Advanced microstructural characterization in high-strength steels via machine learning-enhanced high-speed nanoindentation and EBSD mapping

Aug 5, 2026

Upload by Oliver

This research investigates the nanoscopic features of Advanced High-Strength Steels (AHSS) using a bottom-up approach that combines high-speed nanoindentation mapping with a structure-property correlation workflow. Grain boundary effects on nanomechanical behavior are analyzed while addressing the limits of SEM-EBSD for distinguishing phases sharing similar crystal structures. A modular four-step, machine learning-enhanced protocol is developed and validated on ferritic-bainitic TRIP steels, enabling probabilistic phase statistics and supervised association between EBSD and nanoindentation. Image analysis and clustering refine phase/microstructure-to-property mapping, improving identification and quantification of martensite, austenite, bainite, and ferrite while reducing classification uncertainty.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

TRIP steels and AHSS microstructure

Austempering and phase stabilization

Mechanical performance and TRIP effect

Engineering relevance (automotive BIW)

Materials Today Communications 39 (2024) 109192 Contents lists available at ScienceDirect Materials Today Communications journal [homepage:](homepage: www.elsevier.com/locate/mtcomm)[ www.elsevier.com/locate/mtcomm](homepage: www.elsevier.com/locate/mtcomm) | Advanced microstructural characterization in high-strength steels via machine learning-enhanced high-speed nanoindentation and
EBSD mapping | | | | | --- | --- | --- | --- | | Federico Bruno a, b, Georgios Konstantoupoulos c, Edoardo Rossid, *, Gianluca Fiore a, Costas Charitidisc, Marco Sebastianid, Luca Belforteb, Mauro Palumbo a
a Department of Chemistry, University of Turin, Via Pietro Giuria 7, Torino 10125, Italy
b Materials Engineering and Sustainability, Centro Ricerche Fiat, C.R.F. S.C.p.A., Corso Settembrini 40, Torino 10135, Italy
c RNANO Lab.—Research Unit of Advanced, Composite, Nano-Materials & Nanotechnology, School of Chemical Engineering, National Technical University of Athens, Athens, Zographos GR-15773, Greece
d Department of Civil, Computer Science and Aeronautical Technologies Engineering, Roma Tre University, Via della Vasca Navale 79, Rome 00146, Italy | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Advanced High-Strength Steels High-speed nanoindentation EBSD
Machine learning | | This research investigates the nanoscopic features of Advanced High-Strength Steels (AHSS) through a bottom-up approach employing high-speed nanoindentation mapping (HSNM) to elucidate structure-property relationships. The influence of grain boundaries on nanomechanical properties was documented, highlighting the challenge of SEM-EBSD analysis in differentiating phases with identical crystal structures (BCC, FCC, etc.). Integrating SEMEBSD with HSNM in the same region of interest is essential for detailed insights into phase/microstructure distribution and accurate grain boundary identification. A modular four-step analysis protocol, designed and validated on ferritic-bainitic TRIP steels (TBF), leverages machine learning-enhanced HSNM for significant advancements in AHSS design. The initial phase involves the application of the expectation-maximization algorithm for probability distribution fitting of HSNM data, deriving primary mechanical phase statistics. This exclusively facilitates the correlation of elastic modulus and hardness for each phase/microstructure using nanoindentation data. Further refinement of phase/microstructure to mechanical property correlations was achieved through a supervised machine learning approach, ensuring precise association between EBSD and nanoindentation data. This includes detailed image analysis and clustering of nanoindentation data, enhancing the precision in phase recognition. This methodology addresses the critical challenges in developing 3rd Generation AHSS, aiming to fill the gap in accurately identifying and quantifying phases such as martensite, austenite, bainite, and ferrite, thereby reducing classification and measurement uncertainties. The approach contributes to the fundamental understanding of AHSS microstructures and provides a scalable framework for the comprehensive characterization of structural materials. | | 1. Introduction TRIP (Transformation Induced Plasticity) steels belong to the category of Advanced High-Strength Steels (AHSS). Their microstructure is characterized by a ferrite matrix interspersed with varying proportions of retained austenite, martensite, and bainite. The production of TRIP steels involves an isothermal process at an intermediate temperature, leading to bainite formation [1]. This specific thermal treatment is termed “austempering.” Bainite and ferrite predominance increases with higher silicon and aluminum contents. Conversely, the presence of martensite (unstable at room temperature) is reduced, while an increase in silicon and carbon content in the steel stabilizes the retained austenite, increasing its quantity [1]. In ter

FAQs

How does the method combine high-speed nanoindentation mapping and EBSD mapping?

It integrates SEM-EBSD with high-speed nanoindentation mapping in the same region of interest, enabling phase/microstructure distribution to be linked with nanomechanical properties and supporting accurate grain boundary identification.

What is the role of the expectation-maximization algorithm in the protocol?

The protocol uses expectation-maximization to fit probability distributions of HSNM data, deriving primary mechanical phase statistics that support correlation of elastic modulus and hardness for each phase/microstructure.

How does supervised machine learning improve phase recognition in TRIP steels?

Supervised machine learning refines the association between EBSD and nanoindentation data by performing detailed image analysis and clustering of nanoindentation measurements, improving the precision of phase recognition.

Aug 5, 2026

Upload by Oliver