Steel weight estimation of new ships using principal component analysis

C. K. Lin, Heiu-Jou Shaw

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

This paper presents an agile model to estimate the weight of steel in the initial design stage of a ship. A container ship database was obtained from the database of fee three-dimensional computer-aided design systems of the CSBC Corporation. Principal Component Analysis was applied to define the principal parameters, i.e., the principal dimension and the parameters of the ship's segments. Then, two methods were developed for estimating a new ship. The first method uses the principal dimension to estimate the weight of fee steel in fee entire ship. The second method is based on fee division of a ship into several structural segments and uses fee parameters of fee individual segments to estimate each segment The parameters of fee individual segments are referenced from a similar vessel selected using the principal dimensioa Then, the parameters of the individual segments are obtained from a rough arrangement negotiated with the ship owner to adjust the estimated weight A linear regression is used to investigate the relationships between the parameters and the estimated weight for both methods and then the estimation system is built. By comparing the variability in the estimations, the segment estimation provides a more accurate steel weight and also provides a new way of efficiently obtaining the weight distribution necessary to support the related preliminary design, i.e., the center of gravity, the design of the ship lines and an evaluation of ship performance.

Original languageEnglish
Pages (from-to)175-182
Number of pages8
JournalJournal of Taiwan Society of Naval Architects and Marine Engineers
Volume33
Issue number4
Publication statusPublished - 2014 Nov 1

All Science Journal Classification (ASJC) codes

  • Ocean Engineering
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Steel weight estimation of new ships using principal component analysis'. Together they form a unique fingerprint.

Cite this