Mechanical Behavior of Austenitic Steel under Multi-Axial Cyclic Loading.

Low-nickel austenitic steel is subjected to high-pressure torsion fatigue (HPTF) loading, where a constant axial compression is overlaid with a cyclic torsion. The focus of this work lies on investigating whether isotropic J2 plasticity or crystal plasticity can describe the mechanical behavior during HPTF loading, particularly focusing on the axial creep deformation seen in the experiment. The results indicate that a J2 plasticity model with an associated flow rule fails to describe the axial creep behavior. In contrast, a micromechanical model based on an empirical crystal plasticity law with kinematic hardening described by the Ohno-Wang rule can match the HPTF experiments quite accurately. Hence, our results confirm the versatility of crystal plasticity in combination with microstructural models to describe the mechanical behavior of materials under reversing multiaxial loading situations.

Wear Mechanism Classification Using Artificial Intelligence.

Understanding the acting wear mechanisms in many cases is key to predicting lifetime, developing models describing component behavior, or for the improvement of the performance of components under tribological loading. Conventionally scanning electron microscopy (SEM) and sometimes additional analytical techniques are performed in order to analyze wear appearances, i.e., grooves, pittings, surface films, and others. In addition, experience is required in order to draw the correct and relevant conclusions on the acting damage and wear mechanisms from the obtained analytical data. Until now, different types of wear mechanisms are classified by experts examining the damage patterns manually. In addition to this approach based on expert knowledge, the use of artificial intelligence (AI) represents a promising alternative. Here, no expert knowledge is required, instead, the classification is done by a purely data-driven model. In this contribution, artificial neural networks are used to classify the wear mechanisms based on SEM images. In order to obtain optimal performance of the artificial neural network, a hyperparameter optimization is performed in addition. The content of this contribution is the investigation of the feasibility of an AI-based model for the automated classification of wear mechanisms.