Latest Physics-Informed Neural Nets Research Papers
The newest Physics-Informed Neural Nets papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Physics-Informed Neural Nets so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest Physics-Informed Neural Nets papers in your inbox — free →Recent papers
- MCMC-PINNS: Adaptively Sampling Collocation Points of PINNs with an Improved Markov Chain Monte Carlo MethodTengchao Yu, Heng Yong, Li Liu, Han Wang et al. · East Asian Journal on Appli... · Sep 11, 2026
In recent years, physics-informed neural networks (PINNs) have emerged as an effective method for solving partial differential equations (PDEs). PINNs offer several advantages such as no limitation of dimensionality, low data requirements, …
- Research on a PINN-Based Predictive Model for the Dynamic Ablation Process of Insulation LayerZilong Wang, Yang Liu, Tao Cui, Xiaojing Yu et al. · Aerospace · Sep 10, 2026
Thermal protection is critical for solid rocket motor safety, yet ablation prediction of insulation layers remains a core challenge. To achieve rapid and accurate prediction, this study develops a Physics-Informed Neural Network (PINN) mode…
- A physics-informed neural networks-based kinematic formulation for limit analysisCanh V. Le · Computers & Structures · Sep 10, 2026
- PINN-based Oka reinforced modelling and prediction of erosion wear in Al-Mg-MoS₂ powder metallurgy compositesNarmada Ch, Rajesh S, Senthil Muthu Kumar Thiagamani · Next Materials · Sep 10, 2026
The solid-particle erosion is a crucial degrading mechanism in engineering components, although dependable predictions are challenging, especially when experimental data is limited. This analysis explores the erosion characteristics of Al–M…
- A Dual-Physics-Informed Neural Network with Incremental Learning for Corrosion Fatigue Crack Growth Prediction in Aluminum AlloysYongzhen Zhang, Xinyu Feng, Dongxu Zhang, Haitao Wang et al. · Metals · Sep 10, 2026
Aluminum alloys used in aircraft structures are susceptible to corrosion fatigue cracking under combined aggressive environments and cyclic loading, threatening structural integrity. Pure data-driven models often fail under distribution shi…
- Neural-network placement in physics-informed machine learning for mechanistic process-model repair: a case study in industrial coffee roastingMorgen Pronk, Brian Anthony · Scientific Reports · Sep 10, 2026
Abstract Mechanistic process models are central to industrial simulation and control, but their rollout accuracy often depends on run-specific initialization data that archival production telemetry cannot reliably provide. This gap can leav…
- A Physics-Informed Neural Network Approach to Numerical Solution of Partial Differential EquationsArshad Anmol · Zenodo (CERN European Organ... · Sep 9, 2026
Abstract Physics-informed neural networks (PINNs) have become a revolutionary computational paradigm that combines the power of data-driven learning with the laws of physics to solve forward and inverse problems of partial differential equa…
- Physics-Informed Digital Twins for Real-Time Health Monitoring Performance Prediction and Remaining Useful Life Assessment of Gas Turbines Foundations and Structural Support SystemsRansben Zac Addy, Aondoseer Abraham Atoo, Emmanuel Okechukwu Nwafor · Zenodo (CERN European Organ... · Sep 9, 2026
Gas turbines and their foundations and structural support systems operate as dynamically coupled thermo-mechanical assets whose degradation is governed by interacting aerodynamic, thermal, rotational, vibration, fatigue, settlement, stiffne…
- Physics-informed thermodynamical Hamiltonian hybrid modeling method for vibration prediction of electric spindlesXiaojian Liu, Xinyu Lu, Huishu Jia, Wei Zeng et al. · Journal of Intelligent Manu... · Sep 9, 2026
- AL-BO: Adaptive Loss-Weighted Probabilistic Physics-Informed Neural Networks for Bayesian OptimizationZhiqin Kuang, Jingyi Lu · Industrial & Engineering Ch... · Sep 9, 2026
Abstract Black-box optimization of expensive functions governed by physical laws remains challenging for standard Gaussian process (GP)-based Bayesian optimization (BO), which can become computationally demanding and does not naturally embe…
- A Hellinger–Reissner mixed physics-informed neural network for two-dimensional linear elasticityYimeng Kang, Guanghui Qing · Engineering Analysis with B... · Sep 9, 2026
- Physics-Informed Deep Learning for False Ventricular Tachycardia Alarm Reduction in the ICUAthanasios Papastathopoulos-Katsaros, Alexandra Stavrianidi, Zhandong Liu · arXiv · Sep 8, 2026
False ventricular tachycardia (VT) alarms are a leading contributor to alarm fatigue in intensive care units. We propose a deep learning framework combining a 1D SE-ResNet with ICU-realistic data augmentations and a physics-informed auxilia…
- Incorporating continuous dependence qualifies physics-informed neural networks for operator learningGuojie Li, Wuyue Yang, Liu Hong · Chaos Solitons & Fractals · Sep 7, 2026
- A new numerical method based on physics-informed neural networks for solving an optimal control problem governed by scale-invariant heat transfer equationMelissa Mansouri, Karim Benalia, Brahim Oukacha, Karim Beddek · Studia Universitatis Babes-... · Sep 7, 2026
In this paper, we propose a new numerical method based on physics-informed neural networks (PINNs) for solving a boundary optimal control problem governed by a scale-invariant one-dimensional heat transfer equation with two-point boundary c…
- Free vibration behavior of curved laminated composite and sandwich beams using hybridized physics-informed artificial neural network-support vector machine learning algorithmAshish, S Anbukumar · Sadhana · Sep 7, 2026
- PINN-based laser cladding morphology prediction for digital twin frameworkXiang Li, Jin Shi, Dong He, Xiaojun Liu et al. · Journal of Intelligent Manu... · Sep 6, 2026
- IA-PINNs: Integrated adaptive Physics-informed neural networks for solving partial differential equationsHaifeng Niu, Yingxin Chen, Yongjin Zhang, Lingling Zhou · Engineering Analysis with B... · Sep 6, 2026
- Thermal error modeling method of linear motor feed drive axis based on physics-informed neural networkChi Zhang, Geo-Ry Tang, Maolei Chen, Sitong Xiang · The International Journal o... · Sep 5, 2026
- A physics-informed neural network surrogate for multi-band reflection-loss prediction of carbon-fiber-reinforced polymer / Ti-6Al-4V ELI radar absorbing materials for UAV airframe integrationAbdullah Mevlüt Mutluel · Multiscale and Multidiscipl... · Sep 5, 2026
Abstract Radar absorbing materials (RAM) are critical for stealth performance of unmanned aerial vehicles (UAVs), but their design typically requires expensive parametric sweeps over frequency, incidence angle, and material thickness. This …
- Novel analysis of physics-informed neural networks for solving Cahn-Allen, FitzHugh-Nagumo and Fisher–KPP ModelsAzzh Saad Alshehry, Saima Noor, Humaira Yasmin, Rasool Shah · Scientific Reports · Sep 5, 2026
This paper presents a hybrid semi-analytical/deep-learning framework for nonlinear PDEs, combining the New Iterative Method (NIM) with Physics-Informed Neural Networks (PINNs). A truncated NIM series provides a closed-form baseline satisfyi…
- AI-driven Digital Twin Framework for Predictive Maintenance, Asset Integrity Management, and Energy Optimization in Smart Oil and Gas Industrial SystemsHenry Inkum, Chidiebere Anastacia Ezeh, Vanessa Grant, Urhiofe God'sfavour Oghenerabome et al. · Asian Journal of Advanced R... · Sep 5, 2026
Advances in AI, physics-informed modelling, and Digital Twin technologies offer the potential to enhance predictive maintenance, asset-integrity assessment, and energy management within oil and gas processing systems. However, these framewo…
- Flow field reconstruction and time series prediction of two-dimensional flow past a circular cylinder using MO-PINNYE Pengcheng, YE Chenhang, SHI Yao, He Yue et al. · Acta Physica Sinica · Sep 4, 2026
物理信息神经网络（Physics-Informed Neural Network，PINN）通过嵌入物理方程，在稀疏数据条件下实现流场精准重构，适用于流体问题求解。针对PINN在流场重构中存在物理量耦合干扰严重、优化效率低，时序预测能力不足的问题，本文提出一种基于多通道输出的物理信息神经网络模型（Multi-output PINN，MO-PINN）。MO-PINN模型在输出层为各类物理量搭建独立输出通道，并分别开展参数优化，有效实现多物理量解耦。流场输入数据经由共享特征层提取…
- Artificial-intelligence-driven garment simulation: Advances, challenges, and future perspectivesKeke Yang, Mengting Ye, Yuxing Zhang, Jie Zhou · Textile Research Journal · Sep 4, 2026
Finite-element simulation of garment represents a fundamental technology for digital design and virtual fitting; however, conventional methods are hindered by challenges such as complex modeling, difficulties in parameter acquisition, and l…
- Physics-Informed Wavelet Neural Network for Super-Resolution Imaging Based on Crossed Structured IlluminationXin Li, Xiang Chen, Xinyang Yu, Xianjie Liu et al. · Acta Physica Sinica · Sep 4, 2026
结构光照明显微技术(SIM)因其较低光毒性和明场成像特性被广泛应用于超分辨成像。然而，传统SIM通常需在每个方向上采集三幅相移图像，并依据准确相移量实现重建；同时，对于具有一定厚度的样品，离焦效应易引入重建伪影并降低对比度。为此，本文提出一种物理驱动的小波神经网络(PIWNN)用于实现基于交叉结构光照明的超分辨重建。交叉结构光照明允许两个方向的高频信息同时被编码进莫尔条纹中，提高数据获取的速度同时有效抑制不同照明条件下零级频谱对重建结果的影响，PIWNN将SIM成像物理模型与…
- Parameterized physics-informed neural-network modeling of radio-frequency capacitively coupled He and Ar discharges constrained by fluid equationsWU Tong, LI Jingyu, JIANG Senzhong, He Qian et al. · Acta Physica Sinica · Sep 4, 2026
随着人工智能的发展，神经网络在复杂物理系统中的建模、计算和推理能力受到广泛关注。在等离子体模拟领域，对于射频容性耦合等离子体（RF-CCP）这类具有强非线性和多场耦合的放电体系，基于神经网络与流体控制方程相结合的建模研究不足，特别是实现多压强、多射频电压条件下的快速时空场计算推理，尚处于空白。本文构建了用于一维射频容性耦合 He 和 Ar 放电流体模拟的参数化物理信息神经网络（P-PINN）。模型以时空坐标、气体压强 P 和射频电压幅值V0 为输入，并将流体方程组嵌入神经网络…
- Quantitative Prediction of Coal–Gangue Content Using Terahertz Time-Domain Spectroscopy and Physics-Informed Machine LearningZeping Liu, Lipeng Hu, Jianfei Xu, Yadong Yang et al. · Materials · Sep 4, 2026
Quantitative determination of gangue content is important for efficient coal use and intelligent coal–gangue separation. We combine transmission terahertz time-domain spectroscopy (THz-TDS), multidomain feature fusion, and machine learning …
- Physics-Informed and Data-Driven Forecasting of Chaotic Dynamics Across Lorenz and Rössler SystemsAbdul Karim, Marco Carratù, In Cheol Jeong · Mathematics · Sep 3, 2026
Reliable finite-horizon forecasting of chaotic dynamics is challenging because small approximation errors grow rapidly during recursive prediction. This study presents a controlled comparison of data-driven and physics-regularized forecasti…
- Physics-Informed Neural Networks: Generalization and Free Energy AnalysisSafa Mohamed Safa Mostafa · Zenodo (CERN European Organ... · Sep 3, 2026
- LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style UpdatesDmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026
Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…
- A physics-informed neural network framework for phase-change bioheat transfer in cryosurgeryYunjia Lei, Weidong Wang, Fuliang Luo · International Communication... · Sep 2, 2026