Structural Mechanics

Follow this topic Ask about this topic

Structural mechanics studies how solids, beams, shells, lattices, and other structures deform, carry loads, vibrate, buckle, and fail, linking material behavior and geometry to safety and design. Work combines finite-element and variational methods with experiments, while reduced-order models, physics-informed networks, graph neural networks, and neural operators aim to predict stress fields and dynamic responses at lower cost. These approaches address nonlinear elasticity, composites, fracture and contact, crash behavior, architected materials, and inverse tasks such as identifying loads or defects; topology and reliability-based optimization use them to find designs under constraints and uncertainty. A central challenge is preserving physical consistency while generalizing to new geometries, meshes, materials, and loading histories, and validating predictions against high-fidelity simulations and experiments.

Latest papers

71 papers5 papers in the last four weeks, down 37% on the four weeks before. 0.0% of all new papers.

Symmetry-Reduced Physics-Informed Learning of Tensegrity Dynamics
Mar 18, 2026Jing Qin, Muhao ChenPhysics-Informed ML Structural Mechanics
Department of Mathematics, University of Kentucky, Lexington, KY · Department of Mechanical and Aerospace Engineering, University of Houston, TX
Data-driven model order reduction for structures with piecewise linear nonlinearity using dynamic mode decomposition
Mar 18, 2026Akira Saito, Masato TanakaReduced-Order Modeling Dynamical Systems
Department of Mechanical Engineering, Meiji University, Kawasaki, Kanagawa 214-8571, Japan. · Toyota Research Institute of North America Toyota Motor North America, Inc. Ann Arbor, Michigan, 48105, USA
Deep Learning-Based Metamodeling of Nonlinear Stochastic Dynamic Systems under Parametric and Predictive Uncertainty
Mar 12, 2026Haimiti Atila, Seymour M. J. SpenceNeural Surrogate Modeling Uncertainty Quantification
Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, MI 48109, USA
A neural operator for predicting vibration frequency response curves from limited data
Mar 10, 2026D. Bluedorn, A. Badawy, B. E. Saunders +2Neural Surrogate Modeling Neural Operators
Department of Mechanical and Aerospace Engineering, New Mexico State University, Las Cruces, NM 88003, USA. · Knight Foundation School of Computing and Information Science, Florida International University, Miami, FL 33199, USA. · Sandia National Laboratories, Albuquerque, NM 87123, USA.
A Dual-Graph Spatiotemporal GNN Surrogate for Nonlinear Response Prediction of Reinforced Concrete Beams under Four-Point Bending
Mar 7, 2026Zhaoyang Ren, Qilin LiNeural Surrogate Modeling Spatiotemporal GNNs
Discipline of Computing, School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Australia
Physics-Consistent Neural Networks for Learning Deformation and Director Fields in Microstructured Media with Loss-Based Validation Criteria
Mar 6, 2026Milad Shirani, Pete H. Gueldner, Murat Khidoyatov +2Structural Mechanics Materials Science
Department of Biomedical Engineering, Yale University, New Haven, CT, USA · Department of Mechanical Engineering, Yale University, New Haven, CT, USA
Constraint-Free Static Modeling of Continuum Parallel Robot
Mar 5, 2026Lingxiao Xun, Matyas Diezinger, Azad Artinian +2Robotics Structural Mechanics
Passive Phase-Oriented Impedance Shaping for Rapid Acceleration in Soft Robotic Swimmers
Mar 3, 2026Qimin Feng, Orion A. Roberts, Qiang ZhongRobot Locomotion Underwater Robotics
Department of Mechanical Engineering, Iowa State University, Ames, IA 50011, USA.
Deep Clustering based Boundary-Decoder Net for Inter and Intra Layer Stress Prediction of Heterogeneous Integrated IC Chip
Feb 25, 2026Kart Leong Lim, Ji LinNeural Surrogate Modeling Structural Mechanics
Institute of Microelectronics (IME), Agency for Science, Technology and Research (A*STAR), 2 Fusionopolis Way, Innovis #08-02, Singapore 138634, Republic of Singapore
GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer
Dec 23, 2025Corey Adams, Rishikesh Ranade, Ram Cherukuri +1Neural Surrogate Modeling Structural Mechanics
NVIDIA Corporation, Santa Clara, US
Physics-Informed Graph Neural Networks to Reconstruct Local Fields Considering Finite Strain Hyperelasticity
Jul 5, 2025Manuel Ricardo Guevara Garban, Yves Chemisky, Étienne Prulière +1Physics-Informed GNNs Structural Mechanics
Univ. Bordeaux, CNRS, Bordeaux INP, I2M, UMR 5295, Talence 33400 France · Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, Talence 33400 France · Arts et Metiers Institute of Technology, CNRS, Bordeaux INP, I2M, UMR 5295, Talence 33400 France

Mar 18, 2026J/K move · Enter open · S save

Symmetry-Reduced Physics-Informed Learning of Tensegrity Dynamics

Jing Qin, Muhao Chen

Department of Mathematics, University of Kentucky, Lexington, KY · Department of Mechanical and Aerospace Engineering, University of Houston, TX

Physics-Informed ML Structural Mechanics Multibody Dynamics

Open paper AskPDF arXiv

Tensegrity structures possess intrinsic geometric symmetries that govern their dynamic behavior. However, most existing physics-informed neural network (PINN) approaches for tensegrity dynamics do not explicitly exploit these symmetries, leading to high computational complexity and unstable optimization. In this work, we propose a symmetry-reduced physics-informed neural network (SymPINN) framework that embeds group-theory-based symmetry directly into both the solution expression and the neural network architecture to predict tensegrity dynamics. By decomposing nodes into symmetry orbits and representing free nodal coordinates using a symmetry basis, the proposed method constructs a reduced coordinate representation that preserves geometric symmetry of the structure. The full coordinates are then recovered via symmetry transformations of the reduced solution learned by the network, ensuring that the predicted configurations automatically satisfy the symmetry constraints. In this framework, equivariance is enforced through orbit-based coordinate generation, symmetry-consistent message passing, and physics residual constraints. In addition, SymPINN improves training effectiveness by encoding initial conditions as hard constraints, incorporating Fourier feature encoding to enhance the representation of dynamic motions, and employing a two-stage optimization strategy. Extensive numerical experiments on symmetric T-bars and lander structures demonstrate significantly improved prediction accuracy and computational efficiency compared to standard physics-informed models, indicating the great potential of symmetry-aware learning for structure-preserving modeling of tensegrity dynamics.