Lloyd’s Register—Cyber CBM (Condition based maintenance)
Joseph MorelosLloyd’s Register Global Technology Centre, University of Southampton Boldrewood Campus, Burgess Road, Southampton SO16 7QF. Email: joseph.morelos@lr.org
The APPEA Journal 57(2) 623-628 https://doi.org/10.1071/AJ16223
Accepted: 6 March 2017 Published: 22 June 2017
Abstract
Classification survey requirements are anchored on the concept of a periodic, time-based preventive maintenance regime. The underlying principle of the periodic maintenance philosophy is that parts and components of equipment, machinery, systems and structures eventually wear out, thus the safety and reliability of parts and components – indeed the entire vessel – are directly correlated with time and operational age. While development of techniques and technologies have continuously improved surveys and inspection, the periodic maintenance philosophy has been the de-facto standard in marine and offshore industries for many decades.
This paper presents Lloyd Register’s Cyber condition based maintenance (CBM) technique: a scalable evaluation of components, equipment, machinery, systems and structures that detects their emergent faults, and characterises their progression to failure. This is an important step in the evolution of in-service classification:moving away from a periodic, time-based maintenance regime into an intelligent, real-time and predictive vessel health maintenance regime.
Keywords: data acquisition, data-driven techniques, data processing, diagnostics, edge computing, in-service classification, physics of failures techniques, prognostics, reliability based techniques, sensors.
Joseph Morelos is part of Lloyd’s Register Marine and Offshore Innovation team and has 15 years’ experience in the maritime industry. Currently dedicated to understanding novel, agnostic technologies and their practical applications in the marine industry, Joseph has dealt with a variety of new building projects including cruise ships, gas fuelled vessels, liquefied natural gas (LNG) tankers, naval vessels and passenger ferries. His last role was Lead Technical Specialist for engineering systems, which focused on the safe deployment of LNG to use as a marine fuel and the application of safe return to port principles in large passenger ferries and cruise ships. He has also represented LR in IACS working groups involving LNG and the use of gas as a marine fuel. He holds a BSc in mechanical engineering from the University of the Philippines and training from the Institution of Gas Engineers and Managers. |
References
BAE Systems. (2016). Real-time analytical tool monitors health of Royal Navy ships. Press release 18 July 2016. Available at: http://www.baesystems.com/en/article/real-time-analytical-tool-monitors-health-of-royal-navy-ships [Verified 10 March 2017]Byington, C. S., Roemer, M. J., and Galie, T. (2002). Prognostic enhancements to diagnostic systems for improved condition-based maintenance. In: IEEE aerospace conference proceedings, Big Sky, Montana, 9–16 March 2002.
Coble, J., Ramuhalli, P., Bond, L. J., Hines, J. W., and Ipadhyaya, B. (2015). A Review of Prognostics and Health Management Applications in Nuclear Power Plants. International Journal of Prognostics and Health Management 6, 016.
GE. (2016). Predix: Your Platform for the Industrial Internet. Brochure. Available at: https://www.ge.com/digital/sites/default/files/Predix-Platform-for-the-Industrial-Internet-Datasheet-from-GE-Digital.pdf [Verified 10 March 2017]
Goebel, K. (2007). Prognostics and Health Management, guest lecture, ENME 808A – Fall 2007. Methods for Making Predictions: model based methods, data driven methods and hybrid approaches, pp. 8–9 and 54–55 of 69.
Goebel, K., Saxena, A., Daigle, M., Celaya, J., and Roychoudhury, I. (2012). Introduction to Prognostics. In First European Conference of the Prognosis and Health Management Society (NASA Ames).
IAEA [International Atomic Energy Agency]. (2013). Advanced Surveillance, Diagnostic and Prognostic Techniques in Monitoring Structures, Systems and Components in Nuclear Power Plants, IAEA Nuclear Energy Series No. NP-T-3.14, IAEA, Vienna.
LR (2016). Cyber-enabled ships. ShipRight Procedure – autonomous ships. (Lloyds Register) Available at: http://info.lr.org/l/12702/2016-07-07/32rrbk [Verified 24 April 2017]
Moore Stephens. (2012). OpCost 2012 annual report: Ship operating cost benchmarking report. (Moore Stephens: London)
NAVSEA. (2010). Handbook of reliability and methods of predictions. Chapter 19. Sensor uncertainty theories.
Rolls Royce. (2017). Rolls-Royce announces investment in Research & Development for Ship Intelligence. Press release 8 March 2017. Available at: https://www.rolls-royce.com/media/press-releases/yr-2017/08-03-2017-rr-announces-investment-in-research.aspx [Verified 24 April 2017]
Saxena, A. (2010). Prognostics: Science of Prediction. In Annual Conference of the PHM Society, 10–14 October 2010, Portland, OR. Available at: https://www.phmsociety.org/sites/phmsociety.org/files/Saxena_Prognostics_TutorialPHM10.pdf [Verified 24 April 2017].
Silva, J. C., Saxena, A., Balaban, E., and Goebel, K. (2012). A knowledge-based system approach for sensor fault modeling, detection and mitigation. Journal of Expert Systems 39, 10977–10989.
| A knowledge-based system approach for sensor fault modeling, detection and mitigation.Crossref | GoogleScholarGoogle Scholar |
Wärtsilä Services. (2015). Lifecycle efficiency through optimising operations. Presentation. (Wärtsilä Services).
