The use of a set of artificial neural networks to predict added resistance in head waves at the parametric ship design stage

During the parametric ship design stage, added ship resistance, a component of total ship resistance is analysed to estimate the required propulsive power. The determination of added resistance at this design stage is problematic because the added resistance is calculated using hull shape, which is unknown at this stage. At the parametric design stage, only basic ship parameters, such as length, breadth, draught, block coefficient and Froude number are defined and known. Therefore, the focus of this research was to develop an effective tool to solve this problem. The article presents a set of five Artificial Neural Networks (ANNs) to predict added resistance using basic design parameters. Only model test data was used to train the ANNs in order to obtain reliable results. The research showed that using an ANN set consisting of five ANNs developed using different segregated data resulted in slightly more reliable and accurate estimates than using an individual ANN. To facilitate implementation, the developed ANNs were provided in the form of mathematical functions and open source software code from the Mendeley Data repository. A practical example of how an ANN set can be used to solve a design task was demonstrated in this article.

• Record URL:
  • https://doi.org/10.1016/j.oceaneng.2023.114744
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S0029801823011289
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00298018
• Supplemental Notes:
  • © 2023 The Author. Published by Elsevier Ltd. Abstract reprinted with permission of Elsevier.
• Authors:
  • Cepowski, Tomasz
  • 0000-0001-8038-075X
• Publication Date: 2023-8-1

Language

• English

Media Info

• Media Type: Web
• Features: Figures; References; Tables;
• Pagination: 114744
• Serial:
  • Ocean Engineering
  • Volume: 281
  • Issue Number: 0
  • Publisher: Pergamon
  • ISSN: 0029-8018
  • EISSN: 1873-5258
  • Serial URL: http://www.sciencedirect.com/science/journal/00298018

Subject/Index Terms

• TRT Terms: Design; Neural networks; Ships; Wave resistance
• Subject Areas: Design; Marine Transportation; Vehicles and Equipment;

Filing Info

• Accession Number: 01887646
• Record Type: Publication
• Files: TRIS
• Created Date: Jul 17 2023 3:13PM