Journal of Marine Science and Technology

, Volume 17, Issue 1, pp 30–39 | Cite as

Statistical modelling for ship propulsion efficiency

  • Jóan Petur PetersenEmail author
  • Daniel J. Jacobsen
  • Ole Winther
Original Article


This paper presents a state-of-the-art systems approach to statistical modelling of fuel efficiency in ship propulsion, and also a novel and publicly available data set of high quality sensory data. Two statistical model approaches are investigated and compared: artificial neural networks and Gaussian processes (GP). The data presented is a publicly available full-scale data set, with a whole range of features sampled over a period of 2 months. We further discuss interpretations of the operational data in relation to the underlying physical system.


Vessel efficiency Artificial neural networks Gaussian processes Energy conservation Advisory systems Computer simulation 


  1. 1.
    ADOPT—Advanced decision support system for ship design, operation, and training.
  2. 2.
    (2008) The maritime engineering reference handbook. Butterworth-Heinemann, OxfordGoogle Scholar
  3. 3.
    Atwater R (1990) Shipboard wave height sensor. Technical report, Ship Structure CommitteeGoogle Scholar
  4. 4.
    Bishop CM (2006) Pattern recognition and machine learning (information science and statistics), 1st edn. Springer, Berlin (corr. 2nd printing edn. Springer, Berlin (2007))Google Scholar
  5. 5.
    Blendermann W (1996) Wind loading of ships collected data from wind tunnel tests in uniform flow. Technical report, Institut fur Schiffbau der Universitat HamburgGoogle Scholar
  6. 6.
    Briggs MJ (2006) Ship squat predictions for ship/tow simulator. Technical report, US Army Corps of EngineersGoogle Scholar
  7. 7.
    Ghahramani Z, Hinton GE (1996) Parameter estimation for linear dynamical systems. Technical reportGoogle Scholar
  8. 8.
    Hansen H, Freund M (2010) Assistance tools for operational fuel efficiency. In: 9th conference computer and IT applications in the maritime industries (COMPIT), pp 356–366Google Scholar
  9. 9.
    Holtrop J (1984) A statistical re-analysis of resistance and propulsion data. Int Shipbuild Prog 31:272–276Google Scholar
  10. 10.
    Holtrop J, Mennen GGJ (1982) An approximate power prediction method. Int Shipbuild Prog 29:166–170Google Scholar
  11. 11.
    Journée J (2003) Review of the 1985 full-scale calm water performance tests onboard m.v. mighty servant 3. Technical report DUT-SHL report 1361, Delft University of Technology, Ship Hydromechanics LaboratoryGoogle Scholar
  12. 12.
    Journée J, Rijke R, Verleg G (1987) Marine performance surveillance with a personal computer. Technical report report 753-P, Delft University of Technology, Ship Hydromechanics Laboratory, Delft, The NetherlandsGoogle Scholar
  13. 13.
    Leifsson LT, Sævarsdóttir H, Sigurdsson ST, Vésteinsson A (2008) Grey-box modeling of an ocean vessel for operational optimization. Simul Model Pract Theory 16(8):923–932CrossRefGoogle Scholar
  14. 14.
    Noblesse F, Hendrix D, Faul L, Slutsky J (2006) Simple analytical expressions for the height, location, and steepness of a ship bow wave. J Ship Res 50(4):360–370Google Scholar
  15. 15.
    Pedersen BP, Larsen J (2009) Prediction of full-scale propulsion power using artificial neural networks. In: Proceedings of the 8th international conference on computer and IT applications in the maritime industries (COMPIT’09), Budapest, Hungary May 10–12, pp 537–550.
  16. 16.
    Rasmussen CE, Williams C (2006) Gaussian processes for machine learning. MIT Press, Cambridge.
  17. 17.
    Ruggiero V, Filardi V, Cucinotta F (2007) Mesh size influence in a CFD code on resistance evaluation of a motor yacht. In: COMPIT07—computer and IT applications in the maritime industries, pp 458–466Google Scholar
  18. 18.
    Townsin R (2003) The ship hull fouling penalty. Biofouling 19:9–15CrossRefGoogle Scholar

Copyright information

© JASNAOE 2011

Authors and Affiliations

  • Jóan Petur Petersen
    • 1
    • 2
    Email author
  • Daniel J. Jacobsen
    • 1
  • Ole Winther
    • 2
  1. 1.Decision3 Lucas Debesargota 3TórshavnFaroe Islands
  2. 2.Informatics and Mathematical ModellingTechnical University of Denmark (DTU) B321LyngbyDenmark

Personalised recommendations