On Neural Network Identification for Low-Speed Ship Maneuvering Model

TL;DR

This paper introduces a neural network-based system identification method for low-speed ship maneuvering models, focusing on berthing, using free running tests and a novel loss function to improve accuracy amidst noise.

Contribution

It proposes a new RNN-based identification approach with a specialized loss function and demonstrates its effectiveness for low-speed ship maneuvering modeling.

Findings

RNN ignoring past memory improves prediction accuracy.

Random maneuver tests enhance model accuracy.

Neural network models accurately represent low-speed maneuvers.

Abstract

Several studies on ship maneuvering models have been conducted using captive model tests or computational fluid dynamics (CFD) and physical models, such as the maneuvering modeling group (MMG) model. A new system identification method for generating a low-speed maneuvering model using recurrent neural networks (RNNs) and free running model tests is proposed in this study. We especially focus on a low-speed maneuver such as the final phase in berthing to achieve automatic berthing control. Accurate dynamic modeling with minimum modeling error is highly desired to establish a model-based control system. We propose a new loss function that reduces the effect of the noise included in the training data. Besides, we revealed the following facts - an RNN that ignores the memory before a certain time improved the prediction accuracy compared with the "standard" RNN, and the random maneuver test was effective in obtaining an accurate berthing maneuver model. In addition, several low-speed free running model tests were performed for the scale model of the M.V. Esso Osaka. As a result, this paper showed that the proposed method using a neural network model could accurately represent low-speed maneuvering motions.