Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios

Abstract

Recently, a class of machine learning methods called physics-informed neural networks (PINNs) has been proposed and gained prevalence in solving various scientific computing problems. This approach enables the solution of partial differential equations (PDEs) via embedding physical laws into the loss function. Many inverse problems can be tackled by simply combining the data from real life scenarios with existing PINN algorithms. In this paper, we present a multi-task learning method using uncertainty weighting to improve the training efficiency and accuracy of PINNs for inverse problems in linear elasticity and hyperelasticity. Furthermore, we demonstrate an application of PINNs to a practical inverse problem in structural analysis: prediction of external loads of diverse engineering structures based on limited displacement monitoring points. To this end, we first determine a simplified loading scenario at the offline stage. By setting unknown boundary conditions as learnable parameters, PINNs can predict the external loads with the support of measured data. When it comes to the online stage in real engineering projects, transfer learning is employed to fine-tune the pre-trained model from offline stage. Our results show that, even with noisy gappy data, satisfactory results can still be obtained from the PINN model due to the dual regularization of physics laws and prior knowledge, which exhibits better robustness compared to traditional analysis methods. Our approach is capable of bridging the gap between various structures with geometric scaling and under different loading scenarios, and the convergence of training is also greatly accelerated through not only the layer freezing but also the multi-task weight inheritance from pre-trained models, thus making it possible to be applied as surrogate models in actual engineering projects.

final version

References in corpus (6)

• Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems
• Efficient training of physics-informed neural networks via importance sampling
• Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
• Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training
• Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
• Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings

Cited by in corpus (16)

• Deep Learning in Deterministic Computational Mechanics
• Physics-informed radial basis network (PIRBN): A local approximating neural network for solving nonlinear PDEs
• Solving Forward and Inverse Problems of Contact Mechanics using Physics-Informed Neural Networks
• A multi-fidelity deep operator network (DeepONet) for fusing simulation and monitoring data: Application to real-time settlement prediction during tunnel construction
• In-Context Operator Learning with Data Prompts for Differential Equation Problems
• Learning thermoacoustic interactions in combustors using a physics-informed neural network
• Physics-Informed Holomorphic Neural Networks (PIHNNs): Solving Linear Elasticity Problems
• Neural network based approach for solving problems in plane wave duct acoustics
• From Mesh to Neural Nets: A Multi-Method Evaluation of Physics-Informed Neural Networks and Galerkin Finite Element Method for Solving Nonlinear Convection-Reaction-Diffusion Equations
• Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
• Finite Element Neural Network Interpolation. Part I: Interpretable and Adaptive Discretization for Solving PDEs
• Bridging Simulation and Experiment: A Self-Supervised Domain Adaptation Framework for Concrete Damage Classification
• Active learning with physics-informed neural networks for optimal sensor placement in deep tunneling through transversely isotropic elastic rocks
• Prediction of acoustic field in 1-D uniform duct with varying mean flow and temperature using neural networks
• Toward using explainable data-driven surrogate models for treating performance-based seismic design as an inverse engineering problem
• Transforming physics-informed machine learning to convex optimization