푸리에 변환 및 이미지 증강을 통한 분류 성능 최적화에 관한 연구
A Study on Optimization of Classification Performance through Fourier Transform and Image Augmentation
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
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.
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.
참고문헌 (24)
- Cooley JW,, "An algorithm for the machine calculation of complex Fourier series", Mathematics of Computation, 19(90), pp.297~301 (1965)
- Gabor D, "Theory of communication. Part 1: The analysis of information", Journal of the Institution of Electrical Engineers-Part III : Radio and Communication Engineering, 93(26), pp.429~441 (1946)
- Goodfellow I., "Generative adversarial networks", Communications of the ACM, 63(11), pp.139~144 (2020)
- 한민수, "시계열 분해 및 데이터 증강 기법 활용 건화물운임지수 예측", 품질경영학회지, 50(4), pp.701~716 (2022), 한국품질경영학회[DOI]
- 한석윤, "고무차륜 AGT 차량시스템의 신뢰성관리체계 개발", 대한안전경영과학회지, 6(4), pp.139~154 (2004), 대한안전경영과학회
- Hussain F, "IoT DoS and DDoS attack detection using ResNet", 2020 IEEE 23rd International Multitopic Conference (INMIC), pp.1~6 (2020)
- Isola P., "Image-to-image translation with conditional adversarial networks", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1125~1134 (2017)
- 강경원, "스펙트로그램 이미지를 이용한 CNN 기반 자동화 기계 고장 진단 기법", 융합신호처리학회 논문지, 21(3), pp.121~126 (2020), 한국융합신호처리학회[DOI]
- Karras T, "Progressive growing of gans for improved quality, stability, and variation", arXiv Preprint arXiv:1710.10196, ~ (2017)
- 김대경, "점검-정비 모형에서 열화부품의 발견확률을 고려한 시스템의 최적 점검주기", 신뢰성 응용연구, 22(4), pp.309~318 (2022), 한국신뢰성학회[DOI]
- 이송호, "자율운항선박 보조기기 내 고무 씰의 상태기반정비를 위한 고장진단용 데이터베이스 및 알고리즘 개발에 관한 연구", 신뢰성 응용연구, 22(1), pp.48~58 (2022), 한국신뢰성학회[DOI]
- 이연호, "환경데이터 기반 유휴(dormant) 유도탄 상태 진단 및 모니터링 방안 연구", 신뢰성 응용연구, 22(3), pp.219~228 (2022), 한국신뢰성학회
- Li Z, "A novel method for imbalanced fault diagnosis of rotating machinery based on generative adversarial networks", IEEE transactions on instrumentation and measurement, 70, pp.1~17 (2020)
- 임문원, "복합 고장 유형을 가지는 변압기에 대한 수명추정", 신뢰성 응용연구, 22(4), pp.428~435 (2022), 한국신뢰성학회[DOI]
- 임수창, "FFT 적용을 통한 Convolution 연산속도 향상에 관한 연구", 멀티미디어학회논문지, 24(11), pp.1552~1559 (2021), 한국멀티미디어학회
- 문병민, "군집 지수를 통한 디스플레이의 결점 탐지", 신뢰성 응용연구, 20(3), pp.277~283 (2020), 한국신뢰성학회[DOI]
- Salimans T, "Improved techniques for training gans", Advances in Neural Information Processing Systems, 29 (2016)
- Sedigh P, "Generating synthetic medical images by using GAN to improve CNN performance in skin cancer classification", 2019 7th International Conference on Robotics and Mechatronics (ICRoM), pp.497~502 (2019)
- 서재홍, "LSTM-VAE를 활용한 기계시설물 장치의 이상 탐지 시스템", 품질경영학회지, 49(4), pp.581~594 (2021), 한국품질경영학회[DOI]
- 신종호, "상태기반 보전 방법에 대한 고찰 및 사례 소개", Entrue Journal of Information Technology, 13(3), pp.123~138 (2014), 엘지씨엔에스
- 손민정, "열상감시장비 운용 데이터 기반 CBM+ 적용 방안 연구", 신뢰성 응용연구, 22(3), pp.240~247 (2022), 한국신뢰성학회
- 손민정, "상태기반정비 요구도 국방규격 반영에 관한 연구", 품질경영학회지, 49(3), pp.269~279 (2021), 한국품질경영학회[DOI]
- Teixeira HN, "Condition-based maintenance implementation : a literature review", Procedia Manufacturing, 51, pp.228~235 (2020)
- Zhao R, "Deep learning and its applications to machine health monitoring", Mechanical Systems and Signal Processing, 115, pp.213~237 (2019)