Structural identification with physics-informed neural ordinary differential equations

2021/05/10 by Zhilu Lai, Charilaos Mylonas, Satish Nagarajaiah +1 · 212 citations
Engineering · Mathematics · Physics and Astronomy · #Algorithm #Applied mathematics #Artificial intelligence #Artificial neural network #Computer science #Curse of dimensionality #Data modeling #Differential equation #Dynamical systems theory #Hydraulic and Pneumatic Systems #Identification (biology) #Machine learning #Mathematical analysis #Mathematics #Model Reduction and Neural Networks #Nonlinear system #Nonlinear system identification #Ode #Ordinary differential equation #Physics #Representation (politics) #Structural Health Monitoring Techniques #System dynamics #System identification

paper · open access · doi:10.1016/j.jsv.2021.116196

published in Journal of Sound and Vibration 508, 116196 (Elsevier BV)

openalex publication_date 2021/05/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Citations

• Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks
• Neural network-based seismic response prediction model for building structures using artificial earthquakes

Cited by

• KAN-ODEs: Kolmogorov–Arnold network ordinary differential equations for learning dynamical systems and hidden physics
• Learning thermodynamic master equations for open quantum systems
• Forecasting N-Body Dynamics: A Comparative Study of Neural Ordinary Differential Equations and Universal Differential Equations
• Control-Oriented System Identification: Classical, Learning, and Physics-Informed Approaches
• Spectrum and Physics-Informed Neural Networks (SaPINNs) for Input-State-Parameter Estimation in Dynamic Systems Subjected to Natural Hazards-Induced Excitation
• Deep recurrent-convolutional neural network learning and physics Kalman filtering comparison in dynamic load identification
• MATLAB Implementation of Physics Informed Deep Neural Networks for Forward and Inverse Structural Vibration Problems
• Physics-constrained neural ordinary differential equation models to discover and predict microbial community dynamics
• Experimental validation of universal filtering and smoothing for linear system identification using adaptive tuning
• Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next
• Structured Kolmogorov-Arnold Neural ODEs for Interpretable Learning and Symbolic Discovery of Nonlinear Dynamics
• Data-Driven Theory-guided Learning of Partial Differential Equations using SimultaNeous Basis Function Approximation and Parameter Estimation (SNAPE)
• Transforming physics-informed machine learning to convex optimization
• Node Assigned physics-informed neural networks for thermal-hydraulic system simulation: CVH/FL module
• Data-driven nonlinear model reduction to spectral submanifolds in mechanical systems. [europepmc]
• Symplectic encoders for physics-constrained variational dynamics inference. [europepmc]
• Physics-informed neural network with transfer learning (TL-PINN) based on domain similarity measure for prediction of nuclear reactor transients. [europepmc]
• h-Analysis and data-parallel physics-informed neural networks. [europepmc]
• A hybrid neural ordinary differential equation model of the cardiovascular system. [europepmc]
• A novel hybrid framework for efficient higher order ODE solvers using neural networks and block methods. [europepmc]
• Addressing model discrepancy in a clinical model of the oxygen dissociation curve. [europepmc]
• Physics-informed neural networks for physiological signal processing and modeling: a narrative review. [europepmc]
• Universal differential equations as a unifying modeling language for neuroscience. [europepmc]