KEPCO Journal on Electric Power and Energy

Korea Electric Power Corporation (한국전력공사)
권호 표지
DOI QR코드

DOI QR Code

Data Augmentation Techniques of Power Facilities for Improve Deep Learning Performance

  • Jang, Seungmin (KEPCO Research Institute, Korea Electric Power Corporation) ;
  • Son, Seungwoo (KEPCO Research Institute, Korea Electric Power Corporation) ;
  • Kim, Bongsuck (KEPCO Research Institute, Korea Electric Power Corporation)
  • Received : 2020.07.28
  • Accepted : 2020.09.29
  • Published : 2021.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.

Keywords

Acknowledgement

This research was supported by Korea Electric Power Corporation under Grant R21IA02.

References

  1. 이동엽, 김준오, 윤정용, 신동열, 최민희 (2017). 인공지능 기반 배전 폴리머 현수애자 진단 장비 개발. 대한전기학회 학술대회 논문집, 1547-1548.
  2. 이동엽, 김준오, 윤정용, 최민희 (2017). Deep Learning을 활용한 배전 기자재 영상 진단 알고리즘 개발. 대한전기학회 학술대회 논문집, 1504-1505.
  3. Shorten, C., Khoshgoftaar, T.M. A survey on Image Data Augmentation for Deep Learning. J Big Data 6, 60 (2019). https://doi.org/10.1186/s40537-019-0197-0.
  4. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. Adv Neural Inf Process Syst 2014:2672-2680.
  5. M.-Y. Liu, X. Huang, A. Mallya, T. Karras, T. Aila, J. Lehtinen, and J. Kautz. Few-shot unsupervised image-to-image translation. In ICCV, 2019.
  6. E. Zakharov, A. Shysheya, E. Burkov, and V. Lempitsky. Few-shot adversarial learning of realistic neural talking head models. arXiv preprint arXiv:1905.08233, 2019.
  7. S. Sinha, H. Zhang, A. Goyal, Y. Bengio, H. Larochelle, and A. Odena. Small-gan: Speeding up gan training using coresets. arXiv preprint arXiv:1910.13540, 2019.
  8. Y. Wang, A. Gonzalez-Garcia, D. Berga, L. Herranz, F. S. Khan, and J. van de Weijer. Minegan: effective knowledge transfer from gans to target domains with few images. arXiv preprint arXiv:1912.05270, 2019.
  9. J. Yosinski, J. Clune, Y. Bengio, and H. Lipson. How transferable are features in deep neural networks? In NeurIPS, 2014.
  10. Sangwoo Mo, Minsu Cho, and Jinwoo Shin. Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs. arXiv:2002.10964v2, 2020.
  11. Transfer Learning, Lisa Torrey and Jude Shavlik, Handbook of Research on Machine Learning Applications, IGI Global, 2009.
  12. Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, and Timo Aila. Training Generative Adversarial Networks with Limited Data. arXiv:2006.06676v2 [cs.CV] 7 Oct 2020.