Physics-Informed Neural Network for Ultrasound Nondestructive Quantification of Surface Breaking Cracks

By Khemraj Shukla, Patricio Clark Di Leoni, James L. Blackshire, Daniel Sparkman, G. Em Karniadakis. 2020

292 citations recorded by the source corpus.

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 PINNs 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 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 trainable hyperparameter, which is optimized to achieve the best performance of the network. The adaptive activation function changes dynamically, involved in the optimization process. The usage of the adaptive activation function significantly improves the convergence, evidently 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.

Subfields: Mechanical Engineering, Mechanics of Materials, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Mechanical Engineering

1. G. Em Karniadakis
2. Ameya Dilip Jagtap
3. Majid Rasht-Behesht
4. C. Huber
5. Khemraj Shukla
6. Zhiping Mao

In Mechanics of Materials

1. Ameya Dilip Jagtap
2. G. Em Karniadakis
3. Majid Rasht-Behesht
4. C. Huber
5. Khemraj Shukla

In Statistical and Nonlinear Physics

1. G. Em Karniadakis
2. Ameya Dilip Jagtap
3. Khemraj Shukla
4. Majid Rasht-Behesht
5. C. Huber
6. Zhiping Mao
7. Maizar Raissi
8. Shengze Cai

Citations in the corpus

• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method (2021, unknown): “Interesting applications include quantification of cardiovascular flows from visualization or sensor data [31–33], metamaterials design [34], and nondestructive quantification of cracks [35].”
• Physics‐Informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions (2021, methodology): “Shukla et al., 2020 & 2021 used PINNs for a nondestructive quantification of surface cracks and identification of microstructural properties of polycrystalline Nickle using ultrasound data.”
• Parallel Physics-Informed Neural Networks via Domain Decomposition (2021, background): “Due to their simplicity, PINNs have led to progress in many areas of computational science, see for examples [7, 8, 9, 10, 11, 12, 13, 14, 15].”
• Extended Physics-informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition based Deep Learning Framework for Nonlinear Partial Differential Equations (2020, methodology): “The PINNs has been applied extensively to solve various PDEs, see (10; 5) for more details.”