Abstract

Recently, there is a growing interest in reducing fuel consumption due to the strengthening of regulations on pollutant emission. Reducing fuel consumption is not only a solution to the marine environmental pollution problem, but also economical operation costs can be established through fuel saving. However, it is difficult to calculate the fuel consumption according to the actual environment in that the fuel consumption may change depending on the weather conditions. Therefore, in this study, using an artificial neural network, the fuel consumption according to the weather environment was predicted and the optimal route was determined through a genetic algorithm. The artificial neural network model uses ship information and weather information between each location as input variables, and about 42,000 ship AIS data sets are used to learn the model. To verify the research results, the results of the optimal route through the genetic algorithm were compared with the results of the A<SUP>*</SUP> algorithm, As a result, it was confirmed that the fuel consumption prediction function of the artificial neural network and the optimization function of the GA algorithm were confirmed to be a useful method for determining the optimal path.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call