This paper presents the construction of a neural network-based model to predict fuel consumption and sailing time using a feedforward neural network trained by the backpropagation method. Instead of using in-service data collected from real ships like most previous studies, it often does not have all the necessary data and takes a long time to get a large enough dataset. We use a hardware-in-the-loop (HIL) simulator to create a dataset with many scenarios covering the most common ship operations at sea. Experimental results show that the proposed model gives high-accuracy results, which can be applied to find optimal routes and minimum main engine speeds for cargo ships before each voyage in the future.
A Neural Network-Based Model to Predict Fuel Consumption and Sailing Time for Cargo Ships
2023-09-10
1358432 byte
Conference paper
Electronic Resource
English
Engineering Index Backfile | 1920
|Engineering Index Backfile | 1958
|SLUB | 1988
|Engineering Index Backfile | 1924
|Taylor & Francis Verlag | 1943
|