arXiv subjects

Hyeonbin Moon

Publications and source records attributed to Hyeonbin Moon.

9 recordsLinked to original sources

arXiv2026

Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations

Identifying anisotropic yield functions remains challenging since yielding is not directly observed in full-field mechanical measurements, directional calibration can require many loading directions, and selecting an appropriate analytical form is nontrivial. This study proposes a physics-informed framework for discovering yield functions from full-field displacement data and reaction force data, without stress observations, plastic strain measurements, direct yield surface data, or a prescribed parametric yield function. The framework identifies the yield function as a mechanically constrained constitutive component inside elastoplastic stress integration, rather than through direct stress-space supervision. The yield function is represented by a convex neural network that enforces convexity and positive homogeneity of degree one while imposing the assumed tension-compression symmetry, and this neural yield function is trained with a differentiable stress update and a physics-informed force equilibrium loss across multiple loading cases. The proposed framework is validated using finite element (FE) benchmark studies with von Mises, Hill 1948, and Yld2000-2d yield functions, assessing yield contour agreement, displacement-noise sensitivity, identifiability through plastically active stress states, epistemic uncertainty, and polynomial-surrogate deployment. This study provides a mechanics-constrained pathway for discovering anisotropic yield functions from displacement and force data while keeping the identified component within the structure of elastoplastic stress integration.

cs.LG↗

arXiv2026

A Hybrid GNN-FEM Framework for Phase-Field Fracture Simulation. Physics-Preserving Hybridization for Generalizable Surrogate Modeling

Scientific machine learning (SciML) has emerged as a promising approach for accelerating simulations of complex physical systems, yet achieving physically consistent and generalizable predictions for nonlinear, history-dependent problems remains a central challenge. In this study, we propose a hybrid GNN--FEM framework for efficient and generalizable phase-field fracture modeling. While phase-field approaches provide a robust variational framework for simulating complex crack evolution, their high computational cost limits practical applications because they require solving coupled, nonlinear, and history-dependent systems within an incremental finite element procedure. To address this challenge, a graph neural network surrogate is integrated into the conventional staggered scheme, replacing the phase-field update at each load increment while retaining the FEM-based displacement solver to enforce mechanical equilibrium and boundary conditions. By preserving the incremental solution structure, the framework remains consistent with history-dependent fracture evolution without requiring the surrogate to approximate the full solution trajectory. This selective surrogate strategy emphasizes the identification of a physically meaningful and incrementally structured learning target, rather than relying on brute-force data generation to learn the full fracture process. The proposed framework achieves strong generalization across varying geometries, loading conditions, material properties, and discretizations through dimensionless feature design, a graph-based formulation on mesh-based domains, and a physics-informed loss derived from the governing phase-field equation. Numerical experiments demonstrate that the hybrid approach reduces computational cost while maintaining accuracy compared with conventional FEM, and exhibits robust predictive performance across diverse problem settings.

cs.LG↗

arXiv2026

Critical evaluation of PINN for FWD inverse analysis and differentiable FEM as an alternative

Automatic-differentiation-based inverse analysis methods, including physics-informed neural networks (PINNs) and differentiable programming, have recently shown great promise due to their ability to compute accurate gradients and convergence efficiency. However, their applicability to falling weight deflectometer (FWD) backcalculation remains unexplored. This study critically evaluates PINN-based inverse analysis for a multilayer pavement system and investigates differentiable finite element method (DiffFEM) as an alternative based on a synthetic benchmark. The standard PINN does not recover layer moduli because of the sharp domain discontinuities inherent to layered pavement systems. Although we use an extended PINN with domain decomposition (XPINN), which shows better performance on discontinuous domains, its performance remains highly sensitive to loss weighting and network architecture, and degrades under measurement noise. By contrast, DiffFEM consistently achieves more accurate, stable, and computationally efficient inversion results. These results indicate that DiffFEM, which enforces the governing physics as a hard constraint, yields better accuracy, robustness, and computational efficiency than PINN-based approaches, in which the governing physics is imposed as a soft constraint through the loss function. More broadly, the findings suggest that the choice between PINN- and DiffFEM-based inverse analysis needs careful consideration, with DiffFEM offering practical advantages when an efficient and robust differentiable forward solver is available.

cs.CE↗

arXiv2025

Real-Time Structural Health Monitoring with Bayesian Neural Networks: Distinguishing Aleatoric and Epistemic Uncertainty for Digital Twin Frameworks

Reliable real-time analysis of sensor data is essential for structural health monitoring (SHM) of high-value assets, yet a major challenge is to obtain spatially resolved full-field aleatoric and epistemic uncertainties for trustworthy decision-making. We present an integrated SHM framework that combines principal component analysis (PCA), a Bayesian neural network (BNN), and Hamiltonian Monte Carlo (HMC) inference, mapping sparse strain gauge measurements onto leading PCA modes to reconstruct full-field strain distributions with uncertainty quantification. The framework was validated through cyclic four-point bending tests on carbon fiber reinforced polymer (CFRP) specimens with varying crack lengths, achieving accurate strain field reconstruction (R squared value > 0.9) while simultaneously producing real-time uncertainty fields. A key contribution is that the BNN yields robust full-field strain reconstructions from noisy experimental data with crack-induced strain singularities, while also providing explicit representations of two complementary uncertainty fields. Considered jointly in full-field form, the aleatoric and epistemic uncertainty fields make it possible to diagnose at a local level, whether low-confidence regions are driven by data-inherent issues or by model-related limitations, thereby supporting reliable decision-making. Collectively, the results demonstrate that the proposed framework advances SHM toward trustworthy digital twin deployment and risk-aware structural diagnostics.

cs.LG↗

arXiv2025

Thermal Conductivity Estimation of Thermoelectric Materials with Uncertainty Quantification Using Bayesian Physics-Informed Neural Networks

Characterizing the temperature-dependent thermal conductivity is challenging because the property varies strongly with temperature and reliable heat flow measurement, not just temperature sensing, is difficult under experimental conditions. Here, we present a physics informed deep learning framework that infers conductivity solely from sparse electric potential measurements. We first develop a deterministic physics-informed neural network (PINN) that embeds coupled thermoelectric transport equations as soft constraints, enabling simultaneous recovery of spatial temperature, voltage, and conductivity profiles without temperature data. The deterministic PINN achieves accurate inference under noise-free conditions, yet its predictions degrade when measurement noise is introduced. To address this, we extend the framework to a Bayesian PINN, which models network parameters probabilistically and employs Hamiltonian Monte Carlo (HMC) sampling for posterior inference. This extension produces robust thermal conductivity estimates and, importantly, provides credible intervals that quantify uncertainty from sparse and noisy data. Numerical experiments confirm that the Bayesian PINN not only preserves predictive accuracy under noise but also reveals inference bias and enables uncertainty aware interpretation of material properties. Together, the deterministic and Bayesian formulations establish a scalable and generalizable alternative to conventional methods for determining temperature-dependent properties, offering physics- consistent and risk-aware property inference for thermoelectric systems and other functional materials where direct temperature sensing is impractical

physics.comp-ph↗

arXiv2025

Physics-informed neural network framework for solving forward and inverse flexoelectric problems

Flexoelectricity, the coupling between strain gradients and electric polarization, poses significant computational challenges due to its governing fourth-order partial differential equations that require C1-continuous solutions. To address these issues, we propose a physics-informed neural network (PINN) framework grounded in an energy-based formulation that treats both forward and inverse problems within a unified architecture. The forward problem is recast as a saddle-point optimization of the total potential energy, solved via the deep energy method (DEM), which circumvents the direct computation of high-order derivatives. For the inverse problem of identifying unknown flexoelectric coefficients from sparse measurements, we introduce an additional variational loss that enforces stationarity with respect to the electric potential, ensuring robust and stable parameter inference. The framework integrates finite element-based numerical quadrature for stable energy evaluation and employs hard constraints to rigorously enforce boundary conditions. Numerical results for both direct and converse flexoelectric effects show excellent agreement with mixed-FEM solutions, and the inverse model accurately recovers material parameters from limited data. This study establishes a unified, mesh-compatible, and scalable PINN approach for high-order electromechanical problems, offering a promising alternative to traditional simulation techniques.

physics.comp-ph↗

arXiv2025

Physics-Informed Neural Operators for Generalizable and Label-Free Inference of Temperature-Dependent Thermoelectric Properties

Accurate characterization of temperature-dependent thermoelectric properties (TEPs), such as thermal conductivity and the Seebeck coefficient, is essential for reliable modeling and efficient design of thermoelectric devices. However, their nonlinear temperature dependence and coupled transport behavior make both forward simulation and inverse identification difficult, particularly under sparse measurement conditions. In this study, we develop a physics-informed machine learning approach that employs physics-informed neural networks (PINN) for solving forward and inverse problems in thermoelectric systems, and neural operators (PINO) to enable generalization across diverse material systems. The PINN enables field reconstruction and material property inference by embedding governing transport equations into the loss function, while the PINO generalizes this inference capability across diverse materials without retraining. Trained on simulated data for 20 p-type materials and evaluated on 60 unseen materials, the PINO model demonstrates accurate and label-free inference of TEPs using only sparse field data. The proposed framework offers a scalable, generalizable, and data-efficient approach for thermoelectric property identification, paving the way for high-throughput screening and inverse design of advanced thermoelectric materials.

cond-mat.mtrl-sci↗

arXiv2025

Toward Knowledge-Guided AI for Inverse Design in Manufacturing: A Perspective on Domain, Physics, and Human-AI Synergy

Artificial intelligence (AI) is reshaping inverse design in manufacturing, enabling high-performance discovery in materials, products, and processes. However, purely data-driven approaches often struggle in realistic manufacturing settings characterized by sparse data, high-dimensional design spaces, and complex constraints. This perspective proposes an integrated framework built on three complementary pillars: domain knowledge to establish physically meaningful objectives and constraints while removing variables with limited relevance, physics-informed machine learning to enhance generalization under limited or biased data, and large language model-based interfaces to support intuitive, human-centered interaction. Using injection molding as an illustrative example, we demonstrate how these components can operate in practice and conclude by highlighting key challenges for applying such approaches in realistic manufacturing environments.

cs.AI↗

arXiv2025

Physics-Informed Neural Network-Based Discovery of Hyperelastic Constitutive Models from Extremely Scarce Data

The discovery of constitutive models for hyperelastic materials is essential yet challenging due to their nonlinear behavior and the limited availability of experimental data. Traditional methods typically require extensive stress-strain or full-field measurements, which are often difficult to obtain in practical settings. To overcome these challenges, we propose a physics-informed neural network (PINN)-based framework that enables the discovery of constitutive models using only sparse measurement data - such as displacement and reaction force - that can be acquired from a single material test. By integrating PINNs with finite element discretization, the framework reconstructs full-field displacement and identifies the underlying strain energy density from predefined candidates, while ensuring consistency with physical laws. A two-stage training process is employed: the Adam optimizer jointly updates neural network parameters and model coefficients to obtain an initial solution, followed by L-BFGS refinement and sparse regression with l_p regularization to extract a parsimonious constitutive model. Validation on benchmark hyperelastic models demonstrates that the proposed method can accurately recover constitutive laws and displacement fields, even when the input data are limited and noisy. These findings highlight the applicability of the proposed framework to experimental scenarios where measurement data are both scarce and noisy.

physics.comp-ph↗