주성분 분석을 통한 선박 기관 상태의 차수 축소 모델링
Reduced Order Modeling of Marine Engine Status by Principal Component Analysis
6
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The present study concerns reduced order modeling of a marine diesel engine, which can be used for outlier detection in status monitoring and carbon intensity index calculation. Principal Component Analysis (PCA) is introduced for the reduced order modeling, focusing on the feasibility of detecting and treating nonlinear variables. By cross-correlation, it is found that there are seven non-linear data channels among 23 data channels, i.e., fuel mode, exhaust gas temperature after the turbocharger, and cylinder coolant temperatures. The dataset is handled so that the mean is located at the nominal continuous rating. Polynomial presentation of the dataset is also applied to reflect the linearity between the engine speed and other channels. The first principal mode shows strong effects of linearity of the most data channels to show the linearity of the system. The non-linear variables are effectively explained by other modes. second mode concerns the temperature of the cylinder cooling water, which shows small correlation with other variables. The third and fourth modes correlates the fuel mode and turbocharger exhaust gas temperature, which have inferior linearity to other channels. PCA is proven to be applicable to data given in binary type of fuel mode selection, as well as numerical type data.
Abstract
The present study concerns reduced order modeling of a marine diesel engine, which can be used for outlier detection in status monitoring and carbon intensity index calculation. Principal Component Analysis (PCA) is introduced for the reduced order modeling, focusing on the feasibility of detecting and treating nonlinear variables. By cross-correlation, it is found that there are seven non-linear data channels among 23 data channels, i.e., fuel mode, exhaust gas temperature after the turbocharger, and cylinder coolant temperatures. The dataset is handled so that the mean is located at the nominal continuous rating. Polynomial presentation of the dataset is also applied to reflect the linearity between the engine speed and other channels. The first principal mode shows strong effects of linearity of the most data channels to show the linearity of the system. The non-linear variables are effectively explained by other modes. second mode concerns the temperature of the cylinder cooling water, which shows small correlation with other variables. The third and fourth modes correlates the fuel mode and turbocharger exhaust gas temperature, which have inferior linearity to other channels. PCA is proven to be applicable to data given in binary type of fuel mode selection, as well as numerical type data.
참고문헌 (20)
- Alexandris, N., "Remote sensing of burned areas via PCA, Part 1; centering, scaling and EVD vs SVD. Open Geospatial Data, Software and Standards, 2, Article No. 17", ~ (2017)
- Bishop, C. M., "Pattern Recognition and Machine Learning" (2006), Springer-Verlag
- Kim, S. -H., "A study on the design of fault diagnostic system based on PCA", Journal of Korean Institute of Intelligent Systems, 13(5), pp.600~605 (2003)
- Kim, Y. -I., "The development of diesel engine room fault diagnosis system using a correlation analysis method", Journal of the Korean Society of Marine Engineering, 30(2), pp.253~259 (2006)
- Kim, K. -S., "Development of an application for predicting and visualizing the ocean weather", Korean Journal of Computational Design and Engineering, 25(4), pp.434~444 (2020)
- Kim, D., "Abnormaly detection of vessel main engine big data using Gaussian mixture model", Journal of the Korean Data Analysis Society, 22(4), pp.1473~1489 (2020)
- Kim, D., "Outlier detection and labeling of ship main engine using LSTM-AutoEncoder", The Korea Journal of Big Data, 7(1), pp.125~137 (2022)
- Korean Register, "Guidebook for CII Regulation", Korean Register R&D Division, ~ (2021)
- Landgraf, A. J., "Dimensionality reduction for binary data through the projection of natural parameters", Journal of Multivariate Analysis, pp.180~ (2020)
- Lee, S. B., "Proper orthogonal decomposition of pressure fluctuations in moonpool", Journal of the Society of Naval Architects of Korea, 49(6), pp.484~490 (2012)
- Lee, J. H., "Proper orthogonal decomposition and its application: parametric reduced order models", Computational Structural Engineering, 30(1), pp.29~35 (2017)
- Leeuw, J., "Principal component analysis of binary data by iterated singular value decomposition", Computational Statistics and Data analysis, 50(1), pp.21~39 (2006)
- Loyola-Gonzalez, O., "Black-box vs white-box:understanding their advantages and weaknesses from a practical point of view", IEEE Access, 7, pp.154096~154113 (2019)
- Moeini, B., "Surface analysis insight note. Principal component analysis (PCA) of an X-ray photoelectron spectroscopy image. The importance of preprocessing", Surface and Interface Analysis, 55(11), pp.798~807 (2023)
- Paik, B. -G., "Analysis of the unstable propeller wake using POD method", Journal of the Society of Naval Architects of Korea, 47(1), pp.20~29 (2010)
- Park, J. -H., "Forecasting algorithm for vessel engine failure", Journal of Korean Institute of Information Technology, 14(11), pp.109~117 (2016)
- Park, J. -H., "Improved forecasting algorithm for vessel engine failure", Journal of Korean Institute of Information Technology, 15(11), pp.175~185 (2017)
- Park, J. -C., "The study of failure mode data development and feature parameter’s reliability verification using LSTM algorithm for 2-stroke low speed engine for ship’s propulsion", Journal of the Society of Naval Architects of Korea, 60(2), pp.95~109 (2023)
- Savage, N., "Breaking into the black box of artificial intelligence", Nature (2022)[DOI]
- Shin, S. -Y., "A study on the effect of large coherent structures to the skin friction by POD analysis", Journal of the Society of Naval Architects of Korea, 54(5), pp.406~414 (2017)