Traditional physical model-based nondestructive evaluation (NDE) and damage detection methods are often unreliable due to the complex dependence of model parameters on minor differences in material properties (e.g., thickness, temperature, or loading effects). While classic data-driven approaches appear to eliminate model complexity, their performance highly depends on feature extraction, for which domain-expertise-based data preprocessing is required. Wavefield analysis is a promising alternative for non-contact NDE but suffers from the problem of slow data acquisition. As a result, effective structural health monitoring (SHM) based on wavefield analysis of guided waves in large-scale systems, such as mechanical, civil, or aerospace structures, has remained challenging. To address these challenges, we present a deep convolutional neural network (DCNN)-based transfer learning approach to interpret ultrasonic guided waves with small training data sets, thereby achieving rapid, effective, and automated SHM. Specifically, the proposed learning framework includes a pre-trained DCNN for automated feature extraction from the raw inputs (i.e., wavelet-transformed time-frequency images) and a fully connected classification stage that is trained with partial wavefield scans. Experiments on full wavefield scans of various thin metal plates demonstrate the effectiveness and efficiency of the proposed approach: >95% classification accuracy is obtained with only 5% training data, thus enabling fast scanning and fully automated damage detection of large-scale structures.
KEYWORDS: Associative arrays, Waveguides, Structural health monitoring, Wave propagation, Wave plates, Compressed sensing, Numerical modeling, Data modeling, Data analysis, Aluminum, Modeling and simulation, Structural health monitoring, Computer simulations, Numerical simulations, Systems modeling, Chemical species
Modeling and simulating guided wave propagation in complex, geometric structures is a topic of significant interest in structural health monitoring. These models have the potential to benefit damage detection, localization, and characterization in structures where traditional algorithms fail. Numerical modelling (for example, using finite element or semi-analytical finite element methods) is a popular approach for simulating complex wave behavior. Yet, using these models to improve experimental data analysis remains difficult. Numerical simulations and experimental data rarely match due to uncertainty in the properties of the structures and the guided waves traveling within them. As a result, there is a significant need to reduce this uncertainty by incorporating experimental data into the models. In this paper, we present a dictionary learning framework to address this challenge. Specifically, use dictionary learning to combine numerical wavefield simulations with 24 simulated guided wave measurements with different frequency-dependent velocity characteristics (emulating an experimental system) to make accurate, global predictions about experimental wave behavior. From just 24 measurements, we show that we can predict and extrapolate guided wave behavior with accuracies greater than 92%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.