.png){kind=icon}
.png){kind=icon}
Return
Discovering ship maneuvering models from data
.png){kind=icon}
OA
AI
DOI：10.1007/s00773-024-01045-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we introduce a methodology to discover ship maneuvering models from data, leveraging Wide-Array of Nonlinear Dynamics Approximation (WyNDA) framework. WyNDA operates by utilizing basis functions and estimation algorithms to discern the ship maneuvering behaviors. Specifically, we employ a discrete-time exponential forgetting factor observer to accurately estimate both the structures and parameters inherent in the maneuvering models. Through extensive numerical simulations, we demonstrate the efficacy of our proposed approach in solving system identification and data-driven discovery problems within this domain. Moreover, we assess the robustness of our method with respect to noise levels and system excitation. This research contributes to advancing data-driven discovery of ship maneuvering dynamics and provides a practical tool for applications requiring accurate modeling.
Keywords:
Ship dynamics
Maneuvering models
Data-driven discovery
Journal
IF:
2
Papers:
121
Citations:
2.7K