Data-Driven Approaches for Thrust Prediction in Underwater Flapping Fin Propulsion Systems
This work addresses the slow development of underwater vehicles by providing faster, accurate surrogate models for control systems, though it is incremental in applying existing ML methods to a specific domain.
The paper tackles the expensive testing of flapping-fin underwater propulsion systems by proposing machine learning approaches for thrust prediction based on fin geometries and kinematics, achieving data-efficient predictions for unseen fin shapes.
Flapping-fin underwater vehicle propulsion systems provide an alternative to propeller-driven systems in situations that require involve a constrained environment or require high maneuverability. Testing new configurations through experiments or high-fidelity simulations is an expensive process, slowing development of new systems. This is especially true when introducing new fin geometries. In this work, we propose machine learning approaches for thrust prediction given the system's fin geometries and kinematics. We introduce data-efficient fin shape parameterization strategies that enable our network to predict thrust profiles for unseen fin geometries given limited fin shapes in input data. In addition to faster development of systems, generalizable surrogate models offer fast, accurate predictions that could be used on an unmanned underwater vehicle control system.