Microstructure quality control of steels using deep learning
In quality control, microstructures are investigated rigorously to ensure structural integrity, exclude the presence of critical volume defects, and validate the formation of the target microstructure. For quenched, hierarchically-structured steels, the morphology of the bainitic and martensitic mic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-08-01
|
| Series: | Frontiers in Materials |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmats.2023.1222456/full |
| _version_ | 1797745362615664640 |
|---|---|
| author | Ali Riza Durmaz Ali Riza Durmaz Sai Teja Potu Sai Teja Potu Daniel Romich Johannes J. Möller Ralf Nützel |
| author_facet | Ali Riza Durmaz Ali Riza Durmaz Sai Teja Potu Sai Teja Potu Daniel Romich Johannes J. Möller Ralf Nützel |
| author_sort | Ali Riza Durmaz |
| collection | DOAJ |
| description | In quality control, microstructures are investigated rigorously to ensure structural integrity, exclude the presence of critical volume defects, and validate the formation of the target microstructure. For quenched, hierarchically-structured steels, the morphology of the bainitic and martensitic microstructures are of major concern to guarantee the reliability of the material under service conditions. Therefore, industries conduct small sample-size inspections of materials cross-sections through metallographers to validate the needle morphology of such microstructures. We demonstrate round-robin test results revealing that this visual grading is afflicted by pronounced subjectivity despite the thorough training of personnel. Instead, we propose a deep learning image classification approach that distinguishes steels based on their microstructure type and classifies their needle length alluding to the ISO 643 grain size assessment standard. This classification approach facilitates the reliable, objective, and automated classification of hierarchically structured steels. Specifically, an accuracy of 96% and roughly 91% is attained for the distinction of martensite/bainite subtypes and needle length, respectively. This is achieved on an image dataset that contains significant variance and labeling noise as it is acquired over more than 10 years from multiple plants, alloys, etchant applications, and light optical microscopes by many metallographers (raters). Interpretability analysis gives insights into the decision-making of these models and allows for estimating their generalization capability. |
| first_indexed | 2024-03-12T15:23:10Z |
| format | Article |
| id | doaj.art-ca120744d3574262a21747e7fcade34a |
| institution | Directory Open Access Journal |
| issn | 2296-8016 |
| language | English |
| last_indexed | 2024-03-12T15:23:10Z |
| publishDate | 2023-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Materials |
| spelling | doaj.art-ca120744d3574262a21747e7fcade34a2023-08-11T01:11:36ZengFrontiers Media S.A.Frontiers in Materials2296-80162023-08-011010.3389/fmats.2023.12224561222456Microstructure quality control of steels using deep learningAli Riza Durmaz0Ali Riza Durmaz1Sai Teja Potu2Sai Teja Potu3Daniel Romich4Johannes J. Möller5Ralf Nützel6Group of Meso and Micromechanics, Fraunhofer Institute for Mechanics of Materials IWM, Freiburg im Breisgau, GermanyChair for Micro and Materials Mechanics, University of Freiburg, Freiburg im Breisgau, GermanyGroup of Meso and Micromechanics, Fraunhofer Institute for Mechanics of Materials IWM, Freiburg im Breisgau, GermanyInstitute of Mechanics and Computational Mechanics, Leibniz University Hannover, Hannover, GermanyMaterials Technology, Schaeffler Technologies AG & Co. KG, Schweinfurt, GermanyMaterials Technology, Schaeffler Technologies AG & Co. KG, Schweinfurt, GermanyMaterials Technology, Schaeffler Technologies AG & Co. KG, Schweinfurt, GermanyIn quality control, microstructures are investigated rigorously to ensure structural integrity, exclude the presence of critical volume defects, and validate the formation of the target microstructure. For quenched, hierarchically-structured steels, the morphology of the bainitic and martensitic microstructures are of major concern to guarantee the reliability of the material under service conditions. Therefore, industries conduct small sample-size inspections of materials cross-sections through metallographers to validate the needle morphology of such microstructures. We demonstrate round-robin test results revealing that this visual grading is afflicted by pronounced subjectivity despite the thorough training of personnel. Instead, we propose a deep learning image classification approach that distinguishes steels based on their microstructure type and classifies their needle length alluding to the ISO 643 grain size assessment standard. This classification approach facilitates the reliable, objective, and automated classification of hierarchically structured steels. Specifically, an accuracy of 96% and roughly 91% is attained for the distinction of martensite/bainite subtypes and needle length, respectively. This is achieved on an image dataset that contains significant variance and labeling noise as it is acquired over more than 10 years from multiple plants, alloys, etchant applications, and light optical microscopes by many metallographers (raters). Interpretability analysis gives insights into the decision-making of these models and allows for estimating their generalization capability.https://www.frontiersin.org/articles/10.3389/fmats.2023.1222456/fullquality controlmicrostructuregrain sizesteelmartensitebainite |
| spellingShingle | Ali Riza Durmaz Ali Riza Durmaz Sai Teja Potu Sai Teja Potu Daniel Romich Johannes J. Möller Ralf Nützel Microstructure quality control of steels using deep learning Frontiers in Materials quality control microstructure grain size steel martensite bainite |
| title | Microstructure quality control of steels using deep learning |
| title_full | Microstructure quality control of steels using deep learning |
| title_fullStr | Microstructure quality control of steels using deep learning |
| title_full_unstemmed | Microstructure quality control of steels using deep learning |
| title_short | Microstructure quality control of steels using deep learning |
| title_sort | microstructure quality control of steels using deep learning |
| topic | quality control microstructure grain size steel martensite bainite |
| url | https://www.frontiersin.org/articles/10.3389/fmats.2023.1222456/full |
| work_keys_str_mv | AT alirizadurmaz microstructurequalitycontrolofsteelsusingdeeplearning AT alirizadurmaz microstructurequalitycontrolofsteelsusingdeeplearning AT saitejapotu microstructurequalitycontrolofsteelsusingdeeplearning AT saitejapotu microstructurequalitycontrolofsteelsusingdeeplearning AT danielromich microstructurequalitycontrolofsteelsusingdeeplearning AT johannesjmoller microstructurequalitycontrolofsteelsusingdeeplearning AT ralfnutzel microstructurequalitycontrolofsteelsusingdeeplearning |