Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Optimized Digitalization for Environmentally NeutrAl Industrialization (ODEN-AI)

Reference number
Coordinator Linköpings universitet - Department of Management of Engineering
Funding from Vinnova SEK 4 953 315
Project duration November 2023 - November 2026
Status Ongoing
Venture Advanced digitalization - Enabling technologies
Call AI for advanced digitalization, 2

Purpose and goal

For sustainable automotive industry, environmentally friendly manufacturing is essential. The innovative company STILRIDE has developed a unique folding technique called “STILFOLD”, reducing the number of components and material usage. It saves costs, simplifies production, and reduces CO2 emissions. Automation is key but requires support systems. The ODEN-AI project will integrate digital twins, material models, and AI to optimize the folding and automation processes. It elevates the AI level within the mobility sector and can be adapted to other industries and processes.

Expected effects and result

ODEN-AI addresses the industrial need to predict material behaviour in complex manufacturing processes, to model said behaviour and to use the results to speed up process engineering. The project will increase the maturity level of AI in the mobility sector, by the proven integration of advanced AI tools, material modelling and digital twins. On the specific application level, the project will contribute to increasing sustainability in the mobility sector by supporting the STILFOLD development with needed tools for the scaling of the technology.

Planned approach and implementation

ODEN-AI will start by developing a material model for a selected material, focusing on mobility applications. This will be integrated into a digital twin with a physics engine, and incorporating the manufacturing method of STILFOLD. The material model will be designed as a physics-informed neural network, enabling predictions of complex interactions between material, process, and geometry. These models will be calibrated using real data and utilized to create a sample product. The findings will be shared through workshops, open-source platforms, and academic publications.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 27 May 2024

Reference number 2023-02674