Title:
Concrete Characterization Using Ultrasound and Physics-Informed Neural Networks
Author(s):
Sangmin Lee
Publication:
Web Session
Volume:
ws_S23_SangminLee.pdf
Issue:
Appears on pages(s):
Keywords:
DOI:
Date:
4/2/2023
Abstract:
There is a need for reliable and universal nondestructive test methods that can be applied to characterize structural members in situ in a rapid and efficient manner. However, large amounts of data are normally needed and construction materials are challenging because of their inhomogeneity. Advances in machine learning (ML) have helped to solve many problems that rely on large data sets. More recently, physics-informed neural networks (PINN) have appeared and they can overcome traditional problems of conventional ML methods. PINN is a particular form of artificial neural networks (ANN) and portend notable advantages over purely data-driven approaches, where physics-based equations are embedded within an ANN structure. Here, we explore the potential of in-place concrete characterization using physics-informed neural networks (PINN) and ultrasonic wave data. Ultrasonic wave data is obtained from experiments on long rod-shaped steel and mortar samples and from numerically simulated slabs having defects.