Depth Classification of Defects Based on Neural Architecture SearchCitation formats

  • External authors:
  • Haoze Chen
  • Zhijie Zhang
  • Chenyang Zhao
  • Jiaqi Liu
  • Yanfeng Li
  • Fengxiang Wang
  • Zhenyu Lin

Standard

Depth Classification of Defects Based on Neural Architecture Search. / Chen, Haoze; Zhang, Zhijie; Zhao, Chenyang; Liu, Jiaqi; Yin, Wuliang; Li, Yanfeng; Wang, Fengxiang; Li, Chao; Lin, Zhenyu.

In: IEEE Access, Vol. 9, 9424564, 06.05.2021, p. 73424-73432.

Research output: Contribution to journalArticlepeer-review

Harvard

Chen, H, Zhang, Z, Zhao, C, Liu, J, Yin, W, Li, Y, Wang, F, Li, C & Lin, Z 2021, 'Depth Classification of Defects Based on Neural Architecture Search', IEEE Access, vol. 9, 9424564, pp. 73424-73432. https://doi.org/10.1109/ACCESS.2021.3077961

APA

Chen, H., Zhang, Z., Zhao, C., Liu, J., Yin, W., Li, Y., Wang, F., Li, C., & Lin, Z. (2021). Depth Classification of Defects Based on Neural Architecture Search. IEEE Access, 9, 73424-73432. [9424564]. https://doi.org/10.1109/ACCESS.2021.3077961

Vancouver

Chen H, Zhang Z, Zhao C, Liu J, Yin W, Li Y et al. Depth Classification of Defects Based on Neural Architecture Search. IEEE Access. 2021 May 6;9:73424-73432. 9424564. https://doi.org/10.1109/ACCESS.2021.3077961

Author

Chen, Haoze ; Zhang, Zhijie ; Zhao, Chenyang ; Liu, Jiaqi ; Yin, Wuliang ; Li, Yanfeng ; Wang, Fengxiang ; Li, Chao ; Lin, Zhenyu. / Depth Classification of Defects Based on Neural Architecture Search. In: IEEE Access. 2021 ; Vol. 9. pp. 73424-73432.

Bibtex

@article{00250d6fec48493597962433dcf5f542,
title = "Depth Classification of Defects Based on Neural Architecture Search",
abstract = "As an important part of non-destructive testing, infrared thermography testing is widely used in various fields of industrial development for monitoring the quality of metal parts. Considering the problem of low detection rate of surface defects on steel parts, we explored the application of neural architecture search (NAS) in infrared thermography area for the first time. On the one hand, we compared different time-series temperature features of defect locations in infrared images and validate the performance of three different features such as heating, cooling and full process by machine learning methods. On the other hand, we searched for multilayer perceptron through NAS technology to classify defects with different depths. Experiments have proved that the time-series temperature feature is very effective when used in the depth classification of defects, and the accuracy rate can reach 93% under the verification of traditional machine learning methods. The NAS technique used in this paper can search 100 multilayer perceptrons in a minimum of 121s and achieve 100% defect classification accuracy.",
keywords = "Non-destructive testing, classification, infrared thermography, neural architecture search",
author = "Haoze Chen and Zhijie Zhang and Chenyang Zhao and Jiaqi Liu and Wuliang Yin and Yanfeng Li and Fengxiang Wang and Chao Li and Zhenyu Lin",
note = "Funding Information: This work was supported by the Fund for Shanxi 1331 Project Key Subject Construction of China. Publisher Copyright: {\textcopyright} 2013 IEEE.",
year = "2021",
month = may,
day = "6",
doi = "10.1109/ACCESS.2021.3077961",
language = "English",
volume = "9",
pages = "73424--73432",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE",

}

RIS

TY - JOUR

T1 - Depth Classification of Defects Based on Neural Architecture Search

AU - Chen, Haoze

AU - Zhang, Zhijie

AU - Zhao, Chenyang

AU - Liu, Jiaqi

AU - Yin, Wuliang

AU - Li, Yanfeng

AU - Wang, Fengxiang

AU - Li, Chao

AU - Lin, Zhenyu

N1 - Funding Information: This work was supported by the Fund for Shanxi 1331 Project Key Subject Construction of China. Publisher Copyright: © 2013 IEEE.

PY - 2021/5/6

Y1 - 2021/5/6

N2 - As an important part of non-destructive testing, infrared thermography testing is widely used in various fields of industrial development for monitoring the quality of metal parts. Considering the problem of low detection rate of surface defects on steel parts, we explored the application of neural architecture search (NAS) in infrared thermography area for the first time. On the one hand, we compared different time-series temperature features of defect locations in infrared images and validate the performance of three different features such as heating, cooling and full process by machine learning methods. On the other hand, we searched for multilayer perceptron through NAS technology to classify defects with different depths. Experiments have proved that the time-series temperature feature is very effective when used in the depth classification of defects, and the accuracy rate can reach 93% under the verification of traditional machine learning methods. The NAS technique used in this paper can search 100 multilayer perceptrons in a minimum of 121s and achieve 100% defect classification accuracy.

AB - As an important part of non-destructive testing, infrared thermography testing is widely used in various fields of industrial development for monitoring the quality of metal parts. Considering the problem of low detection rate of surface defects on steel parts, we explored the application of neural architecture search (NAS) in infrared thermography area for the first time. On the one hand, we compared different time-series temperature features of defect locations in infrared images and validate the performance of three different features such as heating, cooling and full process by machine learning methods. On the other hand, we searched for multilayer perceptron through NAS technology to classify defects with different depths. Experiments have proved that the time-series temperature feature is very effective when used in the depth classification of defects, and the accuracy rate can reach 93% under the verification of traditional machine learning methods. The NAS technique used in this paper can search 100 multilayer perceptrons in a minimum of 121s and achieve 100% defect classification accuracy.

KW - Non-destructive testing

KW - classification

KW - infrared thermography

KW - neural architecture search

U2 - 10.1109/ACCESS.2021.3077961

DO - 10.1109/ACCESS.2021.3077961

M3 - Article

VL - 9

SP - 73424

EP - 73432

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 9424564

ER -