arXiv subjects

Tengfei Luo

Publications and source records attributed to Tengfei Luo.

At least 37 records · Page 2Linked to original sources

arXiv2025

Predicting Stress and Damage in Carbon Fiber-Reinforced Composites Deformation Process using Composite U-Net Surrogate Model

Carbon fiber-reinforced composites (CFRC) are pivotal in advanced engineering applications due to their exceptional mechanical properties. A deep understanding of CFRC behavior under mechanical loading is essential for optimizing performance in demanding applications such as aerospace structures. While traditional Finite Element Method (FEM) simulations, including advanced techniques like Interface-enriched Generalized FEM (IGFEM), offer valuable insights, they can struggle with computational efficiency. Existing data-driven surrogate models partially address these challenges by predicting propagated damage or stress-strain behavior but fail to comprehensively capture the evolution of stress and damage throughout the entire deformation history, including crack initiation and propagation. This study proposes a novel auto-regressive composite U-Net deep learning model to simultaneously predict stress and damage fields during CFRC deformation. By leveraging the U-Net architecture's ability to capture spatial features and integrate macro- and micro-scale phenomena, the proposed model overcomes key limitations of prior approaches. The model achieves high accuracy in predicting evolution of stress and damage distribution within the microstructure of a CFRC under unidirectional strain, offering a speed-up of over 60 times compared to IGFEM.

cs.LG↗

arXiv2025

Quantum Annealing for Combinatorial Optimization: A Benchmarking Study

Quantum annealing (QA) has the potential to significantly improve solution quality and reduce time complexity in solving combinatorial optimization problems compared to classical optimization methods. However, due to the limited number of qubits and their connectivity, the QA hardware did not show such an advantage over classical methods in past benchmarking studies. Recent advancements in QA with more than 5,000 qubits, enhanced qubit connectivity, and the hybrid architecture promise to realize the quantum advantage. Here, we use a quantum annealer with state-of-the-art techniques and benchmark its performance against classical solvers. To compare their performance, we solve over 50 optimization problem instances represented by large and dense Hamiltonian matrices using quantum and classical solvers. The results demonstrate that a state-of-the-art quantum solver has higher accuracy (~0.013%) and a significantly faster problem-solving time (~6,561x) than the best classical solver. Our results highlight the advantages of leveraging QA over classical counterparts, particularly in hybrid configurations, for achieving high accuracy and substantially reduced problem solving time in large-scale real-world optimization problems.

quant-ph↗

arXiv2025

Implicit Neural Differential Model for Spatiotemporal Dynamics

Hybrid neural-physics modeling frameworks through differentiable programming have emerged as powerful tools in scientific machine learning, enabling the integration of known physics with data-driven learning to improve prediction accuracy and generalizability. However, most existing hybrid frameworks rely on explicit recurrent formulations, which suffer from numerical instability and error accumulation during long-horizon forecasting. In this work, we introduce Im-PiNDiff, a novel implicit physics-integrated neural differentiable solver for stable and accurate modeling of spatiotemporal dynamics. Inspired by deep equilibrium models, Im-PiNDiff advances the state using implicit fixed-point layers, enabling robust long-term simulation while remaining fully end-to-end differentiable. To enable scalable training, we introduce a hybrid gradient propagation strategy that integrates adjoint-state methods with reverse-mode automatic differentiation. This approach eliminates the need to store intermediate solver states and decouples memory complexity from the number of solver iterations, significantly reducing training overhead. We further incorporate checkpointing techniques to manage memory in long-horizon rollouts. Numerical experiments on various spatiotemporal PDE systems, including advection-diffusion processes, Burgers' dynamics, and multi-physics chemical vapor infiltration processes, demonstrate that Im-PiNDiff achieves superior predictive performance, enhanced numerical stability, and substantial reductions in memory and runtime cost relative to explicit and naive implicit baselines. This work provides a principled, efficient, and scalable framework for hybrid neural-physics modeling.

cs.LG↗

arXiv2025

JAX-BTE: A GPU-Accelerated Differentiable Solver for Phonon Boltzmann Transport Equations

This paper introduces JAX-BTE, a GPU-accelerated, differentiable solver for the phonon Boltzmann Transport Equation (BTE) based on differentiable programming. JAX-BTE enables accurate, efficient and differentiable multiscale thermal modeling by leveraging high-performance GPU computing and automatic differentiation. The solver efficiently addresses the high-dimensional and complex integro-differential nature of the phonon BTE, facilitating both forward simulations and data-augmented inverse simulations through end-to-end optimization. Validation is performed across a range of 1D to 3D simulations, including complex FinFET structures, in both forward and inverse settings, demonstrating excellent performance and reliability. JAX-BTE significantly outperforms state-of-the-art BTE solvers in forward simulations and uniquely enables inverse simulations, making it a powerful tool for multiscale thermal analysis and design for semiconductor devices.

physics.comp-ph↗

arXiv2025

POINT$^{2}$: A Polymer Informatics Training and Testing Database

The advancement of polymer informatics has been significantly propelled by the integration of machine learning (ML) techniques, enabling the rapid prediction of polymer properties and expediting the discovery of high-performance polymeric materials. However, the field lacks a standardized workflow that encompasses prediction accuracy, uncertainty quantification, ML interpretability, and polymer synthesizability. In this study, we introduce POINT$^{2}$ (POlymer INformatics Training and Testing), a comprehensive benchmark database and protocol designed to address these critical challenges. Leveraging the existing labeled datasets and the unlabeled PI1M dataset, a collection of approximately one million virtual polymers generated via a recurrent neural network trained on the realistic polymers, we develop an ensemble of ML models, including Quantile Random Forests, Multilayer Perceptrons with dropout, Graph Neural Networks, and pretrained large language models. These models are coupled with diverse polymer representations such as Morgan, MACCS, RDKit, Topological, Atom Pair fingerprints, and graph-based descriptors to achieve property predictions, uncertainty estimations, model interpretability, and template-based polymerization synthesizability across a spectrum of properties, including gas permeability, thermal conductivity, glass transition temperature, melting temperature, fractional free volume, and density. The POINT$^{2}$ database can serve as a valuable resource for the polymer informatics community for polymer discovery and optimization.

cond-mat.mtrl-sci↗

arXiv2024

Graph Diffusion Transformers for Multi-Conditional Molecular Generation

Inverse molecular design with diffusion models holds great potential for advancements in material and drug discovery. Despite success in unconditional molecular generation, integrating multiple properties such as synthetic score and gas permeability as condition constraints into diffusion models remains unexplored. We present the Graph Diffusion Transformer (Graph DiT) for multi-conditional molecular generation. Graph DiT integrates an encoder to learn numerical and categorical property representations with the Transformer-based denoiser. Unlike previous graph diffusion models that add noise separately on the atoms and bonds in the forward diffusion process, Graph DiT is trained with a novel graph-dependent noise model for accurate estimation of graph-related noise in molecules. We extensively validate Graph DiT for multi-conditional polymer and small molecule generation. Results demonstrate the superiority of Graph DiT across nine metrics from distribution learning to condition control for molecular properties. A polymer inverse design task for gas separation with feedback from domain experts further demonstrates its practical utility.

cs.LG↗

arXiv2024

Experimental observation of ballistic to diffusive transition in AlN thin films

Bulk AlN possesses high thermal conductivity due to long phonon mean-free-paths, high group velocity, and long lifetimes. However, the thermal transport scenario becomes very different in a thin AlN film due to phonon-defect and phonon-boundary scattering. Herein, we report experimental observation of ballistic to diffusive transition in a series of AlN thin films (1.6 - 2440 nm) grown on sapphire substrates. The ballistic transport is characterized by constant thermal resistance as a function of film thickness due to phonon scattering by defects and boundaries. In this transport regime, phonons possess very small group velocities and lifetimes. The lifetime of the optical phonons increases by more than an order of magnitude in the diffusive regime, however, remains nearly constant afterwards. Our study is important for understanding the details of nano and microscale thermal transport in a highly conductive material.

physics.app-ph↗

arXiv2024

Fourier neural operator for large eddy simulation of compressible Rayleigh-Taylor turbulence

The Fourier neural operator (FNO) framework is applied to the large eddy simulation (LES) of three-dimensional compressible Rayleigh-Taylor (RT) turbulence with miscible fluids at Atwood number $A_t=0.5$, stratification parameter $Sr=1.0$, and Reynolds numbers $Re=10000$ and 30000. The FNO model is first used for predicting three-dimensional compressible turbulence. The different magnitudes of physical fields are normalized using root mean square values for an easier training of FNO models. In the \emph{a posteriori} tests, the FNO model outperforms the velocity gradient model (VGM), the dynamic Smagorinsky model (DSM), and implicit large eddy simulation (ILES) in predicting various statistical quantities and instantaneous structures, and is particularly superior to traditional LES methods in predicting temperature fields and velocity divergence. Moreover, the computational efficiency of the FNO model is much higher than that of traditional LES methods. FNO models trained with short-time, low Reynolds number data exhibit a good generalization performance on longer-time predictions and higher Reynolds numbers in the \emph{a posteriori} tests.

physics.flu-dyn↗

arXiv2024

Quantum-Inspired Genetic Algorithm for Designing Planar Multilayer Photonic Structure

Quantum algorithms are emerging tools in the design of functional materials due to their powerful solution space search capability. How to balance the high price of quantum computing resources and the growing computing needs has become an urgent problem to be solved. We propose a novel optimization strategy based on an active learning scheme that combines the improved Quantum Genetic Algorithm (QGA) with machine learning surrogate model regression. Using Random Forests as the surrogate model circumvents the time-consuming physical modeling or experiments, thereby improving the optimization efficiency. QGA, a genetic algorithm embedded with quantum mechanics, combines the advantages of quantum computing and genetic algorithms, enabling faster and more robust convergence to the optimum. Using the design of planar multilayer photonic structures for transparent radiative cooling as a testbed, we show superiority of our algorithm over the classical genetic algorithm (CGA). Additionally, we show the precision advantage of the RF model as a flexible surrogate model, which relaxes the constraints on the type of surrogate model that can be used in other quantum computing optimization algorithms (e.g., quantum annealing needs Ising model as a surrogate).

quant-ph↗

arXiv2024

Superior Polymeric Gas Separation Membrane Designed by Explainable Graph Machine Learning

Gas separation using polymer membranes promises to dramatically drive down the energy, carbon, and water intensity of traditional thermally driven separation, but developing the membrane materials is challenging. Here, we demonstrate a novel graph machine learning (ML) strategy to guide the experimental discovery of synthesizable polymer membranes with performances simultaneously exceeding the empirical upper bounds in multiple industrially important gas separation tasks. Two predicted candidates are synthesized and experimentally validated to perform beyond the upper bounds for multiple gas pairs (O2/N2, H2/CH4, and H2/N2). Notably, the O2/N2 separation selectivity is 1.6-6.7 times higher than existing polymer membranes. The molecular origin of the high performance is revealed by combining the inherent interpretability of our ML model, experimental characterization, and molecule-level simulation. Our study presents a unique explainable ML-experiment combination to tackle challenging energy material design problems in general, and the discovered polymers are beneficial for industrial gas separation.

cond-mat.mtrl-sci↗

arXiv2024

Room-temperature Magnetic Thermal Switching by Suppressing Phonon-Magnon Scattering

Thermal switching materials, whose thermal conductivity can be controlled externally, show great potential in contemporary thermal management. Manipulating thermal transport properties through magnetic fields has been accomplished in materials that exhibit a high magnetoresistance. However, it is generally understood that the lattice thermal conductivity attributed to phonons is not significantly impacted by the magnetic fields. In this study, we experimentally demonstrate the significant impact of phonon-magnon scattering on the thermal conductivity of the rare-earth metal gadolinium near room temperature, which can be controlled by a magnetic field to realize thermal switching. Using first-principles lattice dynamics and spin-lattice dynamics simulations, we attribute the observed change in phononic thermal conductivity to field-suppressed phonon-magnon scattering. This research suggests that phonon-magnon scattering in ferromagnetic materials is crucial for determining their thermal conductivity, opening the door to innovative magnetic-field-controlled thermal switching materials.

cond-mat.mtrl-sci↗

arXiv2023

DiffHybrid-UQ: Uncertainty Quantification for Differentiable Hybrid Neural Modeling

The hybrid neural differentiable models mark a significant advancement in the field of scientific machine learning. These models, integrating numerical representations of known physics into deep neural networks, offer enhanced predictive capabilities and show great potential for data-driven modeling of complex physical systems. However, a critical and yet unaddressed challenge lies in the quantification of inherent uncertainties stemming from multiple sources. Addressing this gap, we introduce a novel method, DiffHybrid-UQ, for effective and efficient uncertainty propagation and estimation in hybrid neural differentiable models, leveraging the strengths of deep ensemble Bayesian learning and nonlinear transformations. Specifically, our approach effectively discerns and quantifies both aleatoric uncertainties, arising from data noise, and epistemic uncertainties, resulting from model-form discrepancies and data sparsity. This is achieved within a Bayesian model averaging framework, where aleatoric uncertainties are modeled through hybrid neural models. The unscented transformation plays a pivotal role in enabling the flow of these uncertainties through the nonlinear functions within the hybrid model. In contrast, epistemic uncertainties are estimated using an ensemble of stochastic gradient descent (SGD) trajectories. This approach offers a practical approximation to the posterior distribution of both the network parameters and the physical parameters. Notably, the DiffHybrid-UQ framework is designed for simplicity in implementation and high scalability, making it suitable for parallel computing environments. The merits of the proposed method have been demonstrated through problems governed by both ordinary and partial differentiable equations.

cs.LG↗

arXiv2023

Probabilistic Physics-integrated Neural Differentiable Modeling for Isothermal Chemical Vapor Infiltration Process

Chemical vapor infiltration (CVI) is a widely adopted manufacturing technique used in producing carbon-carbon and carbon-silicon carbide composites. These materials are especially valued in the aerospace and automotive industries for their robust strength and lightweight characteristics. The densification process during CVI critically influences the final performance, quality, and consistency of these composite materials. Experimentally optimizing the CVI processes is challenging due to long experimental time and large optimization space. To address these challenges, this work takes a modeling-centric approach. Due to the complexities and limited experimental data of the isothermal CVI densification process, we have developed a data-driven predictive model using the physics-integrated neural differentiable (PiNDiff) modeling framework. An uncertainty quantification feature has been embedded within the PiNDiff method, bolstering the model's reliability and robustness. Through comprehensive numerical experiments involving both synthetic and real-world manufacturing data, the proposed method showcases its capability in modeling densification during the CVI process. This research highlights the potential of the PiNDiff framework as an instrumental tool for advancing our understanding, simulation, and optimization of the CVI manufacturing process, particularly when faced with sparse data and an incomplete description of the underlying physics.

cs.LG↗

arXiv2023

Data-Centric Learning from Unlabeled Graphs with Diffusion Model

Graph property prediction tasks are important and numerous. While each task offers a small size of labeled examples, unlabeled graphs have been collected from various sources and at a large scale. A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks. However, the self-supervised task knowledge could not be aligned or sometimes conflicted with what the predictions needed. In this paper, we propose to extract the knowledge underlying the large set of unlabeled graphs as a specific set of useful data points to augment each property prediction model. We use a diffusion model to fully utilize the unlabeled graphs and design two new objectives to guide the model's denoising process with each task's labeled data to generate task-specific graph examples and their labels. Experiments demonstrate that our data-centric approach performs significantly better than fifteen existing various methods on fifteen tasks. The performance improvement brought by unlabeled data is visible as the generated labeled examples unlike the self-supervised learning.

cs.LG↗

arXiv2023

Semi-Supervised Graph Imbalanced Regression

Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph datasets are often small because labeling them requires expensive equipment and effort. To address the lack of examples of rare label values in graph regression tasks, we propose a semi-supervised framework to progressively balance training data and reduce model bias via self-training. The training data balance is achieved by (1) pseudo-labeling more graphs for under-represented labels with a novel regression confidence measurement and (2) augmenting graph examples in latent space for remaining rare labels after data balancing with pseudo-labels. The former is to identify quality examples from unlabeled data whose labels are confidently predicted and sample a subset of them with a reverse distribution from the imbalanced annotated data. The latter collaborates with the former to target a perfect balance using a novel label-anchored mixup algorithm. We perform experiments in seven regression tasks on graph datasets. Results demonstrate that the proposed framework significantly reduces the error of predicted graph properties, especially in under-represented label areas.

cs.LG↗

arXiv2023

Bubble Nucleation and Growth on Microstructure Surface under Microgravity

Understanding the nucleation and growth dynamics of the surface bubbles generated on a heated surface can benefit a wide range of modern technologies, such as the cooling systems of electronics, refrigeration cycles, nuclear reactors and metal industries, etc. Usually, these studies are conducted in the terrestrial environment. As space exploration and economy expanding at an unprecedented pace, the aforementioned applications that potentially deployable in space call for the understanding of thermal bubble phenomena in a microgravity setting. In this work, we investigate the nucleation and growth of surface bubble in space, where the gravity effect is negligible compared to the earth. We observe much faster bubble nucleation, and the growth rate can be ~30 times higher than that on the earth. Our finite element thermofluidic simulations show that the thermal convective flow due to gravity around the nucleation site is the key factor that effectively dissipates the heat from heating substrate to the bulk liquid and slows down the bubble nucleation and growth processes. Due to the microgravity field in space, the thermal convective flow is negligible compared to the terrestrial environment, leading to the localization of heat around the nucleation site, and thus enables faster bubble nucleation and growth in space. We also find that bubble nucleation can be influenced by the characteristic length of the microstructures on the heating surface. The microstructures behave as fins to enhance the cooling of the surface. With finer microstructures enabling more efficient surface to liquid heat transfer, the bubble nucleation takes longer.

physics.flu-dyn↗

arXiv2023

Bayesian Optimization of Metastable Nickel Formation During the Spontaneous Crystallization under Extreme Conditions

Spontaneous crystallization of metals under extreme conditions is a unique phenomenon occurring under far-from-equilibrium conditions that could enable the development of revolutionary and disruptive metastable metals with unusual properties. In this work, the formation of the hexagonal close-packed Nickel (hcp-Ni) metastable phase during spontaneous crystallization is studied using non-equilibrium molecular dynamics (MD) simulations, with the goal of maximizing the fraction of this metastable phase in the final state. We employ Bayesian Optimization (BO) with the Gaussian Processes (GP) regression as the surrogate model to maximize the hcp-Ni phase fraction, where temperature and pressure are control variables. MD simulations provide data for training the GP model, which is then used with BO to predict the next simulation condition. Such a BO-guided active learning leads to a maximum hcp-Ni fraction of 43.38% in the final crystalized phase within 40 iterations when a face-centered cubic (fcc) crystallite serves as the seed for crystallization from the amorphous phase. When an hcp seed is used, the maximum hcp-Ni fraction in the final crystal increases to 58.25% with 13 iterations. This study shows the promise of using BO to identify the process conditions that can maximize the rare phases. This method can also be generally applicable to process optimization to achieve target material properties.

cond-mat.mtrl-sci↗

arXiv2023

Tuning Optical Properties of Metamaterials by Mie Scattering for Efficient Sub-ambient Daytime Radiative Cooling

The management of the abundant eggshell biowaste produced worldwide has become a problematic issue due to the generated odor and microorganisms after directly disposing eggshell biowaste in landfills. Herein, we propose a novel method to convert the hazardous eggshell biowaste to valuable resources for energy management applications. Eggshell-based films are fabricated by embedding eggshell powders into polymer matrix to achieve highly efficient sub-ambient daytime radiative cooling. Benefiting from the Mie scattering of eggshell particles/air pores in the solar spectrum and strong emission of eggshell in the mid-infrared (mid-IR) range, the eggshell-based films present high reflection of 0.96 in the solar spectrum and high emission of 0.95 in the mid-IR range, resulting in significant average temperature drop of 5°C and 12°C below the ambient temperature during daytime and nighttime, respectively. Moreover, the eggshell-based films exhibit excellent flexibility and self-cleaning properties, which are beneficial for practical long-term outdoor applications. Our proposed design provides a novel means for an environmentally friendly and sustainable management of the eggshell biowaste.

physics.optics↗