Physics-informed neural network for ultrasound nondestructive quantification of surface breaking cracks

by   Khemraj Shukla, et al.

We introduce an optimized physics-informed neural network (PINN) trained to solve the problem of identifying and characterizing a surface breaking crack in a metal plate. PINNs are neural networks that can combine data and physics in the learning process by adding the residuals of a system of Partial Differential Equations to the loss function. Our PINN is supervised with realistic ultrasonic surface acoustic wave data acquired at a frequency of 5 MHz. The ultrasonic surface wave data is represented as a surface deformation on the top surface of a metal plate, measured by using the method of laser vibrometry. The PINN is physically informed by the acoustic wave equation and its convergence is sped up using adaptive activation functions. The adaptive activation function uses a scalable hyperparameter in the activation function, which is optimized to achieve best performance of the network as it changes dynamically the topology of the loss function involved in the optimization process. The usage of adaptive activation function significantly improves the convergence, notably observed in the current study. We use PINNs to estimate the speed of sound of the metal plate, which we do with an error of 1%, and then, by allowing the speed of sound to be space dependent, we identify and characterize the crack as the positions where the speed of sound has decreased. Our study also shows the effect of sub-sampling of the data on the sensitivity of sound speed estimates. More broadly, the resulting model shows a promising deep neural network model for ill-posed inverse problems.


page 3

page 6

page 10

page 11

page 12

page 13

page 14

page 19


Error Analysis of Physics-Informed Neural Networks for Approximating Dynamic PDEs of Second Order in Time

We consider the approximation of a class of dynamic partial differential...

Discovery of Physics and Characterization of Microstructure from Data with Bayesian Hidden Physics Models

There has been a surge in the interest of using machine learning techniq...

Locally adaptive activation functions with slope recovery term for deep and physics-informed neural networks

We propose two approaches of locally adaptive activation functions namel...

On the Pareto Front of Physics-Informed Neural Networks

Recently a new type of deep learning method has emerged, called physics-...

A Neural Network with Plane Wave Activation for Helmholtz Equation

This paper proposes a plane wave activation based neural network (PWNN) ...

A Helmholtz equation solver using unsupervised learning: Application to transcranial ultrasound

Transcranial ultrasound therapy is increasingly used for the non-invasiv...

Wave simulation in non-smooth media by PINN with quadratic neural network and PML condition

Frequency-domain simulation of seismic waves plays an important role in ...

Please sign up or login with your details

Forgot password? Click here to reset