Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures

Abstract

This paper introduces an innovative physics-informed deep learning framework for metamodeling of nonlinear structural systems with scarce data. The basic concept is to incorporate physics knowledge (e.g., laws of physics, scientific principles) into deep long short-term memory (LSTM) networks, which boosts the learning within a feasible solution space. The physics constraints are embedded in the loss function to enforce the model training which can accurately capture latent system nonlinearity even with very limited available training datasets. Specifically for dynamic structures, physical laws of equation of motion, state dependency and hysteretic constitutive relationship are considered to construct the physics loss. In particular, two physics-informed multi-LSTM network architectures are proposed for structural metamodeling. The satisfactory performance of the proposed framework is successfully demonstrated through two illustrative examples (e.g., nonlinear structures subjected to ground motion excitation). It turns out that the embedded physics can alleviate overfitting issues, reduce the need of big training datasets, and improve the robustness of the trained model for more reliable prediction. As a result, the physics-informed deep learning paradigm outperforms classical non-physics-guided data-driven neural networks.

arXiv comment21 pages, 13 figures

References in corpus (6)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning

Cited by in corpus (25)

• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Deep Learning in Deterministic Computational Mechanics
• A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic
• Machine Learning on Neutron and X-Ray Scattering
• DynNet: Physics-based neural architecture design for linear and nonlinear structural response modeling and prediction
• A Novel Deep Neural Network Architecture for Real-Time Water Demand Forecasting
• Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
• Machine Learning Approach to Model Order Reduction of Nonlinear Systems via Autoencoder and LSTM Networks
• Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networks
• An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator
• ViscoelasticNet: A physics informed neural network framework for stress discovery and model selection
• Physics informed deep learning for computational elastodynamics without labeled data
• A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data using Unstructured Spatial Discretizations
• Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
• Physics-Informed Long Short-Term Memory for Forecasting and Reconstruction of Chaos
• Condition Assessment of Stay Cables through Enhanced Time Series Classification Using a Deep Learning Approach
• How machine learning can help the design and analysis of composite materials and structures?
• Physics-Informed Neural Networks for Solving Multiscale Mode-Resolved Phonon Boltzmann Transport Equation
• Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of Flows
• Incremental Bayesian tensor learning for structural monitoring data imputation and response forecasting
• On the Application of Data-Driven Deep Neural Networks in Linear and Nonlinear Structural Dynamics