BMW advancing use of AI in crash simulation

The BMW Group has partnered Mistral AI to advance the use of artificial intelligence (AI) in vehicle crash simulations.

It aims to improve quality, accuracy and speed in complex engineering tasks.

Each week, BMW says it runs thousands of virtual crash simulations, generating vast amounts of engineering data.

Over time, the automaker says this has resulted in a historical dataset of over one million gigabite of crash simulation data.

According to BMW, the system provides highly detailed insights into vehicle structures and material behaviour, forming a unique foundation for training an industrial AI model.

To scale this approach, BMW is focusing on so-called Large Industry Models (LIM). These are AI systems trained on industry specific engineering and simulation data from vehicle development and safety testing.

Unlike general‑purpose AI systems, LIMs embed domain‑specific knowledge directly into the AI model. This requires not only industrial data, but also deep domain expertise and technical environments that allow AI systems to learn directly from BMW’s development processes.