SAFeCRAFT Develops Predictive Maintenance Tools for Alternative-Fuel Systems

Keeping an alternative-fuel system reliable over its service life depends on detecting problems early, before they affect safety or operation. Under Task 5.6 of the SAFeCRAFT project, the University of Patras (UPAT) is developing predictive maintenance tools for the fuel system, working together with the University of Strathclyde, the School of Naval Architecture and Marine Engineering at the National Technical University of Athens (NTUA) and Technische Universität Dresden (TUD).

The tools are being built into the SAFeCRAFT digital platform, where they will monitor the performance of the fuel system in real time and flag potential issues at an early stage. Over time, the platform will also accumulate and analyse large volumes of operational data, making it possible to recognise trends and patterns and to plan maintenance on the basis of evidence rather than fixed intervals. By embedding predictive maintenance in an open digital environment, the project aims to make this approach readily transferable to industry.

The work builds directly on the multiphysics models developed in Task 5.4, which simulate bunkering and fuel-supply processes under a range of operating conditions. These models are now being combined with machine-learning algorithms, currently under development, that will interpret the data the models generate and recommend appropriate maintenance actions. Task 5.6 is advancing well and is approaching the point at which the models, algorithms and methods developed so far will be brought together to produce first results.

Depending on the configuration of the final demonstration, the tools could be applied to the monitoring and predictive maintenance of the fuel system onboard the project’s demonstrator vessel, providing a real-world test of their value.

 Through this work, SAFeCRAFT is adding a further element to its digital toolset for the safe, efficient and sustainable use of alternative fuels in maritime transport.

Read also

Hydrus
Hydrus
Hydrus
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognizing you when you return to our website and helping our team understand which sections of the website you find most interesting and useful.
Find out more information on our Cookie policy page.