Ships are a high-value asset and often operate in a hostile environment. To ensure their integrity, a smart intelligent asset integrity and maintenance platform is needed for managing the uncertainties and the risks for the people, the environment and the very expensive assets throughout their service life.
The Digital Monitoring of Ships (DiMOS) project aims to develop a disruptive integrated software platform capable of performing prescriptive maintenance of ship's structure, machinery and auxiliary system. It will do that by utilising data from wireless condition monitoring and diagnostic systems, implementing big data analytics, and integrating maintenance actions/prescription database powered by advanced deep learning algorithms. It will also select the best maintenance strategy (as prescription) for the targeted ship asset, based on the faults or conditions observed. Incorporating such intelligent software in maintenance will enable diagnostics and proactive maintenance, reducing assets downtime, and enabling a greater level of control and efficiency.
The key objectives of the DiMOS project are:
- Optimisation of sensor system for real-time condition monitoring of machinery and structure (hull) of ships;
- Development of intelligent diagnostic and prognostic models to detect faults or failures in ship;
- Development of risk assessment and failure analysis models;
- Development of maintenance procedures database;
- Design and development of machine learning based advanced data analytics and processing models for prescriptive maintenance;
- Integrated intelligent software platform for real-time condition monitoring and prescriptive maintenance of ships structure and machinery.
- Reduced reliance on experienced and expert inspection engineers to process condition monitoring data and devise a maintenance plan;
- Reduced interpretation time in devising and implementing maintenance actions reducing maintenance hours by 70%;
- Automatisation of safety or maintenance operations to the extent where maintenance operations do not require human intervention;
- Reduction of assets unscheduled downtime by 25%, cost by 35% and will improve performance and efficiency of asset;
- Operators will perform cost-effective maintenance based on the risk profile of faults detected.
Brunel Innovation Centre of Brunel University will bring to the DiMOS project its knowledge in both condition and structural health monitoring. It will process the big data generated by monitoring sensors by combining signal processing algorithms and machine learning models for real-time condition monitoring and health assessment of key subsystems and components of ships.