Abstract
The complexity and changefulness of inland navigation environment in space and time makes it hard to guarantee the applicability and accuracy of existing ship speed models. In this paper, a novel method for inland ship speed modelling under complex and changeful navigation environment is proposed. Firstly, an unsupervised machine learning algorithm, Density-Based Spatial Clustering of Application with Noise (DBSCAN), is utilized to cluster the environmental data including water level, water speed, wind speed and wind direction, to get the segment division information, which greatly helps reduce the influence of other uncertain environmental factors on the speed model. Then, Generalized Regression Neural Network (GRNN) is tailored and employed to build the ship speed estimation model with multiple input variables. Finally, a detailed case study of a ship sailing in the Yangtze River trunk line is conducted to validate the proposed methods. The results show that the ship speed model established based on machine learning methods works effectively in speed estimation and analysis. Moreover, compared with other regression methods and neural networks, the proposed GRNN model has the best performance in ship speed modelling.
Highlights
Waterborne transportation, as a green and economical transportation mode, plays an essential role in worldwide trade
The Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU), which are good at dealing with time series, have not exerted their advantages here, and their results are even inferior to Back Propagation neural network (BPNN). These results show that the proposed Generalized Regression Neural Network (GRNN) approach outperforms others in the ship speed modelling
The unsupervised learning algorithm Density-Based Spatial Clustering of Application with Noise (DBSCAN) was used for clustering analysis of navigation environment data to obtain the segment division information of the entire voyage
Summary
Waterborne transportation, as a green and economical transportation mode, plays an essential role in worldwide trade. Z. Yuan et al.: Practical Estimation Method of Inland Ship Speed Under Complex and Changeful Navigation Environment et al [9] applied the fundamentals to develop two regression models for container ship fuel efficiency. Yuan et al.: Practical Estimation Method of Inland Ship Speed Under Complex and Changeful Navigation Environment et al [9] applied the fundamentals to develop two regression models for container ship fuel efficiency It was conducted based on the limited information conveyed by shipping logs. These data include real-time status data and environmental data, which were collected from the multi-source sensors installed on the ship and hydrometeorological stations.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
