Now Reading
How This 3-Year-Old Startup Is Using AI/ML To Deploy & Manage 25,000 Battery Management Systems

How This 3-Year-Old Startup Is Using AI/ML To Deploy & Manage 25,000 Battery Management Systems

Prajakta Hebbar

Since the last decade, the auto industry has experienced technological breakthroughs that have transformed the automotive landscape. Keeping up with the growing demand, almost every major carmaker has launched or has plans to dive into the electric vehicles market.

Mumbai -based ION Energy was born out of the desire to tackle the threat of climate degradation by enabling a much more environment-friendly mobility solution. Founded in 2016, ION acquired an 8-year-old French Battery Management System (BMS) developer – Freemens SAS, in a first of its kind cross-border acquisition. In 2018, ION came out of stealth mode and unveiled its first product UDYR, a portable battery for electric scooters and started commercialising its flagship BMS platform.

To know more about this industry, we got in touch with Akhil Aryan, co-founder and CEO at ION Energy for our weekly column Deep Dive. During the interaction, Aryan talked about has also talked about how ION is successfully utilising artificial intelligence and machine learning to deploy and manage 25,000 BMSs and is empowering 60+ organisations in 12 countries across including south-east Asia, North America and Europe.

What Does ION Energy Do?

ION Energy is an advanced battery management and intelligence platform. It is focused on building technologies that improve the life and performance of lithium-ion batteries that power electric vehicles and energy storage systems. 



The Tech Stack

ION Energy’s flagship BMS platform blends advanced electronics, machine learning software, artificial intelligence and data science with deep domain expertise in energy storage. Aryan explains, “The key differentiator – our battery intelligence platform Edison Analytics, uses real-time simulations and visualizations designed to extend battery life by up to 40% and reduce the overall ownership cost, thus boosting ROI.” He adds that Edison delivers descriptive, diagnostic, predictive and prescriptive analytics.

“We have a team of 20 hardware, firmware, mechanical, software engineers and battery experts,” says Aryan proudly.

The programming languages that ION most commonly uses on the technology side, are Embedded C for anything that’s related to embedded software. On the Frontend side, they use telematics gateway — ION Lens, and their battery intelligence and analytics platform – Edison Analytics, which uses Python and MEAN stack, hosted on the cloud.

ION’s BMS consists of a microcontroller and a bunch of sensors on the hardware so the technology involved is interfacing with this microcontroller through all these sensors and then interfacing this BMS with the battery pack. The core functions that a BMS performs include – data acquisition, protection, storage, and communication. 

In terms of the software used, there are various algorithms that run inside the microcontroller which is used to compute certain parameters of the battery such as the state of charge, state of health, range, etc.


Stay Connected

Get the latest updates and relevant offers by sharing your email.

Training Model

“We recently applied NASA Data sets to Battery Prognostics and Health Management (PHM),” begins Aryan.

See Also

He further explains that the State-of-Health (SoH) of a lithium-ion battery is one of the most complex and critical parameters for the Battery Management System. Essentially, there are two ways to estimate the state-of-health of batteries, they are physics-based methods and data-driven methods. 

Physics-based methods require an understanding of the physical rules of the system, the exact formulas that represent the system. Over a period of time, they become highly complex and require extensive time and resources, which may not be suitable in real-world applications. However, the data-driven models are less complex and are based on empirical lifetime data of the operation of the system. 

“We have used both the approaches on public data sets made available by NASA,” he adds. 

Talent Management

Initially, when ION began operations, one of the biggest challenges they faced was grooming technical talent in-house. Aryan says that there weren’t many engineers who had expertise in the EV sector and the number of engineers who had knowledge in AI and analytics was low as well. “When a new market starts shaping up, the talent pool is not mature and so it’s difficult to make significant progress on technology unless there is senior leadership in-house grooming talent,” says Aryan.

He says that is why they had to train them from the ground-up and provide their knowledge as well within the sector. This helped in creating the core team that today also helps train any new engineer that is hired by the firm. “We hope that in the future, there will be more experts in the EV sector in particular with colleges like COEP (Pune), Cummins College of Engineering for Women and institutes like IITs beginning courses specifically to EVs,” he says.

What Do You Think?

If you loved this story, do join our Telegram Community.


Also, you can write for us and be one of the 500+ experts who have contributed stories at AIM. Share your nominations here.
What's Your Reaction?
Excited
7
Happy
2
In Love
1
Not Sure
0
Silly
0

Copyright Analytics India Magazine Pvt Ltd

Scroll To Top