NOMATEN HYBRID-SEMINAR April 16: Evaluating Tensile Properties of Metallic Materials from Indentation Parameters using an artificial neural network-based model
NOMATEN HYBRID-SEMINAR
online: https://meet.goto.com/NCBJmeetings/nomaten-seminar
In-person: NOMATEN seminar room (102)
Wednesday, APRIL 16th 2025 2 PM (CET)
Evaluating Tensile Properties of Metallic Materials from Indentation Parameters using an artificial neural network-based model
Prof. Jong-hyoung Kim
Pukyong National University, Republic of Korea
Abstract:
The instrumented indentation technique is a widely adopted method for assessing mechanical properties such as hardness, elastic modulus, and yield strength. Its ability to continuously measure penetration depth and applied force makes it particularly valuable for in-situ mechanical testing, especially at the nanoscale, enabling multi-purpose evaluations. However, challenges persist in accurately determining material properties due to phenomena such as plastic pileup and sink-in effects, which complicate the calibration of the contact depth—a critical factor for reliable material property assessments using indentation. In our study, we leverage machine learning (ML) to predict tensile properties, including elastic modulus and yield strength, directly from indentation parameters. To address the limitation of insufficient experimental data for model training, we generated a comprehensive dataset through finite element analysis (FEA) simulations. Recognizing the influence of geometric imperfections in indenter tips on indentation responses, we integrate transfer learning and data normalization techniques. These strategies enhance the robustness of the model, improving prediction accuracy for the targeted mechanical properties.
Bio:
Jong-hyoung Kim is an Assistant Professor working in the Department of Materials Science and Engineering at Pukyong National University (PKNU), Republic of Korea, since 2024. Kim obtained his BS and PhD degrees in materials science and engineering from SNU in 2012 and 2019, respectively. He was a postdoctoral researcher at Harvard University from 2019 to 2024. Kim can be reached by email at jhkim@pknu.ac.kr.

