Actuator Fault-Detection for Autonomous Underwater Vehicles Using Unsupervised Learning
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
autonomous robots, autonomous, Component-based systems, Subsystem Health Monitoring, component-level PHM
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.
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.