A PHM implementation frame work for MASS (Maritime Autonomous Surface Ships) based on RAM (Reliability Availability Maintainability)

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

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

Published Jun 27, 2024
Toby Adam Michael Russell Octavian Niculita

Abstract

The paper focuses on PHM in the maritime industry, specifically on the maintenance of uncrewed vessels, in contrast to the more commonly discussed navigation. The paper examines the potential challenges of removing the maintenance crew and the potential benefits that can result from this major change in operations.
The removal of the primary maintenance team from a vessel necessitates an increase in monitoring and analysis that can be realised by the techniques of PHM. By looking from the perspective of stakeholders, the challenges and opportunities of PHM implementation become clearer. In comparing the challenges that faced other industries with the maritime industry, roadmaps and proposals can be drawn up for vessel owners. There is a correlation between the phased removal of the engineering crew and the increases in monitoring that is required. Current large vessels that do not carry passengers can operate with UMS (un-manned machinery space) for limited periods. To allow this a specific set of sensors referred to as E0 (Engineers-zero) must be established and maintained. This E0 sensor set forms the basis for what is needed to allow UMS for longer periods of time. The critical equipment, as deemed by class societies, is monitored by E0. Acquiring the data from the E0 sensor set and performing PHM analysis on the data allows remote engineers to accurately determine the current and future state of critical equipment. This equipment list needs to be expanded. Causality based risk modelling is employed to establish a data driven critical equipment list and minimum sensor set to cover the maximum amount of failure modes. This builds on the current required E0 sensor set.
With a conventional maintenance system onboard a vessel the crew are doing a lot of the sensing. The crew act as intermediaries between various systems, taking data from one system to help diagnose another system, making a change to one system to help improve another system. The maintenance crew must balance the interfaces of each system so that a harmony or equilibrium can be achieved. This balancing act is part of what makes a PHM study on a vessel so interesting. Many systems onboard a vessel have a sole purpose to support the crew. With the removal of the crew these support systems can also be removed, simplifying the overall engineering of the vessel.
The methodology that has been used to assess the above points is to create a framework for the design and deployment of PHM to marine assets. The framework relates to RAM (Reliability, Availability, Maintainability) and considers stakeholder points of view and their inputs’ implications. In developing the framework, the stakeholder group is realised. The framework compares the ‘As-Is’ conventional method against the proposed PHM framework. The conclusions are that the E0 philosophy can be expanded upon to facilitate the integration of PHM. Also, the paper concludes that a PHM deployment framework gives the maritime industry a basis for using this modern technique for machinery health. Lastly, the paper shows that PHM is a vital element to uncrewed vessels.

How to Cite

Russell, T. A. M. ., & Niculita, O. (2024). A PHM implementation frame work for MASS (Maritime Autonomous Surface Ships) based on RAM (Reliability Availability Maintainability). PHM Society European Conference, 8(1), 16. https://doi.org/10.36001/phme.2024.v8i1.4073
Abstract 70 | PDF Downloads 57

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

Keywords

PHM, RAM, Maritime, MASS, Autonomous, AUV

References
Alexander Athanasios Kamtsiuris, ,. F. (2022). A Health Index Framework for Condition Monitoring and Health Predictions. Turin, Italy.: Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022 - ISBN – 978-1936263-36-3. Alexandre Trilla1, 3. N.-C. (2022). Towards Learning Causal Representations of Technical Word Embeddings for Smart Troubleshooting. International Journal of Prognostics and Health Management, ISSN21532648. Cornelius Scheffer, P. G. (2004). Machinery Vibration Alanysis & Predictive Maintenance. Defeo, J. A. (2010). Juran's Quality Handbook (6th ed.). McGraw-Hill Professional. H.J Hwang, J. L. (2018). A study of the development of a condition-based maintenance system for an LNG FPSO. Ocean Engineering. Hyung Jun Park, ,. N.-H. (2022). A Comparative Study of Health Monitoring Sensors based on Prognostic Performance. Turin, Italy.: Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022 - ISBN – 978-1-93626336-3. Kammal Al-Kahwati, W. B. (2022). Experiences of a Digital Twin Based Predictive Maintenance Solution for Belt Conveyor Systems. Turin, Italy.: Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022 - ISBN 978-1-936263-36-3. Knut Erik Knutsen, G. M. (2014). Beyond Condition Monitoring in the Maritime Industry. DNV. Maximilian-Peter Radtke1, J. B. (2022). Combining Knowledge and Deep Learning for Prognostics and Health Management. Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022 - ISBN – 978-1-93626336-3. Miguel Simão1, R. P. (2022). Long-term Evaluation of the State-of-Health of Traction Lithium-ion Batteries in Operational Buses. International Journal of Prognostics and Health Management, ISSN21532648.
Mulugeta Weldezgina Asres, G. C. (2022). Long Horizon Anomaly Prediction in Multivariate Time Series with Causal Autoencoders. Turin, Italy.: Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022 ISBN – 978-1-936263-36-3. Norway, S. (2010). Risk based maintenance & consequenceclassification. Lysaker, NORWAY: Standards Norway. Qin Lang, K. E. (2024). A review of maritime equipment prognostics health management from a classification society perspective. Ocean Engineering. Shipping, A. B. (2018). Guidance Notes on SMART Function Implementation. ABS. Shorten, D. C. (2012). Marine Machinery Condition Monitoring: Why has the shipping industry been slow to adopt? Lloyd's Register London. Sylvain Poupry, C. B. (2022). Towards data reliability based on triple redundancy and online outlier detection. Turin, Italy.: Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022 - ISBN – 978-1-93626336-3. Tilman Krokotsch1, M. K. (2022). Improving SemiSupervised Learning for Remaining Useful Lifetime Estimation Through Self-Supervision. International Journal of Prognostics and Health Management, ISSN2153-2648.

17. B IOGRAPHIES Toby Russell has 16 years at sea with the majority as chief ETO / Chief Electrical Engineer but also serving as 2nd engineer. Toby holds a MSc in applied Instrumentation and Control and he has a keen interest and passion for marine engineering that has progressed into the fields of RAM engineering to support the development of novel technologies to enable remote vessel operation on a commercial level. Toby has worked for Ocean Infinity for 2 years leading novel system development and integration projects as well as leading on development of RAM philosophies and strategies.

Octavian Niculita Octavian Niculita is a Senior Lecturer in Instrumentation with Glasgow Caledonian University. He has a PhD in Industrial Engineering from the Technical University of Iasi, Romania carried out under the EDSVS framework. His current research interests include industrial digitalisation, predictive maintenance, PHM system design, integration of PHM and asset design for aerospace, maritime, and oil & gas (surface and subsea) applications. Octav has over 15 years of experience in design and development of prognostics and health management applications, having worked on applied aerospace projects funded by The Boeing Company and BAE Systems as a Research Fellow and Technical Lead on his previous appointment with the IVHM Centre at Cranfield University, UK. He is a member of the Prognostics and Health Management Society, InstMC and the IET.
Section
Technical Papers