California, United States – Nissan recently revealed that its officers in the Bay Area, California have been using artificial intelligence to fast-track research in automotive materials.
According to the automaker, the research and testing of new materials for car parts took 20 years and included numerous cycles of trial and error. However, using A.I. simulations, this timeframe can be cut down to just two years–1000 times faster than before.
“With machine learning and AI, you can simulate the properties of materials for a lot more cases than you can test experimentally, in a short time,” said Bala Radhakrishnan, principal researcher, simulation. “It can help you sample millions of materials, and then screen for candidates based on the properties that you want.”
Unlike other common A.I. models like ChatGPT which use generative learning to produce results, Nissan claims that its A.I. is instead a form of machine learning that simulates millions of automotive materials and runs tests on them to predict the most ideal properties.
Once the A.I. filters the content in terms of properties such as strength of materials, temperature and conductivity, a human engineer interprets the data and tests the materials to verify results.
With its A.I. model, Nissan plans to use machine learning capabilities to further its development of solid-state batteries for future electric vehicles. Specifically, the automaker plans to bring A.I. developed solid-state batteries to market by 2028.
