Cargando…

Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface

The precise identification of micro-features on 2.25Cr1Mo0.25V steel is of great significance for understanding the mechanism of hydrogen embrittlement (HE) and evaluating the alloy’s properties of HE resistance. Presently, the convolution neural network (CNN) of deep learning is widely applied in t...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Pan, Song, Yan, Chai, Mengyu, Han, Zelin, Zhang, Yu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8703304/
https://www.ncbi.nlm.nih.gov/pubmed/34947098
http://dx.doi.org/10.3390/ma14247504
_version_ 1784621431375527936
author Liu, Pan
Song, Yan
Chai, Mengyu
Han, Zelin
Zhang, Yu
author_facet Liu, Pan
Song, Yan
Chai, Mengyu
Han, Zelin
Zhang, Yu
author_sort Liu, Pan
collection PubMed
description The precise identification of micro-features on 2.25Cr1Mo0.25V steel is of great significance for understanding the mechanism of hydrogen embrittlement (HE) and evaluating the alloy’s properties of HE resistance. Presently, the convolution neural network (CNN) of deep learning is widely applied in the micro-features identification of alloy. However, with the development of the transformer in image recognition, the transformer-based neural network performs better on the learning of global and long-range semantic information than CNN and achieves higher prediction accuracy. In this work, a new transformer-based neural network model Swin–UNet++ was proposed. Specifically, the architecture of the decoder was redesigned to more precisely detect and identify the micro-feature with complex morphology (i.e., dimples) of 2.25Cr1Mo0.25V steel fracture surface. Swin–UNet++ and other segmentation models performed state-of-the-art (SOTA) were compared on the dimple dataset constructed in this work, which consists of 830 dimple scanning electron microscopy (SEM) images on 2.25Cr1Mo0.25V steel fracture surface. The segmentation results show Swin–UNet++ not only realizes the accurate identification of dimples but displays a much higher prediction accuracy and stronger robustness than Swin–Unet and UNet. Moreover, efforts from this work will also provide an important reference value to the identification of other micro-features with complex morphologies.
format Online
Article
Text
id pubmed-8703304
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87033042021-12-25 Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface Liu, Pan Song, Yan Chai, Mengyu Han, Zelin Zhang, Yu Materials (Basel) Article The precise identification of micro-features on 2.25Cr1Mo0.25V steel is of great significance for understanding the mechanism of hydrogen embrittlement (HE) and evaluating the alloy’s properties of HE resistance. Presently, the convolution neural network (CNN) of deep learning is widely applied in the micro-features identification of alloy. However, with the development of the transformer in image recognition, the transformer-based neural network performs better on the learning of global and long-range semantic information than CNN and achieves higher prediction accuracy. In this work, a new transformer-based neural network model Swin–UNet++ was proposed. Specifically, the architecture of the decoder was redesigned to more precisely detect and identify the micro-feature with complex morphology (i.e., dimples) of 2.25Cr1Mo0.25V steel fracture surface. Swin–UNet++ and other segmentation models performed state-of-the-art (SOTA) were compared on the dimple dataset constructed in this work, which consists of 830 dimple scanning electron microscopy (SEM) images on 2.25Cr1Mo0.25V steel fracture surface. The segmentation results show Swin–UNet++ not only realizes the accurate identification of dimples but displays a much higher prediction accuracy and stronger robustness than Swin–Unet and UNet. Moreover, efforts from this work will also provide an important reference value to the identification of other micro-features with complex morphologies. MDPI 2021-12-07 /pmc/articles/PMC8703304/ /pubmed/34947098 http://dx.doi.org/10.3390/ma14247504 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Liu, Pan
Song, Yan
Chai, Mengyu
Han, Zelin
Zhang, Yu
Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface
title Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface
title_full Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface
title_fullStr Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface
title_full_unstemmed Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface
title_short Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface
title_sort swin–unet++: a nested swin transformer architecture for location identification and morphology segmentation of dimples on 2.25cr1mo0.25v fractured surface
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8703304/
https://www.ncbi.nlm.nih.gov/pubmed/34947098
http://dx.doi.org/10.3390/ma14247504
work_keys_str_mv AT liupan swinunetanestedswintransformerarchitectureforlocationidentificationandmorphologysegmentationofdimpleson225cr1mo025vfracturedsurface
AT songyan swinunetanestedswintransformerarchitectureforlocationidentificationandmorphologysegmentationofdimpleson225cr1mo025vfracturedsurface
AT chaimengyu swinunetanestedswintransformerarchitectureforlocationidentificationandmorphologysegmentationofdimpleson225cr1mo025vfracturedsurface
AT hanzelin swinunetanestedswintransformerarchitectureforlocationidentificationandmorphologysegmentationofdimpleson225cr1mo025vfracturedsurface
AT zhangyu swinunetanestedswintransformerarchitectureforlocationidentificationandmorphologysegmentationofdimpleson225cr1mo025vfracturedsurface