Characterization of High-Speed Steels—Experimental Data and Their Evaluation Supported by Machine Learning Algorithms

X-ray diffractograms of high-speed steels are analyzed using machine learning algorithms to accurately classify various heat treatments. These differently heat-treated steel samples are also investigated by dilatometric analysis and by metallographic analysis in order to label the samples accordingl...

Full description

Saved in:
Bibliographic Details
Main Authors: Manfred Wiessner, Ernst Gamsjäger
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Metals
Subjects:
Online Access:https://www.mdpi.com/2075-4701/15/2/194
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850238718146772992
author Manfred Wiessner
Ernst Gamsjäger
author_facet Manfred Wiessner
Ernst Gamsjäger
author_sort Manfred Wiessner
collection DOAJ
description X-ray diffractograms of high-speed steels are analyzed using machine learning algorithms to accurately classify various heat treatments. These differently heat-treated steel samples are also investigated by dilatometric analysis and by metallographic analysis in order to label the samples accordingly. Both agglomerative hierarchical clustering and t-distributed stochastic neighbor embedding are employed to automatically classify preprocessed X-ray datasets. The clusters obtained by this procedure agree well with the labeled data. By supervised learning via a support vector machine, hyperplanes are constructed that allow separating the clusters from each other based on the X-ray measurements. The exactness of these hyperplanes is analyzed by cross-validation. The machine learning algorithms used in this work are valuable tools to separate different microstructures based on their diffractograms. It is demonstrated that the separation of martensitic, bainitic, and pearlitic microstructures is possible based on the diffractograms only by means of machine learning algorithms, while the same problem is error-prone when looking at the diffractograms only.
format Article
id doaj-art-e30aae86be354625aacaef919443b042
institution OA Journals
issn 2075-4701
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Metals
spelling doaj-art-e30aae86be354625aacaef919443b0422025-08-20T02:01:23ZengMDPI AGMetals2075-47012025-02-0115219410.3390/met15020194Characterization of High-Speed Steels—Experimental Data and Their Evaluation Supported by Machine Learning AlgorithmsManfred Wiessner0Ernst Gamsjäger1DUAL Analytics, Södingberg 282, 8152 Geistthal-Södingberg, AustriaChair of Mechanics, Montanuniversität Leoben, Franz-Josef Str. 18, 8700 Leoben, AustriaX-ray diffractograms of high-speed steels are analyzed using machine learning algorithms to accurately classify various heat treatments. These differently heat-treated steel samples are also investigated by dilatometric analysis and by metallographic analysis in order to label the samples accordingly. Both agglomerative hierarchical clustering and t-distributed stochastic neighbor embedding are employed to automatically classify preprocessed X-ray datasets. The clusters obtained by this procedure agree well with the labeled data. By supervised learning via a support vector machine, hyperplanes are constructed that allow separating the clusters from each other based on the X-ray measurements. The exactness of these hyperplanes is analyzed by cross-validation. The machine learning algorithms used in this work are valuable tools to separate different microstructures based on their diffractograms. It is demonstrated that the separation of martensitic, bainitic, and pearlitic microstructures is possible based on the diffractograms only by means of machine learning algorithms, while the same problem is error-prone when looking at the diffractograms only.https://www.mdpi.com/2075-4701/15/2/194high-speed steelX-ray diffractionagglomerative hierarchical clusteringsupport vector machinet-distributed stochastic neighbor embedding
spellingShingle Manfred Wiessner
Ernst Gamsjäger
Characterization of High-Speed Steels—Experimental Data and Their Evaluation Supported by Machine Learning Algorithms
Metals
high-speed steel
X-ray diffraction
agglomerative hierarchical clustering
support vector machine
t-distributed stochastic neighbor embedding
title Characterization of High-Speed Steels—Experimental Data and Their Evaluation Supported by Machine Learning Algorithms
title_full Characterization of High-Speed Steels—Experimental Data and Their Evaluation Supported by Machine Learning Algorithms
title_fullStr Characterization of High-Speed Steels—Experimental Data and Their Evaluation Supported by Machine Learning Algorithms
title_full_unstemmed Characterization of High-Speed Steels—Experimental Data and Their Evaluation Supported by Machine Learning Algorithms
title_short Characterization of High-Speed Steels—Experimental Data and Their Evaluation Supported by Machine Learning Algorithms
title_sort characterization of high speed steels experimental data and their evaluation supported by machine learning algorithms
topic high-speed steel
X-ray diffraction
agglomerative hierarchical clustering
support vector machine
t-distributed stochastic neighbor embedding
url https://www.mdpi.com/2075-4701/15/2/194
work_keys_str_mv AT manfredwiessner characterizationofhighspeedsteelsexperimentaldataandtheirevaluationsupportedbymachinelearningalgorithms
AT ernstgamsjager characterizationofhighspeedsteelsexperimentaldataandtheirevaluationsupportedbymachinelearningalgorithms