Neural Network Approach for Predicting Ship Speed and Fuel Consumption

Abstract

In this paper, simulations of a ship travelling on a given oceanic route were performed by a weather routing system to provide a large realistic navigation data set, which could represent a collection of data obtained on board a ship in operation. This data set was employed to train a neural network computing system in order to predict ship speed and fuel consumption. The model was trained using the Levenberg–Marquardt backpropagation scheme to establish the relation between the ship speed and the respective propulsion configuration for the existing sea conditions, i.e., the output torque of the main engine, the revolutions per minute of the propulsion shaft, the significant wave height, and the peak period of the waves, together with the relative angle of wave encounter. Additional results were obtained by also using the model to train the relationship between the same inputs used to determine the speed of the ship and the fuel consumption. A sensitivity analysis was performed to analyze the artificial neural network capability to forecast the ship speed and fuel oil consumption without information on the status of the engine (the revolutions per minute and torque) using as inputs only the information of the sea state. The results obtained with the neural network model show very good accuracy both in the prediction of the speed of the vessel and the fuel consumption.

Influence of Marine Fuel Properties on Ignition, Injection Delay and Energy Efficiency

“…This is comparable to some of other methods, used for reduction of fuel consumption for ships, such as changes in hull and propulsion plant design, additional waste heat recovery, change of fuel type and energy management (Lassesson, Andersson 2009;Yan et al 2020). Fuel consumption prediction and optimisation models usually involve evaluation of multiple parameters including hull resistance, weather influence, currents, engine load and many others and by selecting optimal speed, course and load can reach up to 2…7% in fuel consumption reduction (Panapakidis et al 2020;Yan et al 2020;Kim et al 2021;Moreira et al 2021). But in very few it is noted, that fuel quality parameters also influence efficiency and that the effect can be different for each engine model, as it was also shown in this study (Lundh et al 2016;Panapakidis et al 2020).…”

Weather Routing System Architecture Using Onboard Data Collection and Route Optimisation

“…In future, this approach should be replaced by a fully automatic ship model update, utilising Artificial Neural Networks (ANN). The first attempts towards this goal have already been documented in [30] and [31].…”

A Comprehensive Approach to Account for Weather Uncertainties in Ship Route Optimization

“…A tool to obtain the ship speed V S and the fuel consumption per nautical mile FC nmi , given a set of deterministic variables X and a set of uncertain variables X, is here assumed to be available and considered as a black-box (e.g., [27]). Thus, for each track k in which the route is divided, one can always obtain the time d k and the fuel FC k required to sail the track:…”