System Identification of a Moored ASV with Recessed Moon Pool via Deterministic and Bayesian Hankel-DMDc

TL;DR

This study addresses the identification of a moored small autonomous surface vehicle using Hankel-DMDc (HDMDc) and its Bayesian extension (BHDMDc) to build data-driven reduced-order models of vessel dynamics under nonlinear moon-pool sloshing. Experiments in a towing tank with irregular and regular head-sea waves demonstrate that HDMDc yields accurate deterministic predictions for surge, heave, and pitch, while BHDMDc adds uncertainty quantification by propagating hyperparameter variability. The work shows that ROMs trained on irregular, broadband waves can generalize to unseen regular wave conditions within the training spectral band, highlighting the importance of informative training data for robust generalization and the potential for digital-twin applications in marine systems. Despite challenges in predicting mooring loads due to measurement noise and slack moorings, the Bayesian approach consistently improves prediction accuracy and reduces dispersion, offering a practical path toward reliable real-time forecasting and decision support for moored ASVs and related systems.

Abstract

This study addresses the system identification of a small autonomous surface vehicle (ASV) under moored conditions using Hankel dynamic mode decomposition with control (HDMDc) and its Bayesian extension (BHDMDc). Experiments were carried out on a Codevintec CK-14e ASV in the towing tank of CNR-INM, under both irregular and regular head-sea wave conditions. The ASV under investigation features a recessed moon pool, which induces nonlinear responses due to sloshing, thereby increasing the modelling challenge. Data-driven reduced-order models were built from measurements of vessel motions and mooring loads. The HDMDc framework provided accurate deterministic predictions of vessel dynamics, while the Bayesian formulation enabled uncertainty-aware characterization of the model response by accounting for variability in hyperparameter selection. Validation against experimental data demonstrated that both HDMDc and BHDMDc can predict the vessel's response to unseen regular and irregular wave excitations. In conclusion, the study shows that HDMDc-based ROMs are a viable data-driven alternative for system identification, demonstrating for the first time their generalization capability for a sea condition different from the training set, achieving high accuracy in reproducing vessel dynamics.

Figures (11)

• Figure 1: Picture of the CK-14e ASV (\ref{['fig:ck14']}), the top cover was removed, showing the internal configuration and the location of the moon pool, visible from the lid and its fastening system. Towing tank test rig for CK-14e in moored conditions, the white panel used in tracking is visible on the model top cover (\ref{['fig:testfield']}).
• Figure 2: Comparison between nominal Pierson-Moskowitz and experimental power spectral density of wave elevation obtained from irregular wave test data. Vertical lines show the frequencies of regular waves tests.
• Figure 3: Sketch of the wave probes location (\ref{['fig:mooredsketch']}), and wave probes location from wave generator flap (\ref{['tab:waveprobes']}).
• Figure 4: ANRMSE (\ref{['fig:irr2irrANRMSE']}) and NAMMAE (\ref{['fig:irr2irrNAMMAE']}) box-violin plots. Comparison between deterministic and Bayesian predictions over the test sequences.
• Figure 5: Standardized time series prediction by deterministic and Bayesian Hankel-DMDc. Irregular test wave, selected sequence 1.