SAFECAR-ML – Semantic Change Description for Vehicle Development with ML-based Automatic Classification

BMBF-Project / Project start /

Today, most crash tests to evaluate vehicle safety are conducted virtually. Documenting the changes to the simulated vehicle models is particularly time-consuming and costly. The SAFECAR-ML project aims to simplify this process. By combining novel methods of artificial intelligence (AI) with technical knowledge from vehicle development, the project partners from Fraunhofer SCAI and the automotive industry want to standardize the processing of information for the documentation of virtual crash tests. With the help of machine learning (ML), it is already possible to semantically understand free text statements made by engineers. The resulting unstructured data needs to be standardized and linked to multimodal engineering data. The software developed in the project can then automatically derive further steps and recommendations for action.

© Fraunhofer SCAI, Model: Center for Collision Safety and Analysis (CCSA)
Chassis rails of a vehicle body serve an important function in a frontal collision: they distribute impact energy across the body structure, reducing the load on individual components. By adjusting the sheet thickness and geometry of the chassis rails (red: original version, green: software-optimized version) during the product development cycle, impact energy can be absorbed better, thereby enhancing the safety of the vehicle occupants.

Fraunhofer SCAI is contributing its extensive experience in machine learning and comparative analysis of simulation results to the project. The goal of SAFECAR-ML is to create a formal description of technical knowledge for product development. The cooperation with the automotive industry opens the door to further applications in computer-aided engineering.

Fraunhofer SCAI's project partner is SCALE GmbH in Ingolstadt. The car manufacturers AUDI, Volkswagen, and Porsche are associated partners.

The German Federal Ministry of Education and Research (BMBF) is funding the 30-month project as part of the "Erforschung, Entwicklung und Nutzung von Methoden der Künstlichen Intelligenz in KMU (KI4KMU)" program.

Project duration: 09/2024 until 02/2027