A Machine Learning Enabled MDO for Bio-Inspired Autonomous Underwater Gliders
Andrea Serani, Giorgio Palma, Jeroen Wackers, Matteo Diez
TL;DR
This work tackles the challenging, highly coupled design problem of bio‑inspired autonomous underwater gliders by introducing a ML‑enabled bi‑level MDO framework (BLISS) that couples external manta‑ray shaped geometry optimization with internal pressure hull sizing. It combines physics‑driven dimensionality reduction (PD‑PME) to obtain a low‑dimensional latent space, multi‑fidelity stochastic radial basis surrogates with uncertainty quantification, and batch Bayesian optimization to efficiently explore the design space. The methodology yields a Pareto front with significant gains: a 14.7% increase in maximum hydrodynamic efficiency and a 12.8% reduction in empty hull weight relative to a baseline manta‑inspired design, while satisfying all disciplinary constraints; the results are supported by cross‑validation with high‑fidelity solvers and flow‑physics interpretation. The approach demonstrates that integrating physics‑aware dimensionality reduction with multi‑fidelity surrogate modeling and uncertainty‑aware optimization can enable scalable, physically consistent MDO for complex, high‑dimensional, multi‑disciplinary engineering problems, with potential applicability to other marine and aerospace designs.
Abstract
The preliminary design of AUGs is intrinsically challenging due to the strong coupling between the external hydrodynamic shape, the hydrostatic balance, the structural integrity, and internal packaging constraints. This complexity is further amplified for bio-inspired configurations, whose rich geometric parametrizations lead to high-dimensional design spaces that are difficult to explore using conventional optimization approaches. This work presents a ML-enabled bi-level multidisciplinary design optimization (MDO) framework for the performance-driven design of a manta-ray-inspired AUG. At the upper level, hydrodynamically efficient external geometries are explored in a reduced design space obtained through physics-driven parametric model embedding, which identifies a low-dimensional latent representation directly correlated with the lift, drag, and pressure distributions. At the lower level, a constrained internal sizing problem determines the minimum feasible empty weight by accounting for structural, hydrostatic, geometric, and payload constraints. To render the resulting bi-level problem computationally tractable, a multi-fidelity surrogate-based optimization strategy is adopted, combining low- and high-fidelity hydrodynamic models with stochastic radial basis function surrogates and adaptive Bayesian sampling. The framework enables efficient exploration of the coupled design space while rigorously managing model uncertainty and computational cost. The optimized configurations exhibit a 14.7\% improvement in maximum hydrodynamic efficiency and a 12.8\% reduction in empty weight relative to the baseline design, while satisfying all disciplinary constraints. These results demonstrate that the integration of physics-driven dimensionality reduction and multi-fidelity machine learning enables scalable and physically consistent MDO of complex bio-inspired underwater vehicles.