Expert-Informed Hierarchical Diagnostics of Multiple Fault Modes of a Spacecraft Propulsion System
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Published
Sep 4, 2023
Osarenren Kennedy Aimiyekagbon
Alexander Lowen
Amelie Bender
Lars Muth
Walter Sextro
Abstract
This paper presents a comprehensive study on diagnosing a spacecraft propulsion system utilizing data provided by the Prognostics and Health Management (PHM) society, specifically obtained as part of the Asia-Pacific PHM conference’s data challenge 2023. The objective of the challenge is to identify and diagnose known faults as well as unknown anomalies in the spacecraft’s propulsion system, which is critical for ensuring the spacecraft’s proper functionality and safety. To address this challenge, the proposed method follows a systematic approach of feature extraction, feature selection, and model development. The models employed in this study are kMeans clustering and decision trees combined to ensembles, enriched with expert knowledge. With the method presented, our team was capable of reaching high accuracy in identifying anomalies as well as diagnosing faults, resulting in attaining the seventh place with a score of 93.08 %.
##plugins.themes.bootstrap3.article.details##
Keywords
PHM, Data, anomaly detection, Kmeans, fault management
References
Aimiyekagbon, O. K., Bender, A., & Sextro, W. (2021). On the applicability of time series features as health indicators for technical systems operating under varying conditions. 17. International Conference on Condition Monitoring and Asset Management (CM 2021).
Aimiyekagbon, O. K., Muth, L., Wohlleben, M., Bender, A., & Sextro, W. (2021). Rule-based diagnostics of a production line. Proceedings of the 6th European Conference of the Prognostics and Health Management Society 2021, 527–536.
Al-Khayat, R. H., Al-Fatlawi, A. W. A., Al-Baghdadi, M. A. S., & Al-Waily, M. (2022). Water hammer phenomenon in pumping stations: A stability investigation based on root locus. Open Engineering, 12(1), 254–262.
Bandyopadhyay, A., & Majumdar, A. (2014). Network flow simulation of fluid transients in rocket propulsion systems. Journal of Propulsion and Power, 30(6), 1646– 1653.
Bombardieri, C., Traudt, T., & Manfletti, C. (2019). Experimental study of water hammer pressure surge. Progress in Propulsion Physics, 11, 555–570.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140. doi: 10.1007/BF00058655
Christ, M., Braun, N., Neuffer, J., & Kempa-Liehr, A. W. (2018). Time series feature extraction on basis of scalable hypothesis tests (tsfresh – a python package). Neurocomputing, 307, 72-77. doi: 10.1016/j.neucom.2018 .03.067
Fulcher, B., Cliff, O., Harris, B., Philiphorst, Sethi, S., Lubba, C. H., . . . Haohua Li (2020). benfulcher/hctsa: v1.04. Zenodo. Retrieved from https://zenodo .org/record/3955668 doi: 10.5281/ZENODO .3955668
Fulcher, B. D., Little, M. A., & Jones, N. S. (2013). Highly comparative time-series analysis: the empirical structure of time series and their methods. Journal of the Royal Society, Interface, 10(83), 20130048. doi: 10.1098/rsif.2013.0048
Fulcher, B. D., Little, M. A., & Jones, N. S. (2022). Hctsa documentation. Retrieved from https://hctsa-users.gitbook.io/hctsa-manual/ (Last viewed in: 08.2023)
Gao, Y., Yang, T., Xing, N., & Xu, M. (2012). Fault detection and diagnosis for spacecraft using principal component analysis and support vector machines. In 2012 7th ieee conference on industrial electronics and applications (iciea) (pp. 1984–1988). doi: 10.1109/ICIEA.2012.6361054
Geron, A. (2019). ´ Hands-on machine learning with scikitlearn, keras, and tensorflow: Concepts, tools, and techniques to build intelligent systems (Second edition ed.). Beijing and Boston and Farnham and Sebastopol and Tokyo: O’Reilly.
Hennig, M., Grafinger, M., Gerhard, D., Dumss, S., & Rosenberger, P. (2020). Comparison of time series clustering algorithms for machine state detection. Procedia CIRP, 93, 1352-1357. Retrieved from https:// www.sciencedirect.com/science/article/pii/S2212827120307149 (53rd CIRP Conference on Manufacturing Systems 2020) doi: https://doi.org/10.1016/j.procir.2020.03.084
Hoque, N., Bhattacharyya, D., & Kalita, J. (2014). Mifs-nd: A mutual information-based feature selection method. Expert Systems with Applications, 41(14), 6371-6385. doi: https://doi.org/10.1016/j.eswa.2014.04.019
Katipamula, S., & Brambley, M. R. (2005). Methods for fault detection, diagnostics, and prognostics for building systems—a review, part i. Hvac&R Research, 11(1), 3–25.
Kimotho, J. K., & Sextro, W. (2014). An approach for feature extraction and selection from non-trending data for machinery prognosis. In Proceedings of the second european conference of the prognostics and health management society 2014 (Vol. 5).
Li, J., Cheng, K., Wang, S., Morstatter, F., Trevino, R. P., Tang, J., & Liu, H. (2017). Feature selection: A data perspecitve. ACM Computing Surveys, 50(6), 1–45.
Liu, H., & Setiono, R. (1995). Chi2: feature selection and discretization of numeric attributes. In Proceedings of 7th ieee international conference on tools with artificial intelligence (pp. 388–391). doi: 10.1109/ TAI.1995.479783
Loh, W.-Y. (2011). Classification and regression trees. WIREs Data Mining and Knowledge Discovery, 1(1), 14–23. doi: 10.1002/widm.8
Magnello, M. (2005). Chapter 56 - karl pearson, paper on the chi square goodness of fit test (1900). In I. GrattanGuinness, R. Cooke, L. Corry, P. Crepel, & N. Guicciar- ´ dini (Eds.), Landmark writings in western mathematics 1640-1940 (p. 724-731). Amsterdam: Elsevier Science. doi: https://doi.org/10.1016/B978-044450871-3/ 50137-6
Nie, L., Zhang, L., Xu, S., Cai, W., & Yang, H. (2022). Remaining useful life prediction for rolling bearings based on similarity feature fusion and convolutional neural network. In Journal of the brazilian society of mechanical sciences and engineering (Vol. 44). doi: 10.1007/s40430-022-03638-0
Pearson, K. (1900). On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 50(302), 157-175. doi: 10.1080/14786440009463897
PHM Society. (2023). Phmap data challenge. 2023 Asia–Pacific Prognostics and Health Management Society (PHMAP) Data Challenge. Retrieved from https://data.phmsociety.org/ phmap-2023-data-challenge/ (Retrieved on: 22.07.2023)
Rodrıguez Ramos, A., Dom´ınguez Acosta, C., Rivera Torres, P. J., Serrano Mercado, E. I., Beauchamp Baez, G., Rifon, L. A., & Llanes-Santiago, O. (2019). An approach to multiple fault diagnosis using fuzzy logic. Journal of Intelligent Manufacturing, 30, 429–439.
Tominaga, K., Fujii, G., Nagata, T., Wada, D., Hisada, S., Kawatsu, K., & Kasai, T. (2023). Anomaly detection method for spacecraft propulsion system using frequency response functions of multiplexed fbg data. Acta Astronautica. Retrieved from https:// www.sciencedirect.com/science/ article/pii/S0094576523003739 doi: https://doi.org/10.1016/j.actaastro.2023.07.022
Tsai, Y. S., King, P. H., Higgins, M. S., Pierce, D., & Patel, N. P. (1997). An expert-guided decision tree construction strategy: an application in knowledge discovery with medical databases. Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium, 208–212.
Zhang, S., Zhang, S., Wang, B., & Habetler, T. G. (2020). Deep learning algorithms for bearing fault diagnostics—a comprehensive review. IEEE Access, 8, 29857– 29881
Aimiyekagbon, O. K., Muth, L., Wohlleben, M., Bender, A., & Sextro, W. (2021). Rule-based diagnostics of a production line. Proceedings of the 6th European Conference of the Prognostics and Health Management Society 2021, 527–536.
Al-Khayat, R. H., Al-Fatlawi, A. W. A., Al-Baghdadi, M. A. S., & Al-Waily, M. (2022). Water hammer phenomenon in pumping stations: A stability investigation based on root locus. Open Engineering, 12(1), 254–262.
Bandyopadhyay, A., & Majumdar, A. (2014). Network flow simulation of fluid transients in rocket propulsion systems. Journal of Propulsion and Power, 30(6), 1646– 1653.
Bombardieri, C., Traudt, T., & Manfletti, C. (2019). Experimental study of water hammer pressure surge. Progress in Propulsion Physics, 11, 555–570.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140. doi: 10.1007/BF00058655
Christ, M., Braun, N., Neuffer, J., & Kempa-Liehr, A. W. (2018). Time series feature extraction on basis of scalable hypothesis tests (tsfresh – a python package). Neurocomputing, 307, 72-77. doi: 10.1016/j.neucom.2018 .03.067
Fulcher, B., Cliff, O., Harris, B., Philiphorst, Sethi, S., Lubba, C. H., . . . Haohua Li (2020). benfulcher/hctsa: v1.04. Zenodo. Retrieved from https://zenodo .org/record/3955668 doi: 10.5281/ZENODO .3955668
Fulcher, B. D., Little, M. A., & Jones, N. S. (2013). Highly comparative time-series analysis: the empirical structure of time series and their methods. Journal of the Royal Society, Interface, 10(83), 20130048. doi: 10.1098/rsif.2013.0048
Fulcher, B. D., Little, M. A., & Jones, N. S. (2022). Hctsa documentation. Retrieved from https://hctsa-users.gitbook.io/hctsa-manual/ (Last viewed in: 08.2023)
Gao, Y., Yang, T., Xing, N., & Xu, M. (2012). Fault detection and diagnosis for spacecraft using principal component analysis and support vector machines. In 2012 7th ieee conference on industrial electronics and applications (iciea) (pp. 1984–1988). doi: 10.1109/ICIEA.2012.6361054
Geron, A. (2019). ´ Hands-on machine learning with scikitlearn, keras, and tensorflow: Concepts, tools, and techniques to build intelligent systems (Second edition ed.). Beijing and Boston and Farnham and Sebastopol and Tokyo: O’Reilly.
Hennig, M., Grafinger, M., Gerhard, D., Dumss, S., & Rosenberger, P. (2020). Comparison of time series clustering algorithms for machine state detection. Procedia CIRP, 93, 1352-1357. Retrieved from https:// www.sciencedirect.com/science/article/pii/S2212827120307149 (53rd CIRP Conference on Manufacturing Systems 2020) doi: https://doi.org/10.1016/j.procir.2020.03.084
Hoque, N., Bhattacharyya, D., & Kalita, J. (2014). Mifs-nd: A mutual information-based feature selection method. Expert Systems with Applications, 41(14), 6371-6385. doi: https://doi.org/10.1016/j.eswa.2014.04.019
Katipamula, S., & Brambley, M. R. (2005). Methods for fault detection, diagnostics, and prognostics for building systems—a review, part i. Hvac&R Research, 11(1), 3–25.
Kimotho, J. K., & Sextro, W. (2014). An approach for feature extraction and selection from non-trending data for machinery prognosis. In Proceedings of the second european conference of the prognostics and health management society 2014 (Vol. 5).
Li, J., Cheng, K., Wang, S., Morstatter, F., Trevino, R. P., Tang, J., & Liu, H. (2017). Feature selection: A data perspecitve. ACM Computing Surveys, 50(6), 1–45.
Liu, H., & Setiono, R. (1995). Chi2: feature selection and discretization of numeric attributes. In Proceedings of 7th ieee international conference on tools with artificial intelligence (pp. 388–391). doi: 10.1109/ TAI.1995.479783
Loh, W.-Y. (2011). Classification and regression trees. WIREs Data Mining and Knowledge Discovery, 1(1), 14–23. doi: 10.1002/widm.8
Magnello, M. (2005). Chapter 56 - karl pearson, paper on the chi square goodness of fit test (1900). In I. GrattanGuinness, R. Cooke, L. Corry, P. Crepel, & N. Guicciar- ´ dini (Eds.), Landmark writings in western mathematics 1640-1940 (p. 724-731). Amsterdam: Elsevier Science. doi: https://doi.org/10.1016/B978-044450871-3/ 50137-6
Nie, L., Zhang, L., Xu, S., Cai, W., & Yang, H. (2022). Remaining useful life prediction for rolling bearings based on similarity feature fusion and convolutional neural network. In Journal of the brazilian society of mechanical sciences and engineering (Vol. 44). doi: 10.1007/s40430-022-03638-0
Pearson, K. (1900). On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 50(302), 157-175. doi: 10.1080/14786440009463897
PHM Society. (2023). Phmap data challenge. 2023 Asia–Pacific Prognostics and Health Management Society (PHMAP) Data Challenge. Retrieved from https://data.phmsociety.org/ phmap-2023-data-challenge/ (Retrieved on: 22.07.2023)
Rodrıguez Ramos, A., Dom´ınguez Acosta, C., Rivera Torres, P. J., Serrano Mercado, E. I., Beauchamp Baez, G., Rifon, L. A., & Llanes-Santiago, O. (2019). An approach to multiple fault diagnosis using fuzzy logic. Journal of Intelligent Manufacturing, 30, 429–439.
Tominaga, K., Fujii, G., Nagata, T., Wada, D., Hisada, S., Kawatsu, K., & Kasai, T. (2023). Anomaly detection method for spacecraft propulsion system using frequency response functions of multiplexed fbg data. Acta Astronautica. Retrieved from https:// www.sciencedirect.com/science/ article/pii/S0094576523003739 doi: https://doi.org/10.1016/j.actaastro.2023.07.022
Tsai, Y. S., King, P. H., Higgins, M. S., Pierce, D., & Patel, N. P. (1997). An expert-guided decision tree construction strategy: an application in knowledge discovery with medical databases. Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium, 208–212.
Zhang, S., Zhang, S., Wang, B., & Habetler, T. G. (2020). Deep learning algorithms for bearing fault diagnostics—a comprehensive review. IEEE Access, 8, 29857– 29881
Section
Data Challenge Papers
This work is licensed under a Creative Commons Attribution 3.0 Unported License.