Adverse conditions within specific offshore environments magnify the challenges faced by a vessel’s energy-efficiency optimization in the Industry 4.0 era. As the data rate and volume increase, the analysis of big data using analytical techniques might not be efficient, or might even be infeasible in some cases. The purpose of this study is the development of deep-learning models that can be utilized to predict the propulsion power of a vessel. Two models are discriminated: (1) a feed-forward neural network (FFNN) and (2) a recurrent neural network (RNN). Predictions provided by these models were compared with values measured onboard. Comparisons between the two types of networks were also performed. Emphasis was placed on the different data pre-processing phases, as well as on the optimal configuration decision process for each of the developed deep-learning models. Factors and parameters that played a significant role in the outcome, such as the number of layers in the neural network, were also evaluated.

A weather routing tool is presented based on forecasted weather data along the route and considering safety aspects. The tool aims to determine the optimal path for the minimisation of the fuel oil consumption, ensuring a safe passage. It is developed in MATLAB and considers detailed ship characteristics. Specifically, ship's motions and fuel oil consumption of the main engine during a potential path are estimated. For the latter, a physics-based model for a specific vessel is developed where tools of different level of detail are utilised to calculate the various resistance components. A speed management strategy along the route is specified as well as safety criteria representing acceptable limits of ship's responses. When the set criteria and constraints have been set, a genetic algorithm is used to find the optimal route by means of ship's heading or by considering both heading and ship's power settings as variables to minimise the fuel oil consumption. The search space of the algorithm lies within a predefined envelop, but still the evolutionary optimisation approach used has no pre-assigned values to any possible candidate waypoint.