A linear regression model for marine propeller optimization, prototyping and design

  1. (PDF, 447 KB)
AuthorSearch for: ; Search for: ; Search for: ; Search for:
Conference11th International Symposium on Transport Phenomena and Dynamics of Rotating Machinery, 26 February - 2 March 2006, Honolulu, Hawaii
Subjectlinear regression; optimal prototyping; design; model propeller
AbstractA multiple-variable linear regression direct solution model and a statistical model were developed for marine propeller design, optimization and prototype. Computing implementation for the direct solution model was made to create an integrated tool for the marine propeller development process. An error analysis for a simple case with only 4 independent variables was performed. This direct solution model was constructed to provide two functionalities: generation of a set of linear regression coefficients to establish a multiple-variable polynomial equation and interpolation of the multiple-variable data set that are generated by the polynomial equations. An application case was given using a set of data from a marine nozzle propeller series both to cover interpolation to produce curves and linear regression coefficients for interpolation, for both the direct solution model and the statistical model that was computed under a commercial software package. Though much higher than the statistical model, interpolation by the direct solution model showed an error of less than one-tenth of a percent for a group of nozzle propellers. The highly computing-efficient direct solution method showed its capability as a general-purpose linear regression tool which can be applied widely for optimal product prototyping and design.
Publication date
AffiliationNRC Institute for Ocean Technology; National Research Council Canada
Peer reviewedNo
NRC number6285
NPARC number8894986
Export citationExport as RIS
Report a correctionReport a correction
Record identifier8c85d1b4-37bd-4958-a8fb-646dac95da83
Record created2009-04-22
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)
Date modified: