This paper is an investigation into a quantitative selection process of either a mechanical or electrical system architecture for the transmission of propulsion power in naval combatant vessels. A database of historical naval ship characteristics was statistically analyzed to determine if there were any predominant ship parameters that could be used to predict whether a ship should be designed with a mechanical power transmission system or an electric one. A Principal Component Analysis was performed to determine the minimum number of dimensions required to define the relationship between the propulsion transmission architecture and the independent variables. Combining the results of the statistical analysis and the PCA, neural networks were trained and tested to separately predict the transmission architecture or the installed electrical generation capacity of a given class of naval combatant.
Identifer | oai:union.ndltd.org:uno.edu/oai:scholarworks.uno.edu:td-3098 |
Date | 15 May 2015 |
Creators | Waller, Brian S |
Publisher | ScholarWorks@UNO |
Source Sets | University of New Orleans |
Detected Language | English |
Type | text |
Format | application/pdf |
Source | University of New Orleans Theses and Dissertations |
Page generated in 0.0021 seconds