anisotroKI
The creation of anisotropic material models for the structural simulation of plastic components requires an iterative calibration process in which results from specimen production (injection moulding) and material testing (tensile tests) are compared with corresponding simulation results (filling and structural simulation). This procedure requires considerable expertise from the user and generates significant costs. The aim of the project is to replace the currently required simulation programmes with suitable AI models and thus provide the user with a fully encapsulated and automated tool for creating and validating anisotropic material models.
Two AI models are to be developed and trained using simulation results from filling and structural simulations for different materials in order to predict both the local fibre orientations in injection-moulded test specimens and the mechanical behaviour of these test specimens in tensile tests. The prediction quality of the AI models will be validated using practical measurement data and additional simulations.
The project results are to be incorporated into commercial software in the form of an additional module, which will considerably simplify or even enable the use of integrative simulation and thus contribute to the more effective utilisation of the material potential. The project know-how can also be used in other areas of material modelling.