준지도 학습 머신러닝을 이용한 해상 풍력용 설비안전 진단 시스템의 개발
Development of facility safety diagnosis system for offshore wind power using semi-supervised machine learning
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, a semi-supervised machine learning technique applied to actual field vibration data acquired from Jeju-do wind turbines for predictive diagnosis of abnormal conditions of offshore wind turbines is introduced. Semi-supervised machine learning, which combines un-supervised learning with supervised learning, can be used to perform anomaly detection in situations where sufficient fault data cannot be obtained. The signal processing results using the spectrogram of the original signal were shown, and external data were used to overcome the problem that disturbance reactions easily occurred due to the imbalance between the number of normal and abnormal data. Out of distribution (OOD), which uses external data, is a technology that is regarded as abnormal data that is unlikely to occur in reality, but we were able to use it by expanding it. By rearranging the distribution of data in this way, classification can be performed more robustly. Specifically, by observing the trends of the abnormal score and the change in the feature of the representation layer, continuous learning was performed through a mixture of existing and new data.
Abstract
In this paper, a semi-supervised machine learning technique applied to actual field vibration data acquired from Jeju-do wind turbines for predictive diagnosis of abnormal conditions of offshore wind turbines is introduced. Semi-supervised machine learning, which combines un-supervised learning with supervised learning, can be used to perform anomaly detection in situations where sufficient fault data cannot be obtained. The signal processing results using the spectrogram of the original signal were shown, and external data were used to overcome the problem that disturbance reactions easily occurred due to the imbalance between the number of normal and abnormal data. Out of distribution (OOD), which uses external data, is a technology that is regarded as abnormal data that is unlikely to occur in reality, but we were able to use it by expanding it. By rearranging the distribution of data in this way, classification can be performed more robustly. Specifically, by observing the trends of the abnormal score and the change in the feature of the representation layer, continuous learning was performed through a mixture of existing and new data.
참고문헌 (7)
- Xiaojin Zhu,, "Semi-Supervised Learning Literature Survey, Computer Sciences TR 1530", University of Wisconsin - Madison, ~ (2006)
- Razieh Sheikhpour, "A survey on semi-supervised feature selection methods", Pattern Recognition, 64, pp.141~158 (2017)
- Hongyu Zhu, "A cost-sensitive semi-supervised learning model based on uncertainty", Neurocomputing, 251, pp.106~114 (2017)
- 정성목, "풍력발전기 진동 데이터를 활용한 딥러닝 기반 고장진단기법 연구", 한국정보기술학회논문지, 20(6), pp.129~136 (2022), 한국정보기술학회[DOI]
- 이도행, "해상 풍력발전기 고장진단을 위한 CMS 시운전 및 알람 설정", 풍력에너지저널, 10(4), pp.43~49 (2019), 한국풍력에너지학회[DOI]
- Shao Haidong, "A novel deep autoencoder feature learning method for rotating machinery fault diagnosis", Mechanical Systems and Signal Processing, 95, pp.187~204 (2017)
- Mohammakazem Sadoughi, "A Deep Learning-based Approach for Fault Diagnosis of Roller Element Bearings", Annual Conference of the Prognostics and Health Management Society, 10(1) (2018)