Related Experiment Video
Updated: Sep 22, 2025
08:58
Atomic Force Microscopy Cantilever-Based Nanoindentation: Mechanical Property Measurements at the Nanoscale in Air and Fluid
Published on: December 2, 2022
3.2K
Bridging Fidelities to Predict Nanoindentation Tip Radii Using Interpretable Deep Learning Models
Claus O W Trost1, Stanislav Zak1, Sebastian Schaffer2,3
1Erich Schmid Institute of Materials Science, Austrian Academy of Sciences, Jahnstrasse 12, 8700 Leoben, Austria.
JOM (Warrendale, Pa. : 1989)
|May 25, 2022
Summary
Accurate nanoindentation measurements require precise tip radius characterization. This study introduces a data fusion method using machine learning to estimate tip radii in situ, improving data evaluation for miniaturized materials.
Area of Science:
- Materials Science
- Mechanical Engineering
- Computational Science
Background:
- Miniaturized materials require precise characterization.
- Nanoindentation is a key technique for measuring mechanical properties.
- Tip wear in nanoindentation affects measurement accuracy.
Purpose of the Study:
- To develop a method for in situ tip radius estimation in nanoindentation.
- To improve the accuracy of nanoindentation measurements.
- To interpret machine learning models for physical indentation phenomena.
Main Methods:
- A data fusion approach combining finite element simulations and experimental data.
- Utilizing an interpretable multi-fidelity deep learning model.
- In situ estimation of tip radii.
Main Results:
- The developed method accurately estimates tip radii in situ.
- The interpretable deep learning models capture physical indentation phenomena.
- Improved data evaluation for nanoindentation measurements.
Conclusions:
- The data fusion and deep learning approach offers a robust solution for tip radius characterization.
- This method enhances the reliability of nanoindentation for advanced materials.
- Accurate tip radius estimation is crucial for precise materials characterization.
