betaFeedback

WorksPhysics and Astronomy

Physics-Infused Reduced-Order Modeling for Analysis of Multi-Layered Hypersonic Thermal Protection Systems

Abstract

This work presents a physics-infused reduced-order modeling (PIROM) framework for efficient and accurate prediction of transient thermal behavior in multi-layered hypersonic thermal protection systems (TPS). The PIROM architecture integrates a reduced-physics backbone, based on the lumped-capacitance model (LCM), with data-driven correction dynamics formulated via a coarse-graining approach rooted in the Mori-Zwanzig formalism. While the LCM captures the dominant heat transfer mechanisms, the correction terms compensate for residual dynamics arising from higher-order non-linear interactions and heterogeneities across material layers. The proposed PIROM is benchmarked against two non-intrusive reduced-order models (ROMs): Operator Inference (OpInf) and Neural Ordinary Differential Equations (NODE). The PIROM consistently achieves errors below 1% for a wide range of extrapolative settings involving time- and space-dependent boundary conditions and temperature-varying material property perturbations. In contrast, OpInf exhibits moderate degradation, and NODE suffers substantial loss in accuracy due to its lack of embedded physics. Despite higher training costs, PIROM delivers online evaluations of two orders of magnitude faster than the full-order model. These results demonstrate that PIROM effectively reconciles the trade-offs between accuracy, generalizability, and efficiency, providing a robust framework for thermal modeling of TPS under diverse operating conditions.

Nomenclature

Roman Symbols

AA, AiA_i, BB, BijB_{ij} System matrices and their block-wise components

cpc_p Specific heat D\mathcal{D} Dataset

dd Dimension of the domain

EiE_i The iith element

E\mathcal{E} Collection of edges

eije_{ij} Boundary shared by elements ii and jj

f,fi\mathbf{f},\mathbf{f}_i Forcing vector and the iith component

J\mathcal{J} Objective function

k,k\mathbf{k},k Thermal conductivity

ℓ\ell Cost function

MM Number of elements

Ni\mathcal{N}_i Collection of neighbors for element ii

NN Number of layers in TPS

NpN_p Number of steps in a trajectory

NsN_s Number of high-fidelity trajectories

P,Q\mathcal{P},\mathcal{Q} Projection and Residual operators

PP Number of basis functions of an element

qq Heat flux

RR Thermal resistance

r(1),r(2)\mathbf{r}^{(1)},\mathbf{r}^{(2)} Resolved and Unresolved dynamics

TT Temperature

t,t0,tft,t_0,t_f Time, initial time, final time

u,ui\mathbf{u},\mathbf{u}_i Full state vector and the states of element ii

xx Spatial coordinate

yy State vector of PIROM

zzObservables

Greek Symbols

β\betaHidden states
Γ\GammaDomain boundary of partial differential equation
ϵ\epsilonTolerance in training
Θ\boldsymbol{\Theta}Learnable parameters in machine learning model
κ\kappa, κ~\tilde{\kappa}Memory kernels
ρ\rhoDensity
σ\sigmaPenalty factor in Discontinuous Galerkin
Φ\boldsymbol{\Phi}, Φ+\boldsymbol{\Phi}^{+}Projection matrix and its pseudo-inverse
ϕi\phi_i, ϕpi\phi^i_pBasis function of element ii, and its ppth component
φji\varphi^i_jWeight vector mapping states in element ii to average temperature jj
ξ\xiParameters for operating conditions
Ω\OmegaDomain of partial differential equation

Other symbols

□ˉ\bar{\square}Coarse-grained quantity
□ij\square_{ij}Quantity related to elements ii and jj
□HF\square_{HF}Quantities computed using the high-fidelity solver
□q\square_qQuantities related to Neumann boundary condition
□T\square_Tquantities related to Dirichlet boundary condition

Acronyms

BCBoundary Condition
DGDiscontinuous Galerkin
FEMFinite-Element Method

FOM Full-Order Model

IPG Interior-Penalty Galerkin

LCM Lumped-Capacitance Model

MZ Mori-Zwanzig

NN Neural Network

NODE Neural Ordinary Differential Equation

NRMSE Normalized Root-Mean Squared Error

OOD Out of Distribution

OpInf Operator Inference

PIROM Physics-Infused Reduced-Order Modeling

ROM Reduced-Order Model

RPM Reduced-Physics Model

TPS Thermal Protection System

Introduction

Thermal protection systems (TPS) play a critical role in ensuring safety and optimal performance of hypersonic vehicles operating in extreme environments such as atmospheric re-entry or long-range hypersonic cruise. The purpose of the TPS is to shield interior structures from excessive heating rates that may exceed thousands of Watts per square centimeter, depending on the speed, altitude, and trajectory of the space vehicle. For example, the Space Shuttle’s TPS – consisting primarily of reusable silica-based ceramic tiles on the fuselage and reinforced carbon-carbon (RCC) panels on the leading edges – was crucial in protecting the orbiter’s aluminum airframe from the surface temperatures reaching approximately 1,650 ∘C1{,}650\,^\circ\mathrm{C} during re-entry into the Earth’s atmosphere [1]. Advanced hypersonic aircraft, such as the X-51 Waverider and X-43 research plane, employed ablative ceramic matrix composites and heat-resistant alloys designed to withstand temperature above 1,200 ∘C1{,}200\,^\circ\mathrm{C} at speeds approaching Mach 7 [2, 3]. Other applications, such as the Mars Science Laboratory (MSL) rover, used a heat shield composed of phenolic impregnated carbon ablator (PICA) to protect the rover from the intense heat generated during the entry, descent, and landing (EDL) phase on Mars [4]. The examples above demonstrate the critical role of TPS in ensuring the survivability and optimal performance of hypersonic vehicles, underscoring the need for meticulous analysis, design, and rapid manufacturing processes that adhere to strict time and budget constraints.

Nevertheless, designing TPS for complex vehicle geometries – e.g., those with wing-body blending, control surfaces, or highly curved forebodies – introduces geometry-induced complexities in both fluid flow and structural layouts. The presence of such geometric features can lead to highly non-uniform heating rates, shock-layer interactions, and boundary-layer transition, which can significantly affect the performance and survivability of the TPS. Furthermore, accounting for both in-plane and through-thickness variability of material properties, while resolving the difference in local geometries, adds to the computational burden. The high-dimensionality of the aero-thermo-structural domains, together with the extensive exploration required in the design space, leads to computationally prohibitive demands when relying on high-fidelity simulations – such as large-scale computational fluid dynamics (CFD) and finite-element methods (FEMs) for fluid and structural analysis, respectively – due to their immense cost in memory and run time.

Reduced-order models (ROMs) have emerged as a promising approach to address the computational challenges associated with thermodynamic modeling of TPS. Ideally, a ROM should be (1) accurate to reproduce high-fidelity solutions, (2) support continuous or infinite-dimensional design parameters such as geometrical shapes and material distributions, and (3) be computationally efficient to evaluate to allow for fast turnaround time in design optimization. However, the above three capabilities usually form an impossible trinity of modeling, as illustrated in Figure 1; building a ROM that achieves any two capabilities sacrifices the third.

The impossible trinity of modeling in the context of TPS

Figure 1. The impossible trinity of modeling in the context of TPS.

The impossible trinity poses a significant challenge in the development of ROMs for the multi-disciplinary analysis and optimization of TPS. More specifically, full-order models (FOMs), such as finite-element methods (FEMs), offer high accuracy and robust handling of diverse design space, but they are computationally expensive to run. Reduced-physics models (RPMs) – such as simplified convective-radiative heat transfer or engineering correlations – achieve efficiency and broad applicability by ignoring certain non-linear or small-scale effects, however, RPMs sacrifice accuracy for complex thermal boundary conditions or material behaviors. Lastly, data-driven ROMs, such as Gaussian Process Regressors [5] and neural ordinary differential equations (NODE) [6], do provide accurate and computationally efficient approximations of highly non-linear input-output for the temperature distributions over the TPS layers; nonetheless, these data-centric approaches often demand extensive high-fidelity data for training, do not necessarily satisfy fundamental physical constraints or conservation laws, and thus do not generalize well to design space outside the training data.

The landscape of ROM techniques is rapidly changing over time, and some developments may have brought ROMs closer to solving the impossible trinity of modeling. These ROMs are typically divided into intrusive and non-intrusive approaches. In traditional projection-based methods, such as proper-orthogonal decomposition with Galerkin projections (POD-G) [7, 8, 9, 10], a reduced-form representation of the full-order solution is introduced into the FOM to reduce problem dimensionality and preserve the governing physics [11]. Although successful in thermal modeling of ablative TPS systems [12, 13], intrusive methods are only applicable when FOM operators are available, which is not practical in many engineering scenarios where high-fidelity solvers are treated as black boxes.

In contrast, non-intrusive ROMs circumvent the need for direct access to the FOM equations by learning reduced dynamics from high-fidelity simulation or measurement data. Towards the solution of the impossible trinity of modeling, recent advances in non-intrusive reduced-order modeling have emphasized physics-informed approaches; such approaches incorporate physical knowledge in the ROM so as to increase generalizing capability to unknown operating scenarios, particularly when training data are scarce. Physics-informed neural networks (PINNs) [14, 15, 16] incorporate governing laws (e.g., conservation of mass, momentum, energy) into the loss function during training, improving generalizability and reducing the reliance on large datasets [17]. For example, when predicting the stagnation point heat flux over a blunt-nosed body [18], the PINN achieved a predictive accuracy of 4.5% for parameters involving geometries and operating conditions outside the training datasets – this is in contrast to the purely data-driven model, whose error nearly doubled. Physics-Informed DeepONets (PIDeepONets) [19] [20, 21] extended this idea to operator learning, capturing mappings between function spaces under physics constraints. For example, in Ref. [22], it is shown that by including the continuity equation in the objective function, the PIDeepONet can extrapolate chemically-reacting hypersonic wave predictions with an accuracy of 5% for wave perturbations and space-time domains outside the training datasets; the predictions are done for cases where the full-field data is partially known.

Another instance of non-intrusive modeling is Operator inference (OpInf) [23]. The physics-informed nature of the OpInf provides a balance between data-driven flexibility and physics-based structure, and is termed as a “glass-box” approach, as the targeted dynamics are known via the governing PDEs that define the problem of interest, but the inner workings of the high-fidelity solver are unknown. The OpInf projects the governing PDE dynamics onto a reduced basis constructed from high-fidelity snapshot data; the result is a ROM based on the structure of the projected PDE, typically in the form of polynomials. The learning of the operators is performed in the projected space, using a least-squares approach on high-fidelity state data [11]. The OpInf has demonstrated success in rocket combustion [23], TPS thermal modeling [24], and fluid dynamics [23], achieving over three orders of magnitude of computational speed-ups relative to the CFD high-fidelity solvers.

Nonetheless, these methods also exhibit limitations: PINNs and PI-DeepONets only weakly enforce physical laws during training and potentially require large datasets to achieve high accuracy. Meanwhile, OpInf models face challenges when parametric dependency is needed. Due to the model form construction, the parameters need to appear as explicit non-linear features in the OpInf model. The numbers of such features would grow exponentially as more parameters and more non-linear relations are involved, e.g., cubic or quartic operators, which poses a challenge in learning such model from data; this renders OpInf non-ideal for vast design space explorations under scarce high-fidelity data.

This work presents a novel physics-infused reduced-order modeling (PIROM) approach [25–28], a non-intrusive hybrid framework that combines the strengths of physics-based models with machine learning, to formulate and train a ROM for parametrized non-linear dynamical systems. The PIROM methodology is demonstrated for the transient thermodynamics analysis of multi-layered TPS in a high-speed vehicle. The physics component is the lumped capacitance model (LCM), a classical theoretical model of heat conduction and convection, that captures physically-sound, though not accurate, transient temperature dynamics in the multi-layered TPS. The LCM captures arbitrary design parameters in boundary conditions and material properties and can account for a level of non-linearity such as temperature-dependent material properties. The LCM is extended with a data-driven hidden dynamics to account for the missing physics in the LCM, which are learned from high-fidelity data. The hidden dynamics enables higher predictive accuracy of the PIROM when subjected to complex boundary conditions and new material properties. Through this hybrid approach, the PIROM aims to solve the impossible trinity of modeling by leveraging the generalizability and computational efficiency of RPMs, while incorporating the accuracy and adaptability of data-driven extensions.

Moreover, in prior work on PIROM, the hidden dynamics for correction is devised in a heuristic manner, e.g., by introducing corrections to semi-empirical coefficients in a boundary layer model [27]; such heuristic approach might not be applicable to other applications, such as the TPS problem. This study adopts earlier work on coarse-graining modeling of non-linear dynamics [29] to rigorously derive the model form for a PIROM using the Mori-Zwanzig formalism [33] [30, 31, 32]. For the TPS problem, this formulation produces a sufficiently simple model form while maintaining the physical consistency of PIROM. More importantly, the formulation provides a general methodology for developing PIROMs for other problems.

In sum, the objectives of this work are as follows:

  1. Formulate the PIROM for the transient thermodynamics of the multi-layered TPS through a systematic coarse-graining procedure based on the Mori-Zwanzig formalism.

  1. Perform the convergence study of the PIROM, especially its convergence to the full-order solution as the model size increases.

  1. Benchmark the accuracy, generalizability, and efficiency of the PIROM with respect to the other representative non-intrusive ROMs, including OpInf and NODE.

Modeling of Thermal Protection Systems

This section formulates the heat conduction problem for a generic TPS geometry, and provides two different but mathematically-connected solution strategies: (1) a high-fidelity full-order model (FOM) based on a discontinuous Galerkin finite element method, and (2) a low-fidelity reduced-physics model (RPM) based on a lumped capacitance model (LCM). The FOM is computationally expensive but provides the highest fidelity, while the RPM is computationally efficient but has low predictive fidelity; both models are amenable to high-dimensional design variables. The RPM is used in the subsequent sections for deriving the PIROM.

Governing Equations

Consider a generic domain Ω⊂Rd\Omega\subset\mathbb{R}^{d}, d=2d = 2 or 3, with prescribed heat flux qbq_b on boundary Γq\Gamma_q (i.e., Neumann boundary condition) and prescribed temperature TbT_b on boundary ΓT\Gamma_T (i.e., Dirichlet boundary condition), where ∂Ω=Γq∪ΓT\partial\Omega= \Gamma_q \cup\Gamma_T. The transient heat conduction dynamics is governed by the following equation,

ρcp∂T∂t−∇⋅(k∇T)=0,x∈Ω(1)\rho c_p \frac{\partial T}{\partial t} - \nabla\cdot(k\nabla T) = 0,\quad x \in\Omega \tag*{(1)}
−k∇T⋅n=qb(x,t),x∈Γq(2)-k\nabla T \cdot n = q_b(x,t),\quad x \in\Gamma_q \tag*{(2)}
T(x,t)=Tb(x,t),x∈ΓT(3)T(x,t) = T_b(x,t),\quad x \in\Gamma_T \tag*{(3)}
T(x,0)=T0(x),x∈Ω,(4)T(x,0) = T_0(x),\quad x \in\Omega, \tag*{(4)}

where the density ρ\rho is constant, while heat capacity cpc_p, and thermal conductivity k∈Rd×dk \in\mathbb{R}^{d\times d}, are temperature-dependent. The TPS domain is divided into NN non-overlapping components {Ωi}i=1N\{\Omega_i\}_{i=1}^{N}, as illustrated in Figure 2 for N=2N = 2. The ii-th component Ωi\Omega_i is associated with a different set of material properties (ρi,cp,i,ki)(\rho_i, c_{p,i}, k_i), that are assumed to be continuous within one component, and can be discontinuous across two neighboring components.

Composite structure inside TPS

Figure 2. Composite structure inside TPS.

Full-Order Model: Finite Element Method

To obtain the full-order numerical solution, the governing equation is spatially discretized using variational principles of Discontinuous Galerkin (DG) to result in a high-dimensional system of ordinary differential equations (ODEs). Furthermore, the DG model is written in an element-wise form, which is beneficial for subsequent derivations for the lower-order models. Note that the choice of DG approach here is mainly for theoretical convenience in the subsequent coarse-graining formulation. In Sec. IV, the full-order TPS solution is computed using standard FEM instead, and the equivalence between DG and standard FEM is noted upon their convergence.

Domain Discretization

Consider a conforming mesh partition of the domain, as shown in Figure 2, where each element belongs to one and only one component. Denote the collection of all MM elements as {Ei}i=1M\{E_i\}_{i=1}^{M}. To ease the description of the DG model, a graph structure is employed. The elements are treated as vertices, the set of which is denoted V={m}m=1M\mathcal{V}=\{m\}_{m=1}^{M}. Two neighboring elements, EiE_i and EjE_j, are connected by an edge (i,j)(i,j), and the shared boundary between EiE_i and EjE_j is denoted eije_{ij}. The collection of all edges are denoted E\mathcal{E}, and G=(V,E)\mathcal{G}=(\mathcal{V},\mathcal{E}) is referred to as a graph. In the graph, the edges are undirected, meaning if (i,j)∈E(i,j)\in\mathcal{E} then (j,i)∈E(j,i)\in\mathcal{E}. Furthermore, denote the neighbors of the iith element as Ni={j∣(i,j)∈E}\mathcal{N}_i=\{j\mid(i,j)\in\mathcal{E}\}. Lastly, for the ease of notation, introduce two special indices: TT for the boundary of an element that overlaps with the Dirichlet boundary condition, and similarly qq for the Neumann boundary condition.

Weak Form of Discontinuous Galerkin Method

Choosing appropriate basis functions vv and ww and using the Interior Penalty Galerkin (IPG) scheme [34], the variational bilinear form for Eq. (1) is,

∑i=1Maϵ,i(v,w)=∑i=1MLi(v),(5)\sum_{i=1}^{M} a_{\epsilon,i}(v,w)=\sum_{i=1}^{M} L_i(v), \tag*{(5)}

where ϵ\epsilon is a user-specified parameter, and

aϵ,i(v,w)=∫Ei(ρcpv∂w∂t+k∇v⋅∇w) dΩ−∑j∈Ni∪{T}∫eij{k∇v⋅n}[w] dΓ+ϵ∑j∈Ni∪{T}∫eij{k∇w⋅n}[v] dΓ+σ∑j∈Ni∪{T}∫eij[v][w] dΓ(6)\begin{aligned} a_{\epsilon,i}(v,w) ={}& \int_{E_i} \left(\rho c_p v \frac{\partial w}{\partial t} + k\nabla v \cdot\nabla w\right)\,d\Omega\\ &- \sum_{j\in N_i\cup\{T\}} \int_{e_{ij}} \{k\nabla v\cdot n\}[w]\,d\Gamma+ \epsilon\sum_{j\in N_i\cup\{T\}} \int_{e_{ij}} \{k\nabla w\cdot n\}[v]\,d\Gamma+ \sigma\sum_{j\in N_i\cup\{T\}} \int_{e_{ij}} [v][w]\,d\Gamma \tag*{(6)} \end{aligned}
Li(v)=ϵ∑j∈Ni∪{T}∫eij(k∇w⋅n)Tb dΓ+∫eiqvqb dΓ+σ∫eiTvTb dΓ.(7)L_i(v) = \epsilon\sum_{j\in N_i\cup\{T\}} \int_{e_{ij}} (k\nabla w\cdot n)T_b\,d\Gamma+ \int_{e_{iq}} vq_b\,d\Gamma+ \sigma\int_{e_{iT}} vT_b\,d\Gamma. \tag*{(7)}

In the bi-linear form above, the notations of [][] and {}\{\} are respectively the jumps and averages at a boundary ee shared by two elements, E1E_1 and E2E_2,

[u]=u∣E1−u∣E2,{u}=12(u∣E1+u∣E2),for x∈e=E1∩E2.(8)[u] = u|_{E_1} - u|_{E_2}, \qquad\{u\} = \frac{1}{2}(u|_{E_1} + u|_{E_2}), \qquad\text{for } x \in e = E_1 \cap E_2. \tag*{(8)}

Furthermore, in the bi-linear form, the terms associated with σ\sigma are introduced to enforce the Dirichlet boundary condition; σ\sigma is a penalty factor whose value can depend on the size of an element. Depending of the choice of ϵ\epsilon, the bi-linear form corresponds to symmetric IPG (ϵ=−1\epsilon=-1), non-symmetric IPG (ϵ=1\epsilon=1), and incomplete IPG (ϵ=0\epsilon=0). All these schemes are consistent with the original PDE and have similar convergence rate with respect to mesh size. In the following derivations, the case ϵ=0\epsilon=0 is chosen for the sake of simplicity.

Discontinuous Galerkin Model

Next, the DG-based full-order model is written in an element-wise form. For the ii-th element, use a set of PP trial functions, such as polynomials, to represent the temperature distribution,

References

  1. [1]Jenkins, D. R., Space Shuttle: The History of the National Space Transportation System, Voyageur Press, 2007.
  2. [2]Price, A. B., “Design Report - Thermal Protection System X-15A-2,” Tech. rep., National Aeronautics and Space Administration, 1968.
  3. [3]Ohlhorst, C. W., Glass, D., Bruce, W. E., Lindell, M. C., Vaughn, W. L., Smith, R. W., Dirling, R. B., Hogenson, P. A., Nichols, J., Risner, N. W., Thompson, D. R., Kowbel, W., Sullivan, B. J., Koenig, J. R., and Cuneo, J. C., “Development of X-43A Mach 10 Leading Edges,” 56th International Astronautical Congress of the International Astronautical Federation and The International Academy of Astronautics and The International Institute of Space Law, Fukuoka Japan, 2005. https://doi.org/10.2514/6.IAC-05-D2.5.06.
  4. [4]Beck, R. A. S., Driver, D. M., Wright, M. J., and Hwang, H. H., “Development of the Mars Science Laboratory Heatshield Thermal Protection System,” Journal of Spacecraft and Rockets, Vol. 51, No. 4, 2014. https://doi.org/10.2514/1.A32635.
  5. [5]Rasmussen, C. E., and Williams, C. K. I., Gaussian Processes for Machine Learning, The MIT Press, 2005. https://doi.org/10.7551/mitpress/3206.001.0001.
  6. [6]Chen, R. T. Q., Rubanova, Y., Bettenсourt, J., and Duvenaud, D., “Neural Ordinary Differential Equations,” arXiv, 2018. https://doi.org/10.48550/arXiv.1806.07366.
  7. [7]Sirovich, L., “Turbulence and the Dynamics of Coherent Structures Part I: Coherent Structures,” Quarterly of Applied Mathematics, Vol. 45, No. 3, 1987, pp. 561–571.DOI
  8. [8]Sirovich, L., “Turbulence and the Dynamics of Coherent Structures Part II: Symmetries and Transformations,” Quarterly of Applied Mathematics, Vol. 45, No. 3, 1987, pp. 573–582.DOI
  9. [9]Sirovich, L., “Turbulence and the Dynamics of Coherent Structures Part III: Dynamics and Scaling,” Quarterly of Applied Mathematics, Vol. 45, No. 3, 1987, pp. 583–590.DOI
  10. [10]Willcox, K., and Peraire, J., “Balanced Model Reduction via the Proper Orthogonal Decomposition,” AIAA Journal, Vol. 40, No. 11, 2012, pp. 2323–2330. https://doi.org/10.2514/2.1570.
  11. [11]Benner, P., Goyal, P., Kramer, B., Peherstorfer, B., and Willcox, K., “Operator Inference for Non-Intrusive Model Reduction of Systems with Non-Polynomial Nonlinear Terms,” Computer Methods in Applied Mechanics and Engineering, Vol. 372, 2020, p. 113433. https://doi.org/10.1016/j.cma.2020.113433.
  12. [12]Arienti, M., Blonigan, P. J., Rizzi, F., Tencer, J., and Howard, M., “Projection-Based Model Reduction for Finite-Element Simulations of Thermal Protection Systems,” AIAA SciTech Forum, Virtual, 2021. https://doi.org/10.2514/6.2021-1717.
  13. [13]Blonigan, P. J., Tencer, J. T., and Rizzi, F., “Projection-based Reduced-Order Models with Hyperreduction for Finite Element Simulations of Thermal Protection Systems,” AIAA AVIATION 2023 Forum, San Diego, California, 2023. https://doi.org/10.2514/6.2023-3913.
  14. [14]Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., and Yang, L., “Physics-Informed Machine Learning,” ResearchGate, 2021, pp. 1–19. https://doi.org/10.1038/s42254-021-00314-5.
  15. [15]Lui, H. F. S., and Wolf, W. R., “Convolutional Neural Networks for the Construction of Surrogate Models for Fluid Flows,” 2021. https://doi.org/10.2514/6.2021-1675.
  16. [16]Hao, Z., Liu, S., Zhang, Y., Ying, C., Feng, Y., Su, H., and Zhu, J., “Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications,” arXiv, 2022. https://doi.org/10.48550/arXiv.2211.08064.
  17. [17]Penwarden, M., Zhe, S., Narayan, A., and Kirby, R. M., “A metalearning approach for Physics-Informed Neural Networks (PINNs): Application to parameterized PDEs,” Journal of Computational Physics, Vol. 477, 2023, p. 111912. https://doi.org/10.1016/j.jcp.2023.111912.
  18. [18]Yasar, H. A., and Sevinc, O. K., “Physics-Informed Neural Networks for Enhanced Critical Heat Flux Prediction in Hypersonic Flows,” AIAA Aviation Forum and ASCEND Conference, Las Vegas, Nevada, 2024. https://doi.org/10.2514/6.2024-4203.
  19. [19]Wang, R., and Yu, R., “Physics-Guided Deep Learning for Dynamical Systems: A Survey,” arXiv, 2021. https://doi.org/10.48550/arXiv.2107.01272.
  20. [33]Lin, Y. T., Tian, Y., Livescu, D., and Anghel, M., “Data-Driven Learning for the Mori–Zwanzig Formalism: A Generalization of the Koopman Learning Framework,” SIAM Journal on Applied Dynamical Systems, Vol. 20, No. 4, 2021, pp. 2558–2601. https://doi.org/10.1137/21M1401759.
  21. [34]Cohen, G., and Pernet, S., Finite Element and Discontinuous Galerkin Methods for Transient Wave Equations, Springer Dordrecht, 2018. https://doi.org/10.1007/978-94-017-7761-2.
  22. [35]Incropera, F. P., DeWitt, D. P., Bergman, T. L., and Lavine, A. S., Fundamentals of Heat and Mass Transfer, 7th ed., Wiley, Hoboken, NJ, 2011.
  23. [36]Parish, E., and Duraisamy, K., Coarse-Graining Turbulence Using the Mori–Zwanzig Formalism, Cambridge University Press, 2025.DOI
  24. [37]Betts, J. T., “Survey of Numerical Methods for Trajectory Optimization,” Journal of Guidance Control Dynamics, Vol. 21, No. 2, 1998, pp. 193–207. https://doi.org/10.2514/2.4231.
  25. [38]Klock, R. J., and Cesnik, C. E. S., “Nonlinear Thermal Reduced-Order Modeling for Hypersonic Vehicles,” AIAA Journal, Vol. 55, No. 7, 2017, pp. 2358–2368. https://doi.org/10.2514/1.J055499.
  26. [39]Clausen, J., Brunini, V., Collins, L., Knaus, R. C., Kucala, A., Lin, S., Moser, D. R., Phillips, M., Ransegnola, T. M., Subia, S. R., et al., “SIERRA Multimechanics Module: Aria Verification Manual-Version 5.22,” Tech. rep., Sandia National Lab.(SNL-NM), Albuquerque, NM (United States), 2024.
  27. [40]Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A., “Automatic Differentiation in PyTorch,” Tech. rep., October 2017.
  28. [41]Kingma, D., and Ba, J., “Adam: A Method for Stochastic Optimization,” International Conference on Learning Representations, 2014. https://doi.org/10.48550/arXiv.1412.6980.
  29. [42]Yu, Y., Huang, D., Park, S., and Pangborn, H., “Learning Networked Dynamical System Models with Weak Form and Graph Neural Networks,” arXiv preprint arXiv:2407.16779, 2024. https://doi.org/10.48550/arXiv.2407.16779.

Paper details

vlnc:W_4p5rasxp
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Physics and Astronomy

Not recorded for this paper

View statement
Looking for related papers…
Contents