top of page

A Battery Health Diagnostics
Platform Enabling Battery Circularity

Seamlessly Monitor and Evaluate the Impact of Aging on a

Battery’s Performance and Economic Value on the Cloud





Extending the life of a Battery Using Sophisticated Active Monitoring, Diagnostics and Estimation Models

Who We Are:

We are energy technologists leveraging advances in Artificial Intelligence and Machine Learning coupled with Physics-based Modeling to effectively monitor and predict battery aging. We work with leading Battery Scientists and Researchers to Mathematically Model Complex Battery properties.

Beyond battery ageing, our team has experience in renewable energy, investing, software, hardware and policy working with private sector and regulators.

Where We Operate:


After Use

Recycling and Repurposing


During Use
Health Monitoring: 

Performance and Reliability



Meeting all your safety and predictive maintenance needs in one platform

By leveraging our proprietary digital twin and active testing models, we bring transparency on the state of health of your battery. This in turn allows its capacity to be optimally utilized.


Battery Aging Overview


What is Battery Aging?

Batteries age in highly unique ways based on a variety of internal and external factors. As such, this makes estimating their remaining useful life (RUL) complex. While various battery management systems can control a battery’s operating conditions in a way to force a state of health outcome, the industry needs non-invasive solutions that can dynamically assess the impact of a battery’s aging.

What Factors Affect Battery Aging?

A few key factors that affect battery aging and performance include: 

(1) Operating Voltage

(2) Temperature or thermal management

(3) Charge transfer kinetics or C-rating

Why Does Aging Matter?

By understanding a battery’s profile, we can operate it to its full capacity without compromising on reliability and safety.  As a battery ages, its remaining useful life and degradation curve become incredibly complex and unpredictable.

Similarly, with new battery chemistry derivations, charging conditions, and operating environments, our industry needs adaptive models that can effectively predict and monitor battery aging and its impact. This is particularly true given the increased focus on battery circularity and sustainability. 



How We Do it?

Because a battery is effectively a closed system, there are physics-based properties that can be accurately modeled. The thermodynamic laws and outcomes hold true.

Our solution is built to operate as a digital twin operating a cloud-based virtual copy of the battery. By leveraging physics-based models we capture the relationship between materials and their stress factors. In doing so, we can build and monitor systems that mimic the behavior of a battery.  

Our model is fed with real-time usage data. Using this data, it can predict and optimize the aging behavior for different battery profiles with a high degree of fidelity making predictive maintenance possible.


Application to Second Use

There is a realization that the industry needs to promote battery circularity by extending a battery’s life and enabling the reuse of its remaining capacity in alternative applications. By understanding a battery’s state of health and remaining useful life, our diagnostics platform can play an important role in promoting battery circularity.

In modeling a battery's path of aging, our platform can effectively determine whether a battery is a good candidate for materials recycling or a second use after its first mission. By actively estimating a battery's state of health throughout its lifetime, we create the necessary data to enable this promising market.

Furthermore, we can extend our models to offer effective predictive maintenance to batteries that have a highly unpredictable and unconventional aging process.

bottom of page