Application of Different Learning Algorithms for the Prediction of Power of Inland Pushboats

This paper analyzes different learning algorithms for the assessment of ship powering performance. Ship speed through water data have been used as an input in artificial neural networks and propulsion shaft torque data have been used as an output. Five different learning algorithms have been applied in order to get the relationship between the pushboat power and convoy speed. Data are acquired over several years on many different pushed convoys. It was shown that trained neural networks can be used for the prediction of ship power and at the same time, plenty of room was left in the length of training neural networks.

Language

  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; References; Tables;
  • Pagination: pp 29-39
  • Monograph Title: Proceedings of First International Conference on Traffic and Transport Engineering (ICTTE)

Subject/Index Terms

Filing Info

  • Accession Number: 01594703
  • Record Type: Publication
  • ISBN: 9788691615307
  • Files: TRIS
  • Created Date: Mar 25 2016 8:24PM