Anomaly Detection Using Dynamical Linear Models and Sequential Testing on a Marine Engine System
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
This paper presents a study on the use of Dynamical Linear Models for anomaly detection and condition monitoring of a marine engine system. Various sensors are installed at different places within the engine system and records essential parameters such as power output from the engine, engine speed, bearing temperatures and various other temperatures, speeds and pressures for selected engine components. The idea is to utilize the information in these sensor signals in order to monitor the condition of the engine. Such a condition monitoring system should include means of fault detection, diagnosis and prognostics, where robust anomaly detection is a prerequisite for reliable management of the system. Dynamical
Linear Models (DLM) constitute a flexible framework for modelling of sensor signals, where the sensor signals are modelled conditional on some latent states, and the model provides forecasts of the signals that can be compared to new sensor readings. Statistical sequential model testing will then be performed on the forecast errors and model breakdown can be an indication of deviation from normal conditions and possible
impending failures of the engine system. This will then call for further diagnostics and prognostics tasks to interpret the nature of the deviations. The Dynamical Linear Model framework can accommodate a range of candidate models. However, very complicated models in high dimensions may be computationally expensive to estimate and apply, so various pre-processing techniques are investigated in this paper to improve model performance, including simple regression models, cluster analysis and principal component transformation.
How to Cite
##plugins.themes.bootstrap3.article.details##
Condition monitoring, Time series analysis, Marine applications, Fault detection, Data driven models
Baraldi, P., Di Maio, F., Pappaglione, L., Zio, E., & Seraoui, R. (2012). Conditional monitoring of electrical power plant components during operational transients. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 226, 568-583.
Brandsæter, A., Manno, G., Vanem, E., & Glad, I. K. (2016, June). An application of sensor based anomaly detection in the maritime industry. In Proc. IEEE PHM2016.
DNV GL. (2015). Ship connectivity (Tech. Rep. No. Strategic Research and Innovation Position Paper 4-2015). DNV GL.
DNV GL. (2017a). Rules for classification - general regulations. (DNVGL-RU-0050)
DNV GL. (2017b). Rules for classification: Ships. (DNVGLRU-SHIP)
Eleftheria, E., Papanikolaou, A., & Voulgarellis, M. (2016). Statistical analysis of ship accidents and review of safety level. Safety Science, 85, 282-292.
Hayes, M. A., & Capretz, M. A. (2015). Contextual anomaly detection framework for big sensor data. Journal of Big Data, 2, 1-22.
Hines, J. W., & Garvey, D. R. (2006). Development and application of fault detectability performance metrics for instrument calibration verification and anomaly detection. Journal of Pattern Recognition Research, 1, 2-15.
IMO. (2014a). International Safety Management Code (ISM Code) with guidelines for its implementation (2014 edition). International Maritime Organization.
IMO. (2014b). SOLAS, consolidated edition 2014. International Maritime Organization.
Kulldorff, M., Davis, R. L., Kolczak, Lewis, E., Lieu, T., & Platt, R. (2011). A maximized sequential probability ratio test for drug and vaccine safety surveillance. Sequential Analysis, 30, 58-78.
Mindykowski, J., & Tarasiuk, T. (2015). Problems of power quality in the wake of ship technology development. Ocean Engineering, 107, 108-117.
Niculita, O., Nwora, O., & Skaf, Z. (2017). Towards design of prognostics and health management solutions for maritime assets. Procedia CIRP, 59, 122-132.
Psarros, G. A. (2015, May-June). Comparing the navigator’s response time in collision and grounding accidents. In Proc. 34th international conference on ocean, offshore and arctic engineering (omae 2015).
Song, X., Wu, M., Jermaine, C., & Ranka, S. (2007). Conditional anomaly detection. IEEE Transactions on Knowledge and Data Engineering, 19, 631-645.
Vanem, E., Brandsæter, A., & Gramstad, O. (2016, September). Regression models for the effect of environmental conditions on the efficiency of ship machinery systems. In Proc. esrel 2016.
Vanem, E., Rus°as, S., Skjong, R., & Olufsen, O. (2007). Collision damage stability of passenger ships: Holistic and risk-based approach. International Shipbuilding Progress, 54, 323-337.
Vanem, E., & Skjong, R. (2004, July). Fire and evacuation risk assessment for passenger ships. In Proc. 10th international fire science and engineering conference (interflam) 2004 (Vol. 1, p. 365-374).
Vanem, E., & Storvik, G. O. (2016, August). Dynamical linear models for condition monitoring with multivariate sensor data. In Proc. comadem 2016.
Wald, A. (1945). Sequential tests of statistical hypotheses. The Annals of Mathematical Statistics, 16, 117-186.
West, M., & Harrison, J. (1997). Bayesian forecasting and dynamic models (Second ed.). Springer-Verlag.
Zymaris, A. S., Alnes, Ø. A° ., Knutsen, K. E., & Kakalis, N. M. P. (2016, July). Towards a model-based condition assessment of complex marine machinery systems using systems engineering. In Proc. Third European Conference of the Prognostics and Health Management Society 2016.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.