Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2604.22969

Surrogate-Based Co-Design Coupling Analysis for Floating Offshore Wind Turbines

Elena Fernandez Bravo·Sunil Tamang·Yong Hoon Lee·James T. Allison
View original source ↗Read source document ↗Export metadata ↓

Abstract

This work presents a design coupling analysis (DCA) framework to investigate the interactions among control and plant design variables in floating offshore wind turbine (FOWT) and to support the formulation of tractable control co-design (CCD) optimization strategies. DCA provides quantitative information that reveals the relationships and dependencies among design variables and to objective function, enabling improved design variable selection, identification of dominant variables that drive system interactions, and informed selection of optimization solution strategies. However, applying DCA to complex systems is challenging because the models used to describe their dynamics are computationally expensive, and constructing DCA information requires exhaustive model evaluations and optimizations. Here, a surrogate model of the FOWT system is employed to make the repeated model evaluations required for DCA computationally feasible. Using this framework, the bidirectional couplings between control and plant design variables, as well as the couplings among plant design variables, are estimated. The results reveal strong interactions among various design variables, and identify the most influential plant design variables affecting system performance. These insights guide the development of two DCA-based optimization strategies for large CCD problems: a sequential decomposition approach that preserves dominant design variable couplings while reducing problem size at each stage, and a reduced dimensional optimization approach that focuses on collectively the most influential variables. The results demonstrate that these strategies significantly reduce computational complexity while achieving solutions comparable to those obtained through full simultaneous optimization, demonstrating the value of DCA for understanding and solving complex design problems.

Explore related subjects

cs.CEcs.SYeess.SYmath.OC

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Elena Fernandez Bravo, Sunil Tamang, Yong Hoon Lee, James T. Allison. 2026-04-24. Surrogate-Based Co-Design Coupling Analysis for Floating Offshore Wind Turbines. https://arxiv.org/abs/2604.22969

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Dimension Bridging for 3D RANS with Neural Network Accelerated Gaussian Functional Regression

In many computational science and engineering problems, repeatedly solving fully resolved physics-based models to design for a quantity of interest (QoI) can quickly become intractable, requiring the use of low-fidelity models to predict the same QoI but introduce errors where some features are neglected or are otherwise inaccurately resolved. We use Gaussian Functional Regression (GFR) to learn a correction to a 2D Reynolds-Averaged Navier-Stokes (RANS) model to predict the aerodynamic coefficients from a 3D RANS model. This model pair has a disparity in the governing physics from the reduced dimensionality, a previously unexplored application for GFR. Empirically, our results show that with a proper choice of low-dimensional (LD) model, the proposed kernel allows for the use of fewer high-dimensional (HD) evaluations to regress a response surface to the same level of accuracy as standard stationary kernels. Moreover, the new kernel provides more informative uncertainty quantification, which we show is advantageous when used to drive an adaptive sampling algorithm. Finally, we propose a novel neural network accelerated kernel, which we show offers predictions in good agreement while speeding up evaluations by millions of times in wall clock measurements, bringing the computational budget within the real-time regime.

cs.CE↗
arXiv2026

SabreAgent: Language Models at Design Time for Lost-Sales Inventory Control

SabreAgent uses a language model at design time to construct two components for lost-sales inventory control: a product-specific seasonal prior and a validation-selected capped base-stock policy family. During operation, statistical forecasting and inventory optimization use these frozen artifacts to determine orders, with zero language-model calls. We evaluate the approach on the $1{,}320$ instances of InventoryBench. Under the benchmark's cost assumptions, the operations-research core draws on a zero-lead-time optimality result and a projected-inventory rule for positive deterministic lead times. The latter computes replenishment shortfalls by propagating inventory using sales along simulated demand paths. The seasonal prior adds forecast variants alongside the original forecaster, and the selected policy family handles stochastic lead times with order destruction. SabreAgent scores $0.6311$, compared with $0.5380$ for the strongest published baseline, and ranks first in all six benchmark cells. Ablations attribute most of the gain to the OR core. In the paired analysis, the seasonal component adds $1.79\%$ across the three real-data cells, and the search component adds $2.3\%$ across the two stochastic-lead-time cells. These results demonstrate how model-generated priors and policy structure can improve an OR controller through design-time use.

cs.CE↗
arXiv2026

Hierarchical Multi-Task Learning with Liquidity-Aware Signals for Stock Forecasting

Stock price forecasting is a long-standing challenge in computational finance, driven by the inherent randomness of markets and complex temporal patterns. While recent deep-learning models have raised forecasting accuracy by jointly modeling inter-stock and temporal price dynamics, they conflate inter-stock relationships with intra-stock temporal dependencies and focus solely on the univariate objective of price movement. To address these limitations, we propose LiMT, a Hierarchical Multi-Task Learning framework that integrates liquidity-aware signals for stock price forecasting. LiMT employs a Market Regime Encoder (MRE) module that first extracts contemporaneous cross-stock dependencies, then models each stock's temporal dynamics, yielding a unified latent state. Building on this latent state, we introduce a Liquidity-Driven Learning (LDL) module, a mixture-of-experts architecture that features cross-task gating mechanisms to jointly predict price movement, volatility, and trading volume. We further design an Adaptive Portfolio Optimization (APO) mechanism that converts multi-task forecasts into executable portfolio weights under transaction-cost and liquidity constraints. Extensive experiments on the CSI300 and CSI500 benchmarks show that LiMT performs best among strong neural and tree-based baselines across the reported metrics. In realistic CSI300 backtests, APO improves annualized return from 3.99% to 10.01% and Sharpe ratio from 1.22 to 1.86 over equal weighting, showing that the multi-task forecasts translate into deployable portfolio gains.

cs.CE↗