Data-Driven Accelerated Parameter Identification for Chaboche-Type Visco-Plastic Material Models to Describe the Relaxation Behavior of Copper Alloys

Calibrating material models to experimental measurements is crucial for realistic computational analysis of components. For complex material models, however, optimization-based identification procedures can become time-consuming, particularly if the optimization problem is ill-posed.

The objective of this paper is to assess the feasibility of using machine learning to identify the parameters of a Chaboche-type material model that describes copper alloys. Specifically, we apply and analyze this identification approach using short-term uniaxial relaxation tests on a C19010 copper alloy.

A genetic algorithm forms the basis for identifying the parameters of the Chaboche-type material model. The approach is accelerated by replacing the numerical simulation of the experimental setup by a neural network surrogate. The neural networks-based approach is compared against a classic approach using both, synthetic and experimental data.

The results show that on the one hand, a sufficiently accurate identification of the material model parameters can be achieved by a classic but time-consuming genetic algorithm. On the other hand, it is shown that machine learning enables a much more time-efficient identification procedure, however, suffering from the ill-posedness of the identification problem.

Compared to classic parameter identification approaches, machine learning techniques can significantly accelerate the identification procedure for parameters of Chaboche-type material models with acceptable loss of accuracy.