센서 데이터 변곡점에 따른 Time Segmentation 기반 항공기 엔진의 고장 패턴 추출
Fault Pattern Extraction Via Adjustable Time Segmentation Considering Inflection Points of Sensor Signals for Aircraft Engine Monitoring
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
As mechatronic systems have various, complex functions and require high performance, automatic fault detection is necessary for secure operation in manufacturing processes. For conducting automatic and real-time fault detection in modern mechatronic systems, multiple sensor signals are collected by internet of things technologies. Since traditional statistical control charts or machine learning approaches show significant results with unified and solid density models under normal operating states but they have limitations with scattered signal models under normal states, many pattern extraction and matching approaches have been paid attention. Signal discretization-based pattern extraction methods are one of popular signal analyses, which reduce the size of the given datasets as much as possible as well as highlight significant and inherent signal behaviors. Since general pattern extraction methods are usually conducted with a fixed size of time segmentation, they can easily cut off significant behaviors, and consequently the performance of the extracted fault patterns will be reduced. In this regard, adjustable time segmentation is proposed to extract much meaningful fault patterns in multiple sensor signals. By considering inflection points of signals, we determine the optimal cut-points of time segments in each sensor signal. In addition, to clarify the inflection points, we apply Savitzky-golay filter to the original datasets. To validate and verify the performance of the proposed segmentation, the dataset collected from an aircraft engine (provided by NASA prognostics center) is used to fault pattern extraction. As a result, the proposed adjustable time segmentation shows better performance in fault pattern extraction.
Abstract
As mechatronic systems have various, complex functions and require high performance, automatic fault detection is necessary for secure operation in manufacturing processes. For conducting automatic and real-time fault detection in modern mechatronic systems, multiple sensor signals are collected by internet of things technologies. Since traditional statistical control charts or machine learning approaches show significant results with unified and solid density models under normal operating states but they have limitations with scattered signal models under normal states, many pattern extraction and matching approaches have been paid attention. Signal discretization-based pattern extraction methods are one of popular signal analyses, which reduce the size of the given datasets as much as possible as well as highlight significant and inherent signal behaviors. Since general pattern extraction methods are usually conducted with a fixed size of time segmentation, they can easily cut off significant behaviors, and consequently the performance of the extracted fault patterns will be reduced. In this regard, adjustable time segmentation is proposed to extract much meaningful fault patterns in multiple sensor signals. By considering inflection points of signals, we determine the optimal cut-points of time segments in each sensor signal. In addition, to clarify the inflection points, we apply Savitzky-golay filter to the original datasets. To validate and verify the performance of the proposed segmentation, the dataset collected from an aircraft engine (provided by NASA prognostics center) is used to fault pattern extraction. As a result, the proposed adjustable time segmentation shows better performance in fault pattern extraction.
참고문헌 (34)
- Ahn, B., "A Study on the Fault Diagnosis of Wind Turbines Using SVM Based on Cross Validation", Proceedings of 2021 Spring Conference of The Korean Institute of Electrical Engineers, pp.136~137 (2021)
- Baek, S., "Abrupt Variance and Discernibility Analyses of Multi-Sensor Signals for Fault Pattern Extraction", Computers & Industrial Engineering, 128, pp.999~1007 (2019)
- Baek, S., "Empirical Sensitivity Analysis of Discretization Parameters for Fault Pattern Extraction from Multivariate Time Series Data", IEEE Transactions on Cybernetics, 47(5), pp.1198~1209 (2017)
- Bai, X, "Co-anomaly Event Detection in Multiple Temperature Series", Proceedings of the 6th International Conference of Knowledge Science, Engineering, and Management, pp.1~14 (2013)
- Chandola, V., "Anomaly Detection for Discrete Sequences: A Survey", IEEE Transactions on Knowledge and Data Engineering, 24(5), pp.823~839 (2012)
- 천강민, "앙상블 모델 기반의 기계 고장 예측 방법", 한국산업경영시스템학회지, 43(1), pp.123~131 (2020), 한국산업경영시스템학회[DOI]
- 조상제, "LNG FPSO 압축기 고장시간 예측 방안에 관한 연구", 한국산업경영시스템학회지, 37(4), pp.12~23 (2014), 한국산업경영시스템학회
- Duan, L, "A Hybrid Approach of Sax and Bitmap for Machinery Fault Diagnosis", Proceeding of the 2016International Symposium on Flexible Automation, pp.390~396 (2016)
- Fontes, C.H., "Pattern Recognition in Multivariate Time Series – A Case Study Applied to Fault Detection in a Gas Turbine", Engineering Applications of Artificial Intelligence, 49, pp.10~18 (2016)
- Fu, T. C., "A Review on Time Series Data Mining", Engineering Applications of Artificial Intelligence, 24(1), pp.164~181 (2011)
- García, S., "A Survey of Discretization Techniques: Taxonomy and Empirical Analysis in Supervised Learning", IEEE Transactions on Knowledge and Data Engineering, 25(4), pp.734~750 (2013)
- Ghosh, A., "A Novel Automata and Neural Network Based Fault Diagnosis System for PLC Controlled Manufacturing Systems", Computers &Industrial Engineering, 139, pp.1~16 (2020)
- Hodge, V., "A Survey of Outlier Detection Methodologies", Artificial Intelligence Review, 22(2), pp.85~126 (2014)
- 정훈, "기계적 모터 고장진단을 위한 머신러닝 기법", 한국산업경영시스템학회지, 40(1), pp.57~64 (2017), 한국산업경영시스템학회
- Keogh, E., "An Online Algorithm for Segmenting Time Series", Proceedings of the 2001 IEEE International Conference on Data Mining, pp.289~296 (2001)
- Keogh, E., "On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration", Data Mining and Knowledge Discovery, 7(4), pp.349~371 (2003)
- 김가은, "통계적 공정관리 성능지표를 통한 구름 베어링의 결함 검출에 관한 연구", 대한기계학회논문집 A, 45(1), pp.51~57 (2021), 대한기계학회
- 김효수, "A2", O 공정에서 통계학적 기법을 이용한 온라인 센서의 상태진단 알고리즘 개발, 2019, pp.41(11), 627~636[DOI]
- Kim, J.W, "A Study of the Prognostics of Inverter Failure Using RF and KNN", Proceedings of Spring Conference of The Korean Society of Manufacturing Process Engineers, pp.96~ (2020)
- 이건희, "SVM을 이용한 기어펌프의 고장 분류", 신뢰성 응용연구, 20(2), pp.187~196 (2020), 한국신뢰성학회[DOI]
- 이인수, "프레스공정시스템에서 유도전동기 및 윤활유 레벨 상태모니터링을 위한 진단시스템 개발", 한국지능시스템학회 논문지, 19(5), pp.706~712 (2009), 한국지능시스템학회
- Lim, J.-K., "A Study on the Feature Extraction for the Rolling Stock Door Using the Current Value of The Motor and the Selection of a Failure Diagnosis Prediction Algorithm", The Transactions of the Korean Institute of Electrical Engineers, 21(1), pp.96~101 (2021)
- Liu, H., "Discretization: An Enabling Technique", Data Mining and Knowledge Discovery, 6(4), pp.393~423 (2002)
- Luo, R. C., "Sensor Technologies and Microsensor Issues for Mechatronics Systems", IEEE, 1996, pp.1(1), 39~49
- Namgung, K., "Estimating System State through Similarity Analysis of Signal Patterns", Sensors, 20(23), pp.1~13 (2020)
- Phaladiganon, P., "Principal Component Analysis-based Control Charts for Multivariate Nonnormal Distribution", Expert Systems with Applications, 40, pp.3044~3054 (2013)
- Rahman, M. A., "Selecting the Optimal Conditions of Savitzky-Golay Filter for fNIRS Signal", Biocybenetics and Biomedical Engineering, 39(3), pp.624~637 (2019)
- "Turbofan Engine Degradation Simulation Data Set, NASA Ames Prognostics Data Repository" (2008)[URL]
- Saxena, A., "Damage Propagation Modeling for Aircraft Engine Run-to-failure Simulation", Proceedings of the International Conference on Prognostics and Health Management, pp.1~9 (2008)
- Shewhart, M., "Application of Machine Learning and Expert Systems to Statistical Process Control (SPC) Chart Interpretation", Proceedings of the 2nd C Language Integrated Production System Conference, pp.123~138 (1991)
- Tamboli, K., "Design and Development of a Mechatronic System for the Measurement of Railway Tracks", The Industrial Daily Journal, 43(200), pp.174~180 (2015)
- Wilson, S. J., "Data Representation for Time Series Data Mining: Time Domain Approaches", Wiley Interdisciplinary Reviews: Computational Statistics, 9(1), pp.e1392:1~e1392:6 (2017)
- Xu, Y., "High-speed Train Fault Detection with Unsupervised Causality-Based Feature Extraction Methods", Advanced Engineering Informatics, 49, pp.101312~ (2021)
- Yu, G.S., "Development trend of smart factory facility diagnosis and predictive maintenance technology", The Journal of The Korean Institute of Communication Sciences, 37(7), pp.36~42 (2020)