AIMM

Material optimization in product development

Nowadays, digital design methods are the central tools in product development. Realistic simulation models already exist for process simulation (e.g. injection molding simulation) and structural simulation (e.g. NVH and crash simulation), which precisely map physical phenomena and thus enable virtual tests. Using topology optimization, it is now possible to find material-efficient lightweight construction solutions in a highly automated process.

The latest algorithms in commercial simulation programs are also able to optimally select and use different materials. The simulations are based on material models that capture specific material properties such as plasticity, anisotropy and damage. However, the creation and operation of classic material models is currently a lengthy and time-consuming process.

Two factors in particular show that the material models need to be designed more efficiently: Firstly, the experimental determination of the parameters to be considered is time-consuming and cost-intensive, and secondly, the simulation processes require high computing power. However, if the models were simplified or their complexity reduced, the predictive quality of the simulation could suffer.

So how can the processes of material modeling and ultimately the entire product development process be made more innovative and efficient?

Development of a machine learning-based method for material modeling

The aim of the AIMM project is to supplement or replace conventional material modeling with alternative data-driven and therefore digital material modeling. By establishing machine learning (ML) methods in simulation-based vehicle development, complex modeling processes are to be simplified, which leads to a reduction in development times and enables digital functional validation (by a larger user group). Furthermore, computing times can be reduced, as iterative solutions of material equations can possibly be avoided through the use of ML models.

This means that calculations can be carried out more quickly, they require fewer hardware resources and several variants can be considered at the same time. In view of the use of new and complex materials, the aim is to overcome the limitations of conventional material modeling and provide a fast material description for new materials.

Accelerating the introduction of innovative materials through interdisciplinary collaboration

The interdisciplinary collaboration in ARENA2036 is revolutionizing the use of machine learning (ML) in the field of material modelling. Here, the disciplines of artificial intelligence, structural mechanics, numerical mathematics, test execution and metrology come together to integrate data-driven models into the product development process chain.

The data-based modeling method developed in the project enables the considerably faster and more cost-effective introduction of new materials. The complete automation of data generation and evaluation is an enabler for the full utilization of the method's potential. Complex modeling processes, which currently require a lot of time, technical and human resources, are simplified and the digital predictability of material behavior is improved. This will promote both the development and use of innovative materials and material combinations.

AIMM project objectives at a glance:

• Development of more precise and efficient material models by supplementing or substituting classic material models with ML-based models
• Development of new specific test concepts for the efficient generation of necessary training data
• Process automation to shorten the characterization and modelling phase
• Accelerated description and rapid use of new materials

Project partners and sponsors of AIMM

Project partners

• Large companies: Mercedes-Benz AG, ElringKlinger AG
• SME: DYNAmore GmbH
• Research institutes: TU Berlin-IDA, FhG EMI, University of Stuttgart-IFB and IFU
• Associated project partners: GOM GmbH, Renumics GmbH

AIMM is funded by the Federal Ministry of Economics and Climate Protection (formerly BMWi) under the funding code 19|20024A.