EV battery software firm Voltaiq launches open-source platform to accelerate safer production

Breana Noble
The Detroit News

Ann Arbor — Ever since Greg Less, technical director at the University of Michigan's Battery Lab, was hired in 2014, research and automotive partners have asked about the creation of a library for the results of innovative work being done in battery development.

"People were coming here to say, 'We need this. We need this. We need this. You need to develop it,'" Less said. "And I kept saying, 'I don't know how to develop that. I can't get enough data. I can't get access to the data and give it to you.'"

Voltaiq Inc., a California-based electric-vehicle battery analytics software firm and partner of the U-M lab, may have the answer.

Voltaiq Inc. CEO Tal Sholklapper (left) discusses with Greg Less, technical director of the University of Michigan's Battery Lab, how the company's software helps with the research being conducted at the lab.

The company on Thursday announced its "community edition," an open-source platform meant to house data sets collected from battery cells and computer code for algorithms and models used to assess their performance. Executives hope the new tool will get academic and industry research into the hands of manufacturers faster so they can build off it and increase the speed at which they ramp up EV battery production to meet automakers' aggressive EV launch timelines.

"It takes four to five years to get these factories up and running and producing at high yield," Voltaiq CEO Tal Sholklapper said during a tour of U-M's Battery Lab. "And that's just not fast enough."

Voltaiq Inc. CEO Tal Sholklapper discusses how the company's software helps with the research being conducted at the University of Michigan's Battery Lab.

Voltaiq's commercial platform has customers like Alphabet Inc.'s Google, Amazon.com Inc., Daimler AG's Mercedes-Benz, Facebook's Meta Platforms Inc. and Microsoft Corp. It's also worked with two of the Detroit Three automakers. Voltaiq's software gathers data being collected from battery cells and formats it in a useable way in real time to qualify cells, check for anomalies that could indicate fire risk and predict longevity of batteries that matters for vehicle warranties, used car buyers and second-life applications.

Validating that the machine learning and algorithms used to do those functions are accurate, however, can take enormous amounts of data. And at the rate new techniques and materials in battery technology is being developed, there isn't years to collect that data from qualifying batteries when vehicle launches need to happen in the immediate coming years to meet regulatory emissions and fuel economy requirements.

"In order to get to product launch dates, in order to really meet those deadlines that are coming up, and in order to have certainties in the warranties you've provided so you're derisking that so you don't have all the liability leftover," said Nicole Schauser, senior battery data scientist with Voltaiq, "we need better ways of qualifying the batteries faster."

Much of that data, however, already exists and is even available publicly. It's just dispersed and can take days or even months to find. The Voltaiq Community Edition integrates with GitHub Inc., an internet hosting service for software development, and seeks to create one searchable spot for available battery cell data as well as algorithms and machine-learning models that battery engineers can use to test or build off.

That's valuable for the work being collected and performed at U-M's Battery Lab, which tests hundreds of battery cells for automakers, startups and other organizations.

"What Voltaiq has come up with is that solution that people have been asking for," said Less, who was involved in the creation of the platform and uses Voltaiq's commercial platform in the U-M lab. "This is huge for the data industry and solving these problems that they're talking about it."

Greg Less is the technical director of the Battery Lab at the University of Michigan.

The platform offers data and information on reducing formation, the process stabilizing a battery cell that is the lengthiest part of manufacturing, taking days; algorithms assessing battery longevity; and models to detect anomalies. The hope is the platform will help to reduce the multi-year timetable battery manufacturers like LG Energy Solution and Panasonic Corp. have taken to get battery gigafactories up and running. Voltaiq also is talking with universities to incorporate the platform in coursework.

Andrew Weng (right), a third-year graduate student at the University of Michigan, used the Battery Lab to make battery cells and Voltaiq's software to analyze their performance.

Andrew Weng, a third-year U-M research student whose work on formation is available on the platform, says Voltaiq's platform allowed him to do research remotely during the pandemic and now the community edition offers a place to share it.

"We can take time to answer deeper questions," Weng said, "and have everyone benefit."


Twitter: @BreanaCNoble