laboratory

Contact INL About This Technology


PDF Document PublicationTechnology Fact Sheet (1,044 KB)

Top-level block diagram showing processes for Battery Condition Monitor system.
Top-level block diagram showing processes for Battery Condition Monitor system.

Technology Marketing Summary

Batteries are becoming increasingly important for modern life, powering everything from portable electronic devices to transportation, along with hundreds of other applications. They are available in many sizes and chemistries, raising variability and complexity. As electrochemical batteries are age, chemical changes occur that effect the performance, effecting capacity and resistance. Measuring and tracking these changes can help estimate and predict battery health and useful remaining life, as well as optimize performance.

However, current battery health management and operation optimization techniques often exhibit large uncertainties and variation when assessing battery health, driving the adoption of preventative battery replacement strategies instead of more efficient management strategies like condition-based predictive maintenance. Those techniques often also require hours of measurement time, offload operational conditions, and analysis on separate systems, making them cumbersome to employ, especially for approximating real-time health or effecting real-time optimization. These problems combine to result in a substantial volume of used batteries with some remaining useful life being discarded and/or disposed of prematurely, as well as unnecessary maintenance being performed, greatly increasing battery system operation cost.


Researchers at Idaho National Laboratory have developed a new advanced methodology for real-time battery health analysis and performance optimization that utilizes embedded data analytics and machine learning techniques. The system combines active (e.g. impedance) with passive (e.g. temperature) measurements with computationally-efficient data analytics and machine learning to assess real time health under load operation. The system is capable of estimating several health and performance metrics including State-of-Charge (SOC), State-of-Health (SOH), and Remaining-Useful-Life (RUL). The capability supports the production of smart battery products with sufficient intelligence to allow for automated, real-time control and optimization.


·         Fast and precise assessment of battery health and performance conditions

·         Ability to achieving a more complete and accurate health metric

·         Support both battery diagnostics and prognostics with embedded predictive data analytics and learning

·         Adaptable to user needs and preferences for given applications

·         Amenable to include new and expanded electrochemical definitions for battery health

Applications and Industries

·         Plug-in electric vehicles

·         Portable electronics, such as phones, laptops, and wearables

·         Energy storage systems for:

o    Microgrids

o    Utilities

o    Communication Systems

o    Data centers

·         Unmanned Aerial Systems (UAS)

·         Battery infrastructures for energy and weapon systems

Technology Status
Technology IDDevelopment StageAvailabilityPublishedLast Updated

Contact INL About This Technology

To: Ryan Bills<>