머신러닝 기법을 활용한 대용량 시계열 데이터 이상 시점탐지 방법론 : 발전기 부품신호 사례 중심
Anomaly Detection of Big Time Series Data Using Machine Learning
1
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.
Abstract
Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.
참고문헌 (14)
- Ben-Hur, A., "Support vector clustering", Journal of Machine Learning Research, 2, pp.125~137 (2011)
- Bianco, A. M., "Detection in regression models with arima errors using estimates", Journal of Forecasting, 20(8), pp.565~579 (2001)
- Goodfellow, I., "Generative Adversarial Networks", Proceedings of the International Conference on Neural Information Proceeding Systems, pp.2672~2680 (2014)
- Gulli, A, "Deep Learning with Keras : Implementing deep learning models and neural networks with the power of Python" (2017), Packt Publishing
- James, A. A., "An Introduction To Neural Networks" (1995), MIT Press
- "Keras 2. 3. 1" (2019)[URL]
- 권세혁, "하천유역 수질 관측망 구성연구", 한국산업경영시스템학회지, 35(3), pp.187~191 (2012), 한국산업경영시스템학회
- 이상욱, "Agent-Based Model을 활용한 자동차 예비부품 장기수요예측", 한국산업경영시스템학회지, 38(1), pp.110~117 (2015), 한국산업경영시스템학회
- 권세혁, "데이터 탐색 기법 활용 전도현상 예측모형", 한국산업경영시스템학회지, 41(3), pp.90~96 (2018), 한국산업경영시스템학회[DOI]
- Lee, J. U., "Foreign and domestic research trend in failure detection methodology", Journal of the KSME, 56(11), pp.37~40 (2016)
- Sharma, N., "An analysis of convolutional neural networks for image classification", Procedia Computer Science, 132, pp.377~384 (2018)
- Shyu, M., "A novelanomaly detection scheme based on principal component classifier", CDM Foundation and New Direction of Data Mining workshop, pp.172~179 (2003)
- Tibshirani, R., "Regression shrinkage and selection via the LASSO", Journal of the Royal Statistical Society, Series B(methodological), 58(1), pp.267~288 (1996)
- Tsay, R. S., "Outliers in multivariate time series", Biometrika, 87(4), pp.789~804 (2000)