Webasto taps Monolith for AI battery pack test
R&D teams at automotive supplier Webasto are to use Monolith AI software to make battery module and pack testing more efficient for electric vehicles.
Integrating the Monolith AI tools into the development and production processes at Webasto will free up engineering time and improve the quality of EV battery packs.
Webasto builds more than 500 battery system prototypes per year, generating terabytes of raw test data from thousands of tests. However, this test data produced by Webasto is not in a form suited to train AI models. To effectively prepare the data for AI, Monolith engineers provide data collation and compatibility support to train AI models that Webasto’s R&D teams can use. The next step is to integrate automated data cleaning and real-time processing into the development and production processes.
AI recommendation engine slashes battery test requirements
There are a number of use cases identified by Webasto and Monolith for the AI testing, with an iImmediate focus on battery pack screw tightening. Each battery module contains 300-plus screws, with torque monitoring for tightening generating terabytes of data. Tightening and monitoring of screw connections presents an ideal first application for the large scale use of AI, freeing up senior engineer resources.
The two companies expect to work on other use cases together over the next 12 months for battery pack testing, and Monolith has a range of deals for its tools, including AI analysis of battery materials with About:Energy.
“The work we’re doing with Webasto sets a new benchmark for how a company can use AI effectively to improve processes and products. We’ve worked with them every step of the way to identify use cases, prepare data and train the in-house test and domain experts to get the most out of the Monolith platform. The result is an acceleration in battery validation and improved battery quality and performance,” said Dr. Richard Ahlfeld, CEO and Founder of Monolith
“There are many potential use cases for AI to speed the battery test and validation process,” said Markus Meiler, VP Research & Development at Webasto. “After an extensive evaluation, we found Monolith to be an excellent option for scaling AI across our R&D. The Monolith platform demonstrated the potential benefits of using our test data with AI and guided us through a workshop to identify the best potential use cases – becoming more than a tech supplier but an engineering partner.”
The Monolith platform reduces the amount of physical testing time and simulations required to successfully develop products such as a battery pack with highly complex, intractable physics throughout the design cycle. This uses limited engineering test data to identify areas where optimisation and development are required, without the extensive need for repetitive, time-consuming physical tests.
www.monolithai.com; www.webasto.com
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
