EUVIMEDEUVIMED entdecken
Crossref

Autonomous damage recognition of C/SiC composite based on transfer learning

Qianbo Zhou, Zhaofeng Chen, Jianyong Xu

Materials Express · 01.02.2022 · 12 (2) · 327-336

DOI: 10.1166/mex.2022.2154 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials Express, erschienen am 01.02.2022. Verfasst von Qianbo Zhou und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 27 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

C/SiC composite has excellent performance, but their damage patterns cannot be effectively detected, and it is tough to obtain a large amount of label data. Therefore, an autonomous damage image recognition based on transfer learning is proposed in this paper. A C/SiC composite damage image data set is collected from experiments and papers, including fiber pullout, matrix cracking, interface debonding, and fiber breakage images. Pre-trained DenseNet121 was transferred to train and classify this data set. Pre-trained AlexNet and other four networks are selected for comparison. The results of experiment illustrate that the accuracy of directly using the DenseNet121 model is 70.536%, and the accuracy of the transferring pre-trained AlexNet, VGG16, ResNet18, and MobileNet-v2 on the validation set is 96.429%, 84.598%, 94.420%, 94.866%, respectively. The accuracy in this paper is 97.098%. As the number of damage images of C/SiC composite is limited, the recognition accuracy of the method is significantly improved.

Zitieren

APA

Zhou, Q., Chen, Z., & Xu, J. (2022). Autonomous damage recognition of C/SiC composite based on transfer learning. Materials Express, 12(2), 327-336. https://doi.org/10.1166/mex.2022.2154

Vancouver

Zhou Q, Chen Z, Xu J. Autonomous damage recognition of C/SiC composite based on transfer learning. Materials Express. 2022;12(2):327-336. doi:10.1166/mex.2022.2154

BibTeX
@article{Zhou2022,
  author = {Zhou, Qianbo and Chen, Zhaofeng and Xu, Jianyong},
  title = {Autonomous damage recognition of C/SiC composite based on transfer learning},
  journal = {Materials Express},
  year = {2022},
  volume = {12},
  number = {2},
  pages = {327--336},
  doi = {10.1166/mex.2022.2154}
}
Kostenlos starten →