001047296 001__ 1047296
001047296 005__ 20251124095637.0
001047296 0247_ $$2doi$$a10.1016/j.matchar.2025.115645
001047296 0247_ $$2ISSN$$a1044-5803
001047296 0247_ $$2ISSN$$a1873-4189
001047296 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-04211
001047296 0247_ $$2WOS$$aWOS:001439061700001
001047296 037__ $$aFZJ-2025-04211
001047296 082__ $$a670
001047296 1001_ $$0P:(DE-HGF)0$$aSafdar, Mutahar$$b0
001047296 245__ $$aAccelerated quantification of reinforcement degradation in additively manufactured Ni-WC metal matrix composites via SEM and vision transformers
001047296 260__ $$aNew York, NY$$bScience Direct$$c2025
001047296 3367_ $$2DRIVER$$aarticle
001047296 3367_ $$2DataCite$$aOutput Types/Journal article
001047296 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1761206280_25187
001047296 3367_ $$2BibTeX$$aARTICLE
001047296 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001047296 3367_ $$00$$2EndNote$$aJournal Article
001047296 520__ $$aMachine learning (ML) applications have shown potential in analyzing complex patterns in additively manufactured (AMed) structures. Metal matrix composites (MMC) offer the potential to enhance functional parts through a metal matrix and reinforcement particles. However, their processing can induce several co-existing anomalies in the microstructure, which are difficult to analyze through optical metallography. Scanning electron microscopy (SEM) can better highlight the degradation of reinforcement particles, but the analysis can be labor-intensive, time-consuming, and highly dependent on expert knowledge. Deep learning-based semantic segmentation has the potential to expedite the analysis of SEM images and hence support their characterization in the industry. This capability is particularly desired for rapid and precise quantification of defect features from the SEM images. In this study, key state-of-the-art semantic segmentation methods from self-attention-based vision transformers (ViTs) are investigated for their segmentation performance on SEM images with a focus on segmenting defect pixels. Specifically, SegFormer, MaskFormer, Mask2Former, UPerNet, DPT, Segmenter, and SETR models were evaluated. A reference fully convolutional model, DeepLabV3+, widely used on semantic segmentation tasks, is also included in the comparison. A SEM dataset representing AMed MMCs was generated through extensive experimentation and is made available in this work. Our comparison shows that several transformer-based models perform better than the reference CNN model with UPerNet (94.33 % carbide dilution accuracy) and SegFormer (93.46 % carbide dilution accuracy) consistently outperformed the other models in segmenting damage to the carbide particles in the SEM images. The findings on the validation and test sets highlight the most frequent misclassification errors at the boundaries of defective and defect-free pixels. The models were also evaluated based on their prediction confidence as a practical measure to support decision-making and model selection. As a result, the UPerNet model with the Swin backbone is recommended for segmenting SEM images from AMed MMCs in scenarios where accuracy and robustness are desired whereas the SegFormer model is recommended for its lighter design and competitive performance. In the future, the analysis can be extended by including higher capacity as well as smaller models in the comparison. Similarly, variations in specific hyperparameters can be investigated to reinforce the rationale of selecting a specific configuration.
001047296 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001047296 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001047296 7001_ $$0P:(DE-Juel1)196697$$aKazimi, Bashir$$b1$$ufzj
001047296 7001_ $$0P:(DE-Juel1)180323$$aRuzaeva, Karina$$b2$$ufzj
001047296 7001_ $$0P:(DE-HGF)0$$aWood, Gentry$$b3
001047296 7001_ $$0P:(DE-HGF)0$$aZimmermann, Max$$b4
001047296 7001_ $$0P:(DE-HGF)0$$aLamouche, Guy$$b5
001047296 7001_ $$0P:(DE-HGF)0$$aWanjara, Priti$$b6
001047296 7001_ $$0P:(DE-Juel1)186075$$aSandfeld, Stefan$$b7$$ufzj
001047296 7001_ $$0P:(DE-HGF)0$$aZhao, Yaoyao Fiona$$b8$$eCorresponding author
001047296 773__ $$0PERI:(DE-600)1491951-5$$a10.1016/j.matchar.2025.115645$$gVol. 229, p. 115645 -$$nPart B$$p115645 -$$tMaterials characterization$$v229$$x1044-5803$$y2025
001047296 8564_ $$uhttps://juser.fz-juelich.de/record/1047296/files/1-s2.0-S1044580325009349-main.pdf$$yOpenAccess
001047296 909CO $$ooai:juser.fz-juelich.de:1047296$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001047296 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)196697$$aForschungszentrum Jülich$$b1$$kFZJ
001047296 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180323$$aForschungszentrum Jülich$$b2$$kFZJ
001047296 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)186075$$aForschungszentrum Jülich$$b7$$kFZJ
001047296 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001047296 9141_ $$y2025
001047296 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2025-01-06
001047296 915__ $$0LIC:(DE-HGF)CCBYNCND4$$2HGFVOC$$aCreative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND 4.0
001047296 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bMATER CHARACT : 2022$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001047296 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-06
001047296 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-06
001047296 920__ $$lyes
001047296 9201_ $$0I:(DE-Juel1)IAS-9-20201008$$kIAS-9$$lMaterials Data Science and Informatics$$x0
001047296 980__ $$ajournal
001047296 980__ $$aVDB
001047296 980__ $$aUNRESTRICTED
001047296 980__ $$aI:(DE-Juel1)IAS-9-20201008
001047296 9801_ $$aFullTexts