Introducing a Hybrid Physics-Informed Neural Network and Finite Element Model for Predicting Structural Deformation Under Dynamic Load
DOI:
https://doi.org/10.63876/ijtm.v4i1.127Keywords:
Physics-Informed Neural Network (PINN), Finite Element Method (FEM), Structural Deformation, Dynamic Load Prediction, Hybrid Modeling, Real-Time SimulationAbstract
This study introduces a novel hybrid framework that integrates Physics-Informed Neural Networks (PINNs) with the Finite Element Method (FEM) to accurately predict structural deformation under dynamic loading conditions. While FEM remains a powerful tool in structural mechanics, its computational cost rises significantly with complex geometries and time-dependent simulations. To address this, the proposed hybrid model leverages the domain knowledge embedded in partial differential equations through PINNs, which are trained on both synthetic FEM data and governing physics laws. The model enables faster and more generalizable predictions of displacement fields by learning from limited simulation data while enforcing physical consistency. Numerical experiments on beam and plate structures subjected to varying dynamic loads demonstrate that the hybrid approach achieves high accuracy with substantially reduced computational effort compared to traditional FEM-only simulations. This work highlights the potential of combining data-driven and physics-based modeling to support real-time structural health monitoring and decision-making in engineering systems.
Downloads
References
H. Chen and L. Cai, “An elastoplastic energy model for predicting the deformation behaviors of various structural components,” Appl. Math. Model., vol. 68, pp. 405–421, Apr. 2019, doi: https://doi.org/10.1016/j.apm.2018.11.024.
R. Xu, L. Wang, X. Zhao, and Y. Mao, “Characterizing permeability-porosity relationships of porous rocks using a stress sensitivity model in consideration of elastic-structural deformation and tortuosity sensitivity,” J. Rock Mech. Geotech. Eng., vol. 16, no. 9, pp. 3437–3451, Sep. 2024, doi: https://doi.org/10.1016/j.jrmge.2024.01.020.
Y. Imayoshi, S. Ohsaki, H. Nakamura, and S. Watano, “Elucidation of the capping mechanism during the high-speed tableting process based on FEM simulation and fracture mechanics analysis,” J. Pharm. Sci., p. 103784, Apr. 2025, doi: https://doi.org/10.1016/j.xphs.2025.103784.
X.-H. Wu, Q. Zhang, W.-Q. Feng, Z.-Y. Yin, and H. Fang, “Enhanced THM coupling for anisotropic geomaterials and smoothed-FEM simulation,” Int. J. Mech. Sci., vol. 290, p. 110087, Mar. 2025, doi: https://doi.org/10.1016/j.ijmecsci.2025.110087.
T. Bai et al., “Tool wear analysis of high-speed sawing of aerospace aluminum alloy based on FEM simulation and cutting experiments,” J. Manuf. Process., vol. 139, pp. 193–209, Apr. 2025, doi: https://doi.org/10.1016/j.jmapro.2025.02.033.
A. Arora, B. M. Ward, and C. Oskay, “An implementation of the finite element method in hybrid classical/quantum computers,” Finite Elem. Anal. Des., vol. 248, p. 104354, Jun. 2025, doi: https://doi.org/10.1016/j.finel.2025.104354.
X. Liang, Y. Liu, S. Chen, X. Li, X. Jin, and Z. Du, “Physics-informed neural network for chiller plant optimal control with structure-type and trend-type prior knowledge,” Appl. Energy, vol. 390, p. 125857, Jul. 2025, doi: https://doi.org/10.1016/j.apenergy.2025.125857.
X.-C. Zhang, J.-G. Gong, and F.-Z. Xuan, “A physics-informed neural network for creep-fatigue life prediction of components at elevated temperatures,” Eng. Fract. Mech., vol. 258, p. 108130, Dec. 2021, doi: https://doi.org/10.1016/j.engfracmech.2021.108130.
Z. Li et al., “Latent neural PDE solver: A reduced-order modeling framework for partial differential equations,” J. Comput. Phys., vol. 524, p. 113705, Mar. 2025, doi: https://doi.org/10.1016/j.jcp.2024.113705.
M. Ali Aroon and M. A. Khansary, “Generalized similarity transformation method applied to partial differential equations (PDEs) in falling film mass transfer,” Comput. Chem. Eng., vol. 101, pp. 73–80, Jun. 2017, doi: https://doi.org/10.1016/j.compchemeng.2017.02.047.
R. Stephany and C. Earls, “PDE-READ: Human-readable partial differential equation discovery using deep learning,” Neural Networks, vol. 154, pp. 360–382, Oct. 2022, doi: https://doi.org/10.1016/j.neunet.2022.07.008.
“No Title”, doi: https://doi.org/10.1016/j.jaerosci.2021.105902.
C. Duan, J. Huang, Y. Jiao, X. Lu, and J. Z. Yang, “Current density impedance imaging with PINNs,” J. Comput. Appl. Math., vol. 452, p. 116120, Dec. 2024, doi: https://doi.org/10.1016/j.cam.2024.116120.
E. Vambolt, F. Gumpert, L. Lowe, E. Wilczok, L. Fromme, and J. Lohbreier, “Comparison of Fem and Pinn-Based Prediction of the Power Transmission of Ers With Small Data Sets,” in 2024 14th International Electric Drives Production Conference (EDPC), IEEE, Nov. 2024, pp. 1–8. doi: https://doi.org/10.1109/EDPC63771.2024.10932839.
J. Wen and R. Guo, “Deformation Prediction Method of Deep Foundation Pit Support Structure Based On GA-BP,” in 2021 7th International Conference on Hydraulic and Civil Engineering & Smart Water Conservancy and Intelligent Disaster Reduction Forum (ICHCE & SWIDR), IEEE, Nov. 2021, pp. 821–825. doi: https://doi.org/10.1109/ICHCESWIDR54323.2021.9656371.
X. Feng, “A priori error estimates for a coupled finite element method and mixed finite element method for a fluid-solid interaction problem,” IMA J. Numer. Anal., vol. 24, no. 4, pp. 671–698, Oct. 2004, doi: https://doi.org/10.1093/imanum/24.4.671.
X. Li, C. Pei, S. Xie, Z. Chen, T. Uchimoto, and T. Takagi, “A Stable FEM-BEM Hybrid Method for the Numerical Simulation of Magnetomechanical Coupled Problem With Both Inductive and Conductive Current Excitations Aiming to Application to Tokamak In-Vessel Structures,” IEEE Trans. Plasma Sci., vol. 48, no. 8, pp. 2902–2907, Aug. 2020, doi: https://doi.org/10.1109/TPS.2020.3005955.
F. Mahdavi, H. Zayyani, and R. Rajabi, “RSS Localization Using an Optimized Fusion of Two Deep Neural Networks,” IEEE Sensors Lett., vol. 5, no. 12, pp. 1–4, Dec. 2021, doi: https://doi.org/10.1109/LSENS.2021.3125911.
H. Li, “Computer network connection enhancement optimization algorithm based on convolutional neural network,” in 2021 International Conference on Networking, Communications and Information Technology (NetCIT), IEEE, Dec. 2021, pp. 281–284. doi: https://doi.org/10.1109/NetCIT54147.2021.00063.
P. Vogt, “The physical symbol grounding problem,” Cogn. Syst. Res., vol. 3, no. 3, pp. 429–457, Sep. 2002, doi: https://doi.org/10.1016/S1389-0417(02)00051-7.
R. Shenvi, “Physics-Informed Neural Networks for Approximating Loss Evolution of an Artificial Neural Network: Novel Approach to Implicit Regularization,” in 2024 IEEE MIT Undergraduate Research Technology Conference (URTC), IEEE, Oct. 2024, pp. 1–4. doi: https://doi.org/10.1109/URTC65039.2024.10937527.
C. Raissi and P. Poncelet, “Sampling for Sequential Pattern Mining: From Static Databases to Data Streams,” in Seventh IEEE International Conference on Data Mining (ICDM 2007), IEEE, Oct. 2007, pp. 631–636. doi: https://doi.org/10.1109/ICDM.2007.82.
K. Shukla, Z. Zou, C. H. Chan, A. Pandey, Z. Wang, and G. E. Karniadakis, “NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elements,” Comput. Methods Appl. Mech. Eng., vol. 433, p. 117498, Jan. 2025, doi: https://doi.org/10.1016/j.cma.2024.117498.
