Horiba Mira has selected Monolith as its AI partner for data-driven battery and powertrain development and testing. This partnership will provide a value-add techn ical offer for existing Hobriba Mira and Monolith customers as well as “an attractive option for for other OEM vehicle manufacturers and Tier 1 battery suppliers looking to enhance their development process”.
Through the agreement, Monolith will gain access to Horiba Mira’s in-house R&D battery test data to train and enhance its Anomaly Detector (AD) and Next Test Recommender (NTR) algorithms and demonstrate how the technology works at scale.
Furthermore, Horiba Mira’s advanced cloud-based data driven solutions will integrate Monolith’s tools to advance its product offerings. Its data driven digital twins, calibration optimizers and global real-world scenario generators provide an environment for efficient virtual development and testing. This reduces the need for expensive prototype vehicles and time required to develop calibrations for batteries and other powertrains.
Dr Richard Ahlfeld, CEO and founder of Monolith, said, “This partnership combines leaders in physical and AI-driven test and validation processes. The complementary tools and expertise of Horiba Mira and Monolith will accelerate battery development and cut testing in half for our joint clients using data-driven techniques.”
Guy Foulger, engineering and technology director, Horiba Mira, said, “As global automotive companies move toward a stronger focus on virtual development, partnerships which enhance our physical and virtual engineering capability are key to supporting customers with the robust tools they need.”
Monolith is already democratizing AI for engineering with its bespoke SaaS platform that uses no-code, machine-learning software, giving domain experts the power to leverage existing, valuable testing datasets for their product development. The platform analyzes and learns from this information, using it to generate accurate, reliable predictions that enable engineering teams to reduce time-intensive prototype testing programs.
