Maintaining machinery health and repair data is essential for efficient maintenance planning
and implementation. Identifying critical components and failure causes requires detailed
system reliability and diagnostics analysis. Multi-equipment holdings and long voyages across
multiple climates make this challenge especially difficult for ship operators. For naval ships,
the challenging environment and mission profile forced machinery to operate outside its
operational envelope. Thus, this research seeks to develop a critical component analysis
maintenance framework for system reliability and fault identification analysis to aid
maintenance decision-making. Using reliability analysis and machine learning, critical
components and faults were identified. A unique contribution of this study is the integration of
fault detection analysis and reliability tools. DFT and FMECA are used to identify missioncritical components, while BBN is used for availability assessment and maintenance decision
support system. This includes classification and fault detection using ANN-based machine
learning models. An offshore patrol vessel power generation system with four marine diesel
generators was studied. The reliability analysis shows system reliability below 70% in the first
24 of 78 operational months. Over 40% of subsystem failure and related events were isolated
using reliability importance measures and minimal cuts sets. Identifying mission-critical
components using Risk Priority Number in FMECA analysis enabled robust reliability and
critical component analysis. Among the 4 MDGs, the lubricating system had the highest
average availability of 67% and the cooling system the lowest at 38% using the DFTA minimal
cut set. DSS-based 4 maintenance strategies used BBN availability and FMECA mission
critical components. Because some critical parts fail frequently, Corrective Action and
ConMon were recommended maintenance strategies. ANN found overheating when MDG
output was above 180kva, linking component failure to generator performance. The findings
improve ship system reliability and availability by reducing failures and improving
maintenance strategies.
| Date of Award | 24 Apr 2024 |
|---|
| Original language | English |
|---|
| Awarding Institution | - University Of Strathclyde
|
|---|
| Sponsors | University of Strathclyde |
|---|
| Supervisor | Iraklis Lazakis (Supervisor) & Osman Turan (Supervisor) |
|---|