합성곱 네트워크 기반의 Conv1D 알고리즘에서 시간 종속성을 반영한 선박 연료계통 장비의 고장 진단 모델
The Fault Diagnosis Model of Ship Fuel System Equipment Reflecting Time Dependency in Conv1D Algorithm Based on the Convolution Network
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
본 연구는 자율운항 선박의 연료 계통 펌프와 청정기를 대상으로 고장을 진단 사례를 제시하였다. 계측된 신호의 시간종속성을 반영한 심층학습(Deep learning) 알고리즘 적용 절차를 구성하고, 장비의 정상 운전상태와 고장 상태에서 계측한 진동 신호를 고장 패턴 학습에 사용하였다. 특히, 진동 신호에 내포된 열화의 시간 종속성을 반영할 수 있는 방법을 찾고자 하였으며, 슬라이딩 윈도우 연산 과정을 가진 Conv1D를 이용하여 고장의 시간 종속성을 반영하였다. 또한 계측된 신호의 차수를 2차원에서 3차원으로 확장하여 시간 영역의 특징을 반영할 수 있는 데이터 전처리과정을 고안하였다. Conv1D 알고리즘의 적층과 변수를 결정하는 과정에서 그리드 탐색 기법을 사용하여 초매개변수의 최적 값을 결정하였다. 마지막으로 제안한 데이터 전처리 방법과 시계열 데이터의 시간 종속성을 반영한 Conv1D 모델이 이상 감지 및 고장 진단에 타당성이 있음을 확인하였다.
Abstract
The purpose of this study was to propose a deep learning algorithm that applies to the fault diagnosis of fuel pumps and purifiers of autonomous ships. A deep learning algorithm reflecting the time dependence of the measured signal was configured, and the failure pattern was trained using the vibration signal, measured in the equipment's regular operation and failure state. Considering the sequential time-dependence of deterioration implied in the vibration signal, this study adopts Conv1D with sliding window computation for fault detection. The time dependence was also reflected, by transferring the measured signal from two-dimensional to three-dimensional. Additionally, the optimal values of the hyper-parameters of the Conv1D model were determined, using the grid search technique. Finally, the results show that the proposed data preprocessing method as well as the Conv1D model, can reflect the sequential dependency between the fault and its effect on the measured signal, and appropriately perform anomaly as well as failure detection, of the equipment chosen for application.
참고문헌 (23)
- Agrawal, A., "Using CNN for facial expression recognition: a study of the effects of kernel size and number of filters on accuracy", The Visual Computer, 36(2), pp.405~412 (2020)
- Aslam, S., "Internet of ships: A survey on architectures, emerging applications, and challenges", IEEE Internet of Things journal, 7(10), pp.9714~9727 (2020)
- Chen, Y. H., "Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks", IEEE journal of solid-state circuits, 52(1), pp.127~138 (2016)
- Chou, J. S., "Forward forecast of stock price using sliding-window metaheuristicoptimized machine-learning regression", IEEE Transactions on Industrial Informatics, 14(7), pp.3132~3142 (2018)
- Ellefsen, A. L., "A comprehensive survey of prognostics and health management based on deep learning for autonomous ships", IEEE Transactions on Reliability, 68(2), pp.720~740 (2019)
- He, M., "Deep learning based approach for bearing fault diagnosis", IEEE Transactions on Industry Applications, 53(3), pp.3057~3065 (2017)
- 정호철, "에너지인터넷에서 1D-CNN과 양방향 LSTM을이용한 에너지 수요예측", 전기전자학회논문지, 23(1), pp.134~142 (2019), 한국전기전자학회[DOI]
- Kattenborn, T., "Review on Convolutional Neural Networks (CNN) in vegetation remote sensing", ISPRS Journal of Photogrammetry and Remote Sensing, 173, pp.24~49 (2021)
- 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]
- Lei, Y., "A review on empirical mode decomposition in fault diagnosis of rotating machinery", Mechanical systems and signal processing, 35(1-2), pp.108~126 (2013)
- Lei, Y., "Applications of machine learning to machine fault diagnosis: A review and roadmap", Mechanical Systems and Signal Processing, 138, pp.106587~ (2020)
- Liang, C., "Research on ship electronic power system fault diagnosis based on expert system", IOP Conference Series: Materials Science and Engineering, 17(1), pp.12~17 (2020)
- Liu, R., "Artificial intelligence for fault diagnosis of rotating machinery:A review", Mechanical Systems and Signal Processing, 108, pp.33~47 (2018)
- Sharma, N., "An analysis of convolutional neural networks for image classification", Procedia computer science, 132, pp.377~384 (2018)
- Tao, H., "An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks", Journal of the Franklin Institute, 357(11), pp.7286~7307 (2020)
- Tran, T. N., "Grid Search of Convolutional Neural Network model in the case of load forecasting", Archives of Electrical Engineering, 70(1) (2021)
- Verstraete, D., "Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings", Shock and Vibration (2017)
- Wang, J., "A survey of technologies for unmanned merchant ships", IEEE Access, 8, pp.224461~224486 (2020)
- Wu, H., "Towards dropout training for convolutional neural networks", Neural Networks, 71, pp.1~10 (2015)
- Yahmed, Y. B., "Adaptive sliding window algorithm for weather data segmentation", Journal of theoretical and applied information technology, 80(2), pp.322~ (2015)
- Zhang, K., "Learning deep CNN denoiser prior for image restoration", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.3929~3938 (2017)
- Zhang, Y., "A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification", arXiv preprint arXiv:1510.03820, ~ (2015)
- Zhao, L., "A Hybrid Time Series Model based on Dilated Conv1D and LSTM with Applications to PM2. 5 Forecasting", Aust. J. Intell. Inf. Process. Syst, 17(2), pp.49~60 (2019)