Bridging Fidelities to Predict Nanoindentation Tip Radii Using Interpretable Deep Learning Models

TL;DR

This paper introduces an interpretable deep learning approach that combines simulations and experimental data to accurately predict nanoindentation tip radii, enhancing material characterization precision.

Contribution

It presents a novel multi-fidelity deep learning method that fuses simulation and experimental data for in situ tip radius estimation, improving interpretability and accuracy.

Findings

Accurately predicts tip radii using deep learning.

Models interpret physical indentation phenomena.

Enhances precision in nanoindentation measurements.

Abstract

As the need for miniaturized structural and functional materials has increased,the need for precise materials characterizaton has also expanded. Nanoindentation is a popular method that can be used to measure material mechanical behavior which enables high-throughput experiments and, in some cases, can also provide images of the indented area through scanning. Both indenting and scanning can cause tip wear that can influence the measurements. Therefore, precise characterization of tip radii is needed to improve data evaluation. A data fusion method is introduced which uses finite element simulations and experimental data to estimate the tip radius in situ in a meaningful way using an interpretable multi-fidelity deep learning approach. By interpreting the machine learning models, it is shown that the approaches are able to accurately capture physical indentation phenomena.