Full scale measurements of the propulsion power, ship speed, wind speed and direction, sea and air temperature, from four different loading conditions has been used to train a neural network for prediction of propulsion power. The network was able to predict the propulsion power with accuracy between 0.8-2.8%, which is about the same accuracy as for the measurements. The methods developed are intended to support the performance monitoring system SeaTrend® developed by FORCE Technology (FORCE (2008)).
|Title of host publication||World Maritime Technology Conference|
|Publication status||Published - 2009|
|Event||Modeling of Ship Propulsion Performance - |
Duration: 1 Jan 2009 → …
|Conference||Modeling of Ship Propulsion Performance|
|Period||01/01/2009 → …|
- Neural network