Journal of Korean Society for Quality Management (품질경영학회지)

Korean Society for Quality Management (한국품질경영학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Optimization of Classification Performance through Fourier Transform and Image Augmentation

푸리에 변환 및 이미지 증강을 통한 분류 성능 최적화에 관한 연구

  • Kihyun Kim (Department of Industrial Systems Engineering, Kyonggi University Graduate School) ;
  • Seong-Mok Kim (Department of Industrial Systems Engineering, Kyonggi University) ;
  • Yong Soo Kim (Department of Industrial Systems Engineering, Kyonggi University)
  • 김기현 (경기대학교 일반대학원 산업시스템공학과) ;
  • 김성목 (경기대학교 산업시스템공학과) ;
  • 김용수 (경기대학교 산업시스템공학과)
  • Received : 2023.02.28
  • Accepted : 2023.03.05
  • Published : 2023.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: This study proposes a classification model for implementing condition-based maintenance (CBM) by monitoring the real-time status of a machine using acceleration sensor data collected from a vehicle. Methods: The classification model's performance was improved by applying Fourier transform to convert the acceleration sensor data from the time domain to the frequency domain. Additionally, the Generative Adversarial Network (GAN) algorithm was used to augment images and further enhance the classification model's performance. Results: Experimental results demonstrate that the GAN algorithm can effectively serve as an image augmentation technique to enhance the performance of the classification model. Consequently, the proposed approach yielded a significant improvement in the classification model's accuracy. Conclusion: While this study focused on the effectiveness of the GAN algorithm as an image augmentation method, further research is necessary to compare its performance with other image augmentation techniques. Additionally, it is essential to consider the potential for performance degradation due to class imbalance and conduct follow-up studies to address this issue.

Keywords

Acknowledgement

본 연구는 경기도의 경기도 지역협력연구센터 사업의 일환으로 수행하였음(GRRC경기2020-B03, 산업통계 및 데이터마이닝 연구).

References

  1. Cooley JW, and Tukey JW. 1965. An algorithm for the machine calculation of complex Fourier series. Mathematics of Computation 19(90):297-301. https://doi.org/10.1090/S0025-5718-1965-0178586-1
  2. Gabor D. 1946. Theory of communication. Part 1: The analysis of information. Journal of the Institution of Electrical Engineers-Part III: Radio and Communication Engineering 93(26):429-441. https://doi.org/10.1049/ji-3-2.1946.0074
  3. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y. 2020. Generative adversarial networks. Communications of the ACM 63(11):139-144. https://doi.org/10.1145/3422622
  4. Han, MS, Yu, SJ. 2022. Forecasting Baltic Dry Index by Implementing Time-Series Decomposition and Data Augmentation Techniques. Journal of the Korean society for Quality Management 50(4):701-716.
  5. Han, SY, Kim, JG, Hong, SK and Ha, CS. 2004. -Reliability Management of the Rubber-Tired AGT Vehicle System. Journal of the Korea Safety Management and Science 6(4):139-153.
  6. Hussain F, Abbas SG, Husnain M, Fayyaz UU, Shahzad F, and Shah GA. 2020. IoT DoS and DDoS attack detection using ResNet. In 2020 IEEE 23rd International Multitopic Conference (INMIC):1-6
  7. Isola P, Zhu JY, Zhou T, and Efros AA. 2017. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition:1125-1134.
  8. Kang, KW, and Lee, KM. 2020. CNN-based automatic machine fault diagnosis method using spectrogram images. Journal of the Institute of Convergence Signal Processing 21(3):121-126.
  9. Karras T, Aila T, Laine S, and Lehtinen J. 2017. Progressive growing of gans for improved quality, stability, and variation. arXiv Preprint arXiv:1710.10196,
  10. Kim, DK, Park, BN, Song, MO, and Lim, JH. 2022. The Optimal Inspection Period of a System Considering the Probability of Finding Deteriorated Components under the Inspection-Maintenance Model.Journal of Applied Reliability 22(4):309-318.
  11. Lee, SH, Kim, JY, Lee, JJ, Kim, YJ, Kim, SK, and Lee, TH. 2022. A Study on the Development of Database and Algorithm for Fault Diagnosis for Condition Based Maintenance of Rubber Seal in Ancillary Equipment of Autonomous Ships. Journal of Applied Reliability 22(1):48-58. https://doi.org/10.33162/JAR.2022.3.22.1.048
  12. Lee, YH, Yong, HY, Jung, JW, and Kim, JW. 2022. Development of Dormant Missile Health Monitoring Methodology based on Environmental Data. Journal of Applied Reliability 22(3):219-228. https://doi.org/10.33162/JAR.2022.9.22.3.219
  13. Li Z, Zheng T, Wang Y, Cao Z, Guo Z, and Fu H. 2020. A novel method for imbalanced fault diagnosis of rotating machinery based on generative adversarial networks. IEEE transactions on instrumentation and measurement 70:1-17.
  14. Lim, MW, Lee, JH, Park, GH, Bae, SJ. 2022. Lifetime Estimation of Electric Transformers for Multiple Failure-Modes. Journal of Applied Reliability 22(4):428-435. https://doi.org/10.33162/JAR.2022.12.22.4.428
  15. Lim, SC, and Kim, JC. 2021. A Study on the Optimization of Convolution Operation Speed through FFT Algorithm. Journal of Korea Multimedia Society 24(11):1552-1559. https://doi.org/10.9717/KMMS.2021.24.11.1552
  16. Mun, BM, Jeon. YG, Lee, HJ, Kim, JH, Han, SH, and Lee, HJ. 2020. Detection of Display Defects Using a Cluster Index. Journal of Applied Reliability 20(3):277-283. https://doi.org/10.33162/JAR.2020.09.20.3.277
  17. Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, and Chen X. 2016. Improved techniques for training gans. Advances in Neural Information Processing Systems 29.
  18. Sedigh P, Sadeghian R, and Masouleh MT. 2019. Generating synthetic medical images by using GAN to improve CNN performance in skin cancer classification. In 2019 7th International Conference on Robotics and Mechatronics (ICRoM):497-502.
  19. Seo, JH, Park, JS, Yoo, JW, and Park HJ. 2021. Anomaly Detection System in Mechanical Facility Equipment: Using Long Short-Term Memory Variational Autoencoder. Journal of the Korean Society for Quality Management, 49(4):581-594. https://doi.org/10.7469/JKSQM.2021.49.4.581
  20. Shin, JH, Jun, HB, and Kim, DG. 2014. A Study on Several Aspects of Condition Based Maintenance (CBM) Approach and Introduction of Relevant Case Studies. Entrue Journal of Information Technology 13(3):123-138.
  21. Son, MJ, Kim, YG, Noh, SC, Kim, MH, and Kim, KM. 2022. Exploring the Application of CBM+ in an ISR Weapon System, Thermal Observation Device. Journal of Applied Reliability 22(3):240-247. https://doi.org/10.33162/JAR.2022.9.22.3.240
  22. Son, MJ and Kim, YG. 2021. A Study on the Reflection of Condition-Based Maintenance Requirement in the Defense Specification. Journal of the Korean Society for Quality Management 49(3):269-279. https://doi.org/10.7469/JKSQM.2021.49.3.269
  23. Teixeira HN, Lopes I, and Braga AC. 2020. Condition-based maintenance implementation: a literature review. Procedia Manufacturing 51:228-235. https://doi.org/10.1016/j.promfg.2020.10.033
  24. Zhao R, Yan R, Chen Z, Mao K, Wang P, and Gao RX. 2019. Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing 115:213-237. https://doi.org/10.1016/j.ymssp.2018.05.050