Full-order Model Research Articles

A real-time solution method for three-dimensional steady temperature field of transformer windings based on mechanism-embedded cascade network

To enhance the computation efficiency and accuracy of three-dimensional steady temperature field of transformer windings, we propose a new non-invasive Reduced Order Model (ROM) based on a mechanism-embedded cascade network. Initially, a snapshot matrix is formed from the Full Order Model (FOM) and then combined with Proper Orthogonal Decomposition (POD) to extract key modal features that characterize the temperature field. Subsequently, a cascade network architecture, integrating Multilayer Perceptron (MLP) and Radial Basis Function Neural Network (RBFNN), is devised to swiftly map working condition parameters to modal coefficients. Additionally, the cascade network is embedded with condition sensitivity and modal contribution mechanisms to further enhance prediction accuracy. Finally, by linearly weighting the modes with predicted modal coefficients, a rapid reconstruction of the steady temperature field in transformer windings is achieved. Validation against Fluent software simulations and experimental measurements demonstrate a close agreement, with computational errors of less than 4K and an impressive single solution time of only 0.0087 s, which is 48760 times faster compared to Fluent software.

Reduced-order modeling of conjugate heat transfer in lithium-ion batteries

Reduced-order modeling (ROM) techniques involving physics are gaining importance due to their ability to generate physically meaningful results swiftly and accurately. They are finding applications in design and optimization and in digital twins where real-time results are required. The proper orthogonal decomposition (POD)-Galerkin ROM based on finite volume discretization methodology is utilized here for solving a high-dimensional system in a reduced dimensional space in which the reduced basis is spanned by the POD modes. The reduced-order equations are obtained by projecting the discretized form of the full-order model (FOM) equations onto the reduced basis which eliminates the need for boundary control techniques. The proposed methodology is demonstrated for transient conjugate heat transfer (CHT) in an electric vehicle battery. The POD modes are computed using simulation data for three Reynolds numbers and the ROM is evaluated for transient analysis of temperature from initial state to steady state for seven Reynolds numbers. The ROM predictions are fairly accurate both in the interpolated and the extrapolated regions with significant computational speed-up. Five modes are sufficient for constructing the fluid and battery temperature ROM solution. The ROM computational speed-up obtained with 5 modes is approximately 4–7.4 times compared to the FOM. The proposed methodology is generic and can be readily applied for any engineering system involving CHT.

Analysis of Mesh Resolution Effect to Numerical Result of CFD-ROM: Turbulent Flow in Stationary Parallel Plate

Computational fluid dynamics (CFD) is extensively utilized to predict flow behaviour in various industries and applications. The Full Order Model (FOM) is a high-accuracy approach to flow modelling, but it requires significant computational resources due to its high order and thousands of variables. To address this problem, the Reduced Order Model (ROM) was developed. Despite the advancement brought by ROM, there is a notable gap in research concerning the impact of mesh configuration on CFD-ROM results. While the number of modes has been extensively studied for its influence on CFD-ROM, the mesh configuration, a critical aspect of the simulation process, has received relatively limited attention. This study investigates the effect of mesh resolution on numerical results in CFD-ROM concerning turbulent flow within stationary parallel plates. Employing rigorous methods, including Richardson Extrapolation, verification, validation, and error percentage. The results explicitly confirm that mesh resolution directly impacts the numerical results of the velocity field in CFD-ROM. It is found that there is a notable reduction in Convergence Grid Index (CGI) values for different mesh ratios: 6.401% for medium-to-coarse and 2.031% for fine-to-medium ratio. Thus, with the same mode number, mesh resolution selection can enhance the numerical result of the velocity field in CFD-ROM.

PGD in thermal transient problems with a moving heat source: A sensitivity study on factors affecting accuracy and efficiency

AbstractThermal transient problems, essential for modeling applications like welding and additive metal manufacturing, are characterized by a dynamic evolution of temperature. Accurately simulating these phenomena is often computationally expensive, thus limiting their applications, for example for model parameter estimation or online process control. Model order reduction, a solution to preserve the accuracy while reducing the computation time, is explored. This article addresses challenges in developing reduced order models using the proper generalized decomposition (PGD) for transient thermal problems with a specific treatment of the moving heat source within the reduced model. Factors affecting accuracy, convergence, and computational cost, such as discretization methods (finite element and finite difference), a dimensionless formulation, the size of the heat source, and the inclusion of material parameters as additional PGD variables are examined across progressively complex examples. The results demonstrate the influence of these factors on the PGD model's performance and emphasize the importance of their consideration when implementing such models. For thermal example, it is demonstrated that a PGD model with a finite difference discretization in time, a dimensionless representation, a mapping for a moving heat source, and a spatial domain non‐separation yields the best approximation to the full order model.

A fast and accurate domain decomposition nonlinear manifold reduced order model

This paper integrates nonlinear-manifold reduced order models (NM-ROMs) with domain decomposition (DD). NM-ROMs approximate the full order model (FOM) state in a nonlinear-manifold by training a shallow, sparse autoencoder using FOM snapshot data. These NM-ROMs can be advantageous over linear-subspace ROMs (LS-ROMs) for problems with slowly decaying Kolmogorov n-width. However, the number of NM-ROM parameters that need to be trained scales with the size of the FOM. Moreover, for “extreme-scale” problems, the storage of high-dimensional FOM snapshots alone can make ROM training expensive. To alleviate the training cost, this paper applies DD to the FOM, computes NM-ROMs on each subdomain, and couples them to obtain a global NM-ROM. This approach has several advantages: Subdomain NM-ROMs can be trained in parallel, involve fewer parameters to be trained than global NM-ROMs, require smaller subdomain FOM dimensional training data, and can be tailored to subdomain-specific features of the FOM. The shallow, sparse architecture of the autoencoder used in each subdomain NM-ROM allows application of hyper-reduction (HR), reducing the complexity caused by nonlinearity and yielding computational speedup of the NM-ROM. This paper provides the first application of NM-ROM (with HR) to a DD problem. In particular, this paper details an algebraic DD reformulation of the FOM, training a NM-ROM with HR for each subdomain, and a sequential quadratic programming (SQP) solver to evaluate the coupled global NM-ROM. Theoretical convergence results for the SQP method and a priori and a posteriori error estimates for the DD NM-ROM with HR are provided. The proposed DD NM-ROM with HR approach is numerically compared to a DD LS-ROM with HR on the 2D steady-state Burgers’ equation, showing an order of magnitude improvement in accuracy of the proposed DD NM-ROM over the DD LS-ROM.

Model order reduction based on low-rank approximation for parameterized eigenvalue problems in structural dynamics

This study introduces a novel reduced-order modeling approach for parameterized eigenvalue problems. The proposed framework represents eigenvectors as a low-rank approximation and is implemented using an offline-online strategy. In the offline stage, nonlinear equations are formulated by imposing a stationary condition on the weighted Rayleigh quotient over sampled points and eigenvalues of interest. A variant of the Krylov subspace approach is applied to progressively identify the dominant response characteristics at sampled points. In the online stage, a reduced-order model is obtained through Galerkin projection, and eigensolutions at unsampled points are determined. The performance of the proposed framework is validated through numerical examples, where perturbation, least-angle regression, and Gaussian process are considered for comparison. The obtained results demonstrate that the proposed framework can accurately estimate eigensolutions, even when eigenvalues are adjacent to each other. In terms of efficiency, the a priori construction of the low-dimensional basis is possible without solving the full-order model, resulting in substantial CPU time savings during the offline computation process. Lastly, the applicability of the proposed framework is investigated through an uncertainty quantification example using numerical and experimental results.

Proper generalized decomposition-based iterative enrichment process combined with shooting method for steady-state forced response analysis of nonlinear dynamical systems

This paper presents a novel framework combining proper generalized decomposition (PGD) with the shooting method to determine the steady-state response of nonlinear dynamical systems upon a general periodic input. The proposed PGD approximates the response as a low-rank separated representation of the spatial and temporal dimensions. The Galerkin projection is employed to formulate the subproblem for each dimension, then the fixed-point iteration is applied. The subproblem for the spatial vector can be regarded as computing a set of reduced-order basis vectors, and the shooting problem projected onto the subspace spanned by these basis vectors is defined to obtain the temporal coefficients. From this procedure, the proposed framework replaces the complex nonlinear time integration of the full-order model with the series of solving simple iterative subproblems. The proposed framework is validated through two descriptive numerical examples considering the conventional linear normal mode method for comparison. The results show that the proposed shooting method based on PGD can accurately capture nonlinear characteristics within 10 modes, whereas linear modes cannot easily approximate these behaviors. In terms of computational efficiency, the proposed method enables CPU time savings of about one order of magnitude compared with the conventional shooting methods.

Fluid-reduced-solid interaction (FrSI): Physics- and projection-based model reduction for cardiovascular applications

Fluid-solid interaction (FSI) phenomena play an important role in many biomedical engineering applications. While FSI techniques and models have enabled detailed computational simulations of flow and tissue motion, the application of FSI can present challenges, particularly when data for constraining models is sparse and/or when fast computational simulations are required for assessment. In this paper, we propose a novel method for flexible-wall fluid dynamics in an ALE framework applicable for cardiovascular applications where adaptive fluid motion that emulates patient data is required. Efficiency and model simplicity are gained by a physics-based reduction to solid membrane formulations at the fluid-tissue interface combined with a Galerkin projection to a subspace spanned by boundary motion modes, leveraging snapshots observed from imaging data by use of Proper Orthogonal Decomposition (POD). The resulting fluid-reduced-solid interaction (FrSI) model is verified for a series of examples, illustrating efficacy and efficiency. Focusing on an idealized left ventricle model, we demonstrate homogenization of transmural active stress along with the capacity to accommodate prestress in the FrSI model, accounting for whole cycle mechanics by coupling to 0D pre- and afterload models (showing end-diastolic and end-systolic projected endocardial surface position errors of less than 1.5% and 3.5%, respectively). Further, we present strategies to compensate for the inherent approximation errors of the FrSI model, allowing for minimizing both the integral and spatial error between reduced and full-order model by re-calibrating parameters that govern diastolic and systolic function. Finally, the ability of FrSI to extrapolate to impaired system states (increased afterload, localized region of infarct) is shown, providing a simple yet effective strategy to enhance the POD subspace to further reduce errors. These results illustrate the potential of FrSI to streamline the simulation of hemodynamics in the heart and cardiovascular system.

Adjacency-based, non-intrusive model reduction for vortex-induced vibrations

Vortex-induced Vibrations (VIV) pose computationally expensive problems of high practical interest to several engineering fields. In this work we develop a non-intrusive, reduced-order modeling methodology, applied to two-dimensional (2D), VIV cases subject to a laminar, incompressible flow. Performing a physics-informed approximation of the Arbitrary Lagrangian–Eulerian (ALE) incompressible Navier–Stokes (NS), we derive a discrete-time, quadratic-bilinear model structure for the velocity flowfield on a reference domain. This structure, along with a predefined sparsity pattern motivated by the adjacency-based sparsity of the discretized NS-ALE operators, leads to the formulation of a sparse, full-order model (sFOM) inference problem. Thus, the data-driven inference task requires solving many “local” least squares (LS) problems, isolating the contribution of geometrically “nearest neighbours” for each degree of freedom. Numerical aspects of inference such as data centering and regularization, as well as the direct enforcement of boundary conditions under the sFOM formulation are extensively discussed. The inferred, sFOM operators are then projected to a non-intrusive reduced-order model (ROM) for the velocity flowfield via the Proper Orthogonal Decomposition (POD). The resulting non-intrusive ROM (sFOM-POD) is coupled with the first-principle, 2D solid oscillation equations, resulting to a hybrid physics-informed/first-principle VIV dynamics model, simulated using an implicit time integration scheme. The mapping of the coupled solution from the ALE reference domain to the current configuration is also presented. This methodology is applied to two testcases of an elliptical, non-deformable solid mounted on springs, subject to Re=90,180 flows. Numerical results indicate a successful coupling between the data-driven flowfield and solid dynamics, with prediction errors of less than 3% for both the flowfield and the solid oscillation. A comparative study with respect to the sFOM-POD dimension indicates the robustness and potential of the approach.

Preserving Lagrangian structure in data-driven reduced-order modeling of large-scale dynamical systems

This work presents a nonintrusive physics-preserving method to learn reduced-order models (ROMs) of Lagrangian systems, which includes nonlinear wave equations. Existing intrusive projection-based model reduction approaches construct structure-preserving Lagrangian ROMs by projecting the Euler–Lagrange equations of the full-order model (FOM) onto a linear subspace. This Galerkin projection step requires complete knowledge about the Lagrangian operators in the FOM and full access to manipulate the computer code. In contrast, the proposed Lagrangian operator inference approach embeds the mechanics into the operator inference framework to develop a data-driven model reduction method that preserves the underlying Lagrangian structure. The proposed approach exploits knowledge of the governing equations (but not their discretization) to define the form and parametrization of a Lagrangian ROM which can then be learned from projected snapshot data. The method does not require access to FOM operators or computer code. The numerical results demonstrate Lagrangian operator inference on an Euler–Bernoulli beam model, the sine-Gordon (nonlinear) wave equation, and a large-scale discretization of a soft robot fishtail with 779,232 degrees of freedom. The learned Lagrangian ROMs generalize well, as they can accurately predict the physical solutions both far outside the training time interval, as well as for unseen initial conditions.

VpROM: a novel variational autoencoder-boosted reduced order model for the treatment of parametric dependencies in nonlinear systems

Reduced Order Models (ROMs) are of considerable importance in many areas of engineering in which computational time presents difficulties. Established approaches employ projection-based reduction, such as Proper Orthogonal Decomposition. The limitation of the linear nature of such operators is typically tackled via a library of local reduction subspaces, which requires the assembly of numerous local ROMs to address parametric dependencies. Our work attempts to define a more generalisable mapping between parametric inputs and reduced bases for the purpose of generative modeling. We propose the use of Variational Autoencoders (VAEs) in place of the typically utilised clustering or interpolation operations, for inferring the fundamental vectors, termed as modes, which approximate the manifold of the model response for any and each parametric input state. The derived ROM still relies on projection bases, built on the basis of full-order model simulations, thus retaining the imprinted physical connotation. However, it additionally exploits a matrix of coefficients that relates each local sample response and dynamics to the global phenomena across the parametric input domain. The VAE scheme is utilised for approximating these coefficients for any input state. This coupling leads to a high-precision low-order representation, which is particularly suited for problems where model dependencies or excitation traits cause the dynamic behavior to span multiple response regimes. Moreover, the probabilistic treatment of the VAE representation allows for uncertainty quantification on the reduction bases, which may then be propagated to the ROM response. The performance of the proposed approach is validated on an open-source simulation benchmark featuring hysteresis and multi-parametric dependencies, and on a large-scale wind turbine tower characterised by nonlinear material behavior and model uncertainty.

Coupled thermal-mechanical analysis of power electronic modules with finite element method and parametric model order reduction

This work presents a new approach for performing a parametric study and examining nonlinear material behaviours of a coupled thermal-mechanical model of a Power Electronics Module (PEM) by integrating the Finite Element Method (ANSYS-FEM) with Parametric Model Order Reduction (pMOR). The considered coupling method solves the thermal and structural models concurrently compared to the widely practised sequential coupling method. Instead of constant parameter values, which are generally regarded for pMOR studies, the temperature-dependent material properties of the wire material have been parametrised in the work using the pMOR method. A generalised 2D model has been regarded here for thermal-mechanical analysis with the pMOR approach, parametrising temperature-dependent coefficient of thermal expansion (CTE) and Young’s modulus (E) of the wire material to explore their impact on wire bonds. The matrix interpolation method has been applied here for the pMOR study, and PRIMA, a Krylov subspace-based model order reduction (MOR) technique, has been exercised for local model order reductions. A new efficient process of matrix interpolation, based on the Lagrange interpolation technique, has been developed to implement matrix interpolation in the parametric reduced order model (pROM). The local reduced order models (ROMs) have a degree of freedom (DOF) of just 8, compared to the full-order models’ (FOMs) of 50,602. The pROM provides an excellent solution and reduces computational time by 84% for the presented case.

Thermal-Mechanical Analysis of a Power Module with Parametric Model Order Reduction

This paper presents parametric model order reduction (pMOR) by the Lagrange approach of matrix interpolation for the thermal-mechanical and reliability study of a power electronics module (PEM) with nonlinear behaviours. Most previous research in model order reduction (MOR) studies reports thermal-mechanical simulations using a sequentially coupled method. In this research, a direct-coupled thermal-mechanical analysis, which simultaneously solves the thermal and structural governing equations, has been used to obtain thermal and deformation results. Furthermore, for pMOR, the linear approach of matrix interpolation is limited to linear changes between sampled-parametric points. Hence, a new way of interpolating system matrices using the Lagrange interpolation method has been adopted to implement the matrix interpolation efficiently. The parametric reduced-order model (pROM) solution by the Lagrange approach of matrix interpolation agrees well with the full-order model (FOM) and takes similar computational time as the linear (bi-linear) approach of matrix interpolation. pROM simulations offer up to 85.5% reduction in computational time.

Error analysis of a reduced order method for the Allen-Cahn equation⁎

In this paper we carry out an error analysis for a reduced order method for the Allen-Cahn equation. First, an ensemble of snapshots is formed from the numerical solutions at some time instances of the full order model, which is a time-space discretisation of the Allen-Cahn equation. The reduced order model is essentially a new spatial discretisation method by using low dimensional approximations to the original approximation space. The low dimensional approximation space is generated from the ensemble of snapshots by applying a proper orthogonal decomposition method. To determine the error between the exact solution and the solution of the reduced order model. We consider a time-space discretisation for which an error estimate of the full model solution is available. Specifically, the full discretisation is based on a stabilized auxiliary variable approach for the time stepping and a spectral Galerkin method for the spatial discretisation. The advantages of this full discretisation are its unconditional stability, the availability of error estimates and its ease of implementation. An estimate of the errors in the H1 seminorm is rigorously derived for both the full order model and the reduced order model, which is then verified by some numerical examples.

Application of data-driven model reduction techniques in reactor neutron field calculations

High-order harmonic techniques can be used to recreate neutron flux distributions in reactor cores using the neutron diffusion equation. However, traditional source iteration and source correction iteration techniques have sluggish convergence rates and protracted calculation periods. The correctness of the implicitly restarted Arnoldi method (IRAM) in resolving the eigenvalue problems of the one-dimensional and two-dimensional neutron diffusion equations was confirmed by computing the benchmark problems SLAB_1D_1G and two-dimensional steady-state TWIGL using IRAM. By integrating Galerkin projection with Proper Orthogonal Decomposition (POD) techniques, a POD-Galerkin reduced-order model was developed and the IRAM model was used as the full-order model. For 14 macroscopic cross-section values, the TWIGL benchmark problem was perturbed within a 20% range. We extracted 100 sample points using the Latin hypercube sampling method, and 70% of the samples were used as the testing set to assess the performance of the reduced-order model The remaining 30% were utilized as the training set to develop the reduced-order model, which was employed to rebuild the TWIGL benchmark problem. The reduced-order model demonstrates good flexibility and can efficiently and accurately forecast the effective multiplication factor and neutron flux distribution in the core. The reduced-order model predicts keff and neutron flux distribution with a high degree of agreement compared to the full-order model. Additionally, the reduced-order model's computation time is only 10.18% of that required by the full-order model.The neutron flux distribution of the steady-state TWIGL benchmark was recreated using the reduced-order model. The obtained results indicate that the reduced-order model can accurately predict the keff and neutron flux distribution of the steady-state TWIGL benchmark.Overall, the proposed technique not only has the potential to accurately project neutron flux distributions in transient settings, but is also relevant for reconstructing neutron flux distributions in steady-state conditions; thus, its applicability is bound to increase in the future.

Lagrangian operator inference enhanced with structure-preserving machine learning for nonintrusive model reduction of mechanical systems

Complex mechanical systems often exhibit strongly nonlinear behavior due to the presence of nonlinearities in the energy dissipation mechanisms, material constitutive relationships, or geometric/connectivity mechanics. Numerical modeling of these systems leads to nonlinear full-order models that possess an underlying Lagrangian structure. This work proposes a Lagrangian operator inference method enhanced with structure-preserving machine learning to learn nonlinear reduced-order models (ROMs) of nonlinear mechanical systems. This two-step approach first learns the best-fit linear Lagrangian ROM via Lagrangian operator inference and then presents a structure-preserving machine learning method to learn nonlinearities in the reduced space. The proposed approach can learn a structure-preserving nonlinear ROM purely from data, unlike the existing operator inference approaches that require knowledge about the mathematical form of nonlinear terms. From a machine learning perspective, it accelerates the training of the structure-preserving neural network by providing an informed prior (i.e., the linear Lagrangian ROM structure), and it reduces the computational cost of the network training by operating on the reduced space. The method is first demonstrated on two simulated examples: a conservative nonlinear rod model and a two-dimensional nonlinear membrane with nonlinear internal damping. Finally, the method is demonstrated on an experimental dataset consisting of digital image correlation measurements taken from a lap-joint beam structure from which a predictive model is learned that captures amplitude-dependent frequency and damping characteristics accurately. The numerical results demonstrate that the proposed approach yields generalizable nonlinear ROMs that exhibit bounded energy error, capture the nonlinear characteristics reliably, and provide accurate long-time predictions outside the training data regime.

Accelerating structural dynamics simulations with localised phenomena through matrix compression and projection‐based model order reduction

AbstractIn this work, a novel approach is introduced for accelerating the solution of structural dynamics problems in the presence of localised phenomena, such as cracks. For this category of problems, conventional projection‐based Model Order Reduction (MOR) methods are either limited with respect to the range of system configurations that can be represented or require frequent solutions of the Full Order Model (FOM) to update the low‐dimensional spaces, in which solutions are represented. In the proposed approach, low‐dimensional spaces, constructed for the healthy structure, are enriched with appropriately selected columns of the flexibility matrix of the system. It can be shown that these spaces contain the solution to the original problem for the static case, while their dimension is much smaller. In order to allow their online construction for arbitrary localised features, the full flexibility matrix of the system should be available. To this end, a hierarchical representation is used for the matrices involved, allowing to compute the flexibility matrix efficiently and with reduced memory requirements. The resulting method offers significant speedups, without sacrificing the flexibility and accuracy of the full order model. The performance and limitations of the approach are studied through a series of examples in structural dynamics.

A pressure-free long-time stable reduced-order model for two-dimensional Rayleigh-Bénard convection.

The present work presents a stable proper orthogonal decomposition (POD)-Galerkin based reduced-order model (ROM) for two-dimensional Rayleigh-Bénard convection in a square geometry for three Rayleigh numbers: 104 (steady state), 3×105 (periodic), and 6×106 (chaotic). Stability is obtained through a particular (staggered-grid) full-order model (FOM) discretization that leads to a ROM that is pressure-free and has skew-symmetric (energy-conserving) convective terms. This yields long-time stable solutions without requiring stabilizing mechanisms, even outside the training data range. The ROM's stability is validated for the different test cases by investigating the Nusselt and Reynolds number time series and the mean and variance of the vertical temperature profile. In general, these quantities converge to the FOM when increasing the number of modes, and turn out to be a good measure of accuracy. However, for the chaotic case, convergence with increasing numbers of modes is relatively difficult and a high number of modes is required to resolve the low-energy structures that are important for the global dynamics.

Dynamic modeling and parameter sensitivity analysis of AUV by using the POD method and the HB-AFT method

Autonomous Underwater Vehicle (AUV) parameterization is a geometric modification method, and can quickly obtain excellent structure with low vibration and noise performance. Blindness and inefficiency are common outcomes of the lack of an efficient parameter selection approach. But not enough research has been done in this area. In this paper, the finite element (FE) method is used to establish the propeller–shaft–shell double beam system with ball bearings, which is more similar to the real model. The basic theory of the proper orthogonal decomposition (POD) method is introduced in detail, and the original full order model (FOM) is reduced to 4 DOFs. It is found that the accuracy of the reduced order model (ROM) is high enough and the calculation time is greatly reduced. The semi-numerical semi-analytical expression of the ROM system is solved by the harmonic balance and alternating frequency/time domain (HB-AFT) method, whose results are in good agreement with those by the Runge–Kutta method. The sensitivities of the shell responses to the spring stiffness are discussed. The AUV setup is designed to analysis of numerical and experimental results. These results in this paper can provide an advanced theoretical basis for the structural parameter design of the AUV.

A shape optimization pipeline for marine propellers by means of reduced order modeling techniques

AbstractIn this article, we propose a shape optimization pipeline for propeller blades, applied to naval applications. The geometrical features of a blade are exploited to parametrize it, allowing to obtain deformed blades by perturbating their parameters. The optimization is performed using a genetic algorithm that exploits the computational speed‐up of reduced order models to maximize the efficiency of a given propeller. A standard offline–online procedure is exploited to construct the reduced‐order model. In an expensive offline phase, the full order model, which reproduces an open water test, is set up in the open‐source software OpenFOAM and the same full order setting is used to run the CFD simulations for all the deformed propellers. The collected high‐fidelity snapshots and the deformed parameters are used in the online stage to build the nonintrusive reduced‐order model. This article provides a proof of concept of the pipeline proposed, where the optimized propeller improves the efficiency of the original propeller.