Deep learning for full-field ultrasonic characterization

Abstract

This study takes advantage of recent advances in machine learning to establish a physics-based data analytic platform for distributed reconstruction of mechanical properties in layered components from full waveform data. In this vein, two logics, namely the direct inversion and physics-informed neural networks (PINNs), are explored. The direct inversion entails three steps: (i) spectral denoising and differentiation of the full-field data, (ii) building appropriate neural maps to approximate the profile of unknown physical and regularization parameters on their respective domains, and (iii) simultaneous training of the neural networks by minimizing the Tikhonov-regularized PDE loss using data from (i). PINNs furnish efficient surrogate models of complex systems with predictive capabilities via multitask learning where the field variables are modeled by neural maps endowed with (scaler or distributed) auxiliary parameters such as physical unknowns and loss function weights. PINNs are then trained by minimizing a measure of data misfit subject to the underlying physical laws as constraints. In this study, to facilitate learning from ultrasonic data, the PINNs loss adopts (a) wavenumber-dependent Sobolev norms to compute the data misfit, and (b) non-adaptive weights in a specific scaling framework to naturally balance the loss objectives by leveraging the form of PDEs germane to elastic-wave propagation. Both paradigms are examined via synthetic and laboratory test data. In the latter case, the reconstructions are performed at multiple frequencies and the results are verified by a set of complementary experiments highlighting the importance of verification and validation in data-driven modeling.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems
• Self-adaptive loss balanced Physics-informed neural networks for the incompressible Navier-Stokes equations
• Physics-informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions
• On the convergence of physics informed neural networks for linear second-order elliptic and parabolic type PDEs
• Physics informed neural networks for continuum micromechanics
• Solving the acoustic VTI wave equation using physics-informed neural networks
• A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
• Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism
• A physics-informed neural network for quantifying the microstructure properties of polycrystalline Nickel using ultrasound data
• A Dual-Dimer Method for Training Physics-Constrained Neural Networks with Minimax Architecture
• Learning hidden elasticity with deep neural networks
• Physics-informed neural networks for imaging and parameter retrieval of photonic nanostructures from near-field data
• Generalized linear sampling method for elastic-wave sensing of heterogeneous fractures
• Reconstruction of constitutive parameters in isotropic linear elasticity from noisy full-field measurements
• Poroelastic near-field inverse scattering

Cited by in corpus (1)

• Newton-Puiseux Analysis for Interpretability and Calibration of Complex-Valued Neural Networks