Molecular dynamics (MD) simulations are widely used to study tribological deformation at the atomic scale, but translating the resulting high-dimensional data into interpretable deformation pattern maps remains a largely manual and resource-intensive task. In this work, we present a data-driven workflow that aims to automate this process using unsupervised and supervised machine learning techniques. Grain-orientation-colored tomographic images from CuNi alloy simulations were first compressed into a 32-dimensional representation using an autoencoder, demonstrating that microstructural features can be retained under strong dimensionality reduction. The predictive model was trained independently using a dual-branch CNN–MLP architecture that combines image data with simulation metadata to classify dominant deformation patterns (transient and final states). The model achieves > 95% accuracy on spatially independent validation data. To assess generalization, entire simulations were excluded from training, yielding 100% final-state accuracy, as these conditions lie distant from regime boundaries. Evaluation on an artificial pressure–composition grid results in 87% accuracy, with misclassifications concentrated near regime boundaries. For transient states, the model achieves 68% accuracy on unseen simulations, increasing to > 92% when accounting for physically plausible misclassifications between adjacent regimes. A comparison with an image-only ResNet-50 model (~70% accuracy on spatially independent data, ~50% on unseen simulations) highlights the importance of integrating metadata. These results demonstrate that tribological deformation mechanisms can be automatically identified from microstructural data. This work provides a proof of concept for data-driven construction of deformation maps and represents a step toward predictive frameworks that may reduce reliance on large-scale MD simulations.

In this work, we present a fully atomistic approach to modeling a finishing process with the goal to shed light on aspects of work piece development on the microscopic scale, which are difficult or even impossible to observe in experiments, but highly relevant for the resulting material behavior. In a large-scale simulative parametric study, we varied four of the most relevant grinding parameters: The work piece material, the abrasive shape, the temperature, and the infeed depth. In order to validate our model, we compared the normalized surface roughness, the power spectral densities, the steady-state contact stresses, and the microstructure with proportionally scaled macroscopic experimental results. Although the grain sizes vary by a factor of more than 1,000 between experiment and simulation, the characteristic process parameters were reasonably reproduced, to some extent even allowing predictions of surface quality degradation due to tool wear. Using the experimentally validated model, we studied time-resolved stress profiles within the ferrite/steel work piece as well as maps of the microstructural changes occurring in the near-surface regions. We found that blunt abrasives combined with elevated temperatures have the greatest and most complex impact on near-surface microstructure and stresses, as multiple processes are in mutual competition here.