Actuator Fault-Detection for Autonomous Underwater Vehicles Using Unsupervised Learning

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Matt Kemp Ben Raanan

Abstract

Many Autonomous Underwater Vehicles (AUV) have high rates of false-alarms because their health management relies on user-generated rules. The false-alarm rate could be substantially smaller if fault-detection were based on actual actuator performance instead of heuristics. We collected
performance data on a critical AUV actuator, a mass-shifter, and from the data developed an unsupervised fault detector. We found that a small number of features were sufficient to detect known and novel faults with a high probability of detection and a low false alarm rate. We also found that npoint false-alarm reduction schemes performed poorly due to correlation during startup.

How to Cite

Kemp, M., & Raanan, B. (2017). Actuator Fault-Detection for Autonomous Underwater Vehicles Using Unsupervised Learning. Annual Conference of the PHM Society, 9(1). https://doi.org/10.36001/phmconf.2017.v9i1.2486
Abstract 108 | PDF Downloads 74

##plugins.themes.bootstrap3.article.details##

Keywords

autonomous robots, autonomous, Component-based systems, Subsystem Health Monitoring, component-level PHM

References
Bellingham, J.G., Zhang, Y., Kerwin, J.E., Erikson, J., Hobson, B., Kieft, B., & Banka, A. (2010). Efficient Propulsion for the Tethys Long-Range Autonomous Underwater Vehicle. Proceedings of IEEE/OES Autonomous Underwater Vehicles Conference, Sept 1-3, Monterey CA.
Bellingham, J.G. (2014). Fault Detection, Diagnosis, and Mitigation for Long-Duration AUV Missions with Minimal Human Intervention. ONR Autonomy
Workshop, Sept 25, Arlington VA.
Bounsiar, A,. & Madden, M. (2014). Kernels for One-Class Support Vector Machines. Proceedings of IEEE International Conference on Information Science and Applications.
Brito, M.P., Smeed, D., & Griffiths, G. (2014). Underwater Glider Reliability and Implications for Survey Design. Journal of Atmospheric and Oceanic Technology, 31, 2858.
Brito, M.P. (2015), Reliability Case Notes No 9: Autosub Long Range Risk Assessment Report. NOCR Report 51.
Fagogenis, G., De Carolis, V., & Lane, D.M. (2016). Online Fault Detection and Model Adaptations for Underwater Vehicles in the Case of Thruster Failures.
Griffiths, G., Millard, N.W., McPhail, S.D., Stevenson, P., & Challenor, P.G. (2003). On the Reliability of the Autosub Autonomous Underwater Vehicle. International Journal of the Society for Underwater Technology, 25, 175.
Kieft, B., Bellingham, J.G., Godin, M.A., Hobson, B. Hoover, T., McEwen, R.S., & Mellinger, E.C. (2011). Fault Detection and Failure Prevention on the Tethys Long-Range Autonomous Underwater Vehicle, Proceedings of Unmanned Untethered Submersible Technology Conference, August 21-24, Durham NH.
Mardia, K.V. (1980), 9 Tests of univariate and multivariate normality, Handbook of Statistics Volume 1, 279.
Raanan, B. Bellingham, J.G., Zhang, Y., Kemp, M., Kieft, B., Singh, H., & Girdhar, Y. (2016). Automatic Fault Diagnosis for Autonomous Underwater Vehicles using Online Topic Models, Proceedings of Ocean 2016 Conference, Sept 19-22, Monterey CA.
Raanan, B., Bellingham, J.G., Zhang, Y., Kemp, M., Kieft, B., Singh, H., & Girdhar, Y. (2017). Detection of Unanticipated Faults for Autonomous Underwater Vehicles using Online Topic Models. Journal of Field Robotics, in press.
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001). Estimating the Support of a High-Dimensional Distribution. Neural computation, 13(7), 1443-1471.
Section
Technical Papers