Data Augmentation Methods of Dynamic Model Identification for Harbor Maneuvers using Feedforward Neural Network

TL;DR

This paper explores data augmentation techniques, specifically slicing and jittering, to improve neural network-based dynamic models for harbor maneuvers, demonstrating their effectiveness in numerical experiments with limitations in extrapolation scenarios.

Contribution

Introduces and evaluates data augmentation methods for neural network models in harbor maneuver modeling, enhancing generalization performance in system identification tasks.

Findings

Slicing and jittering improve model generalization on training data.

Data augmentation methods are effective but limited for extrapolation states.

Numerical experiments confirm the usefulness of augmentation techniques.

Abstract

A dynamic model for an automatic berthing and unberthing controller has to estimate harbor maneuvers, which include berthing, unberthing, approach maneuvers to berths, and entering and leaving the port. When the dynamic model is estimated by the system identification, a large number of tests or trials are required to measure the various motions of harbor maneuvers. However, the amount of data that can be obtained is limited due to the high costs and time-consuming nature of full-scale ship trials. In this paper, we improve the generalization performance of the dynamic model for the automatic berthing and unberthing controller by introducing data augmentation. This study used slicing and jittering as data augmentation methods and confirmed their effectiveness by numerical experiments using the free-running model tests. The dynamic model is represented by a neural network-based model in numerical experiments. Results of numerical experiments demonstrated that slicing and jittering are effective data augmentation methods but could not improve generalization performance for extrapolation states of the original dataset.