Thesis
A comprehensive approach to ship system maintenance modelling and decision support using machine learning and reliability analysis
- Creator
- Rights statement
- Awarding institution
- University of Strathclyde
- Date of award
- 2024
- Thesis identifier
- T16907
- Person Identifier (Local)
- 201859833
- Qualification Level
- Qualification Name
- Department, School or Faculty
- Abstract
- 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.
- Advisor / supervisor
- Lazakis, Iraklis
- Resource Type
- DOI
- Funder
关系
项目
缩略图 | 标题 | 上传日期 | 公开度 | 行动 |
---|---|---|---|---|
|
PDF of thesis T16907 | 2024-08-27 | 公开 | 下载 |