Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

On the Generalizability of Time-of-Flight Convolutional Neural Networks for Noninvasive Acoustic Measurements

Journal Article · · Sensors
DOI:https://doi.org/10.3390/s24113580· OSTI ID:2433939
 [1];  [1];  [1];  [1]
  1. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
+ Show Author Affiliations
Bulk wave acoustic time-of-flight (ToF) measurements in pipes and closed containers can be hindered by guided waves with similar arrival times propagating in the container wall, especially when a low excitation frequency is used to mitigate sound attenuation from the material. Convolutional neural networks (CNNs) have emerged as a new paradigm for obtaining accurate ToF in non-destructive evaluation (NDE) and have been demonstrated for such complicated conditions. However, the generalizability of ToF-CNNs has not been investigated. In this work, we analyze the generalizability of the ToF-CNN for broader applications, given limited training data. We first investigate the CNN performance with respect to training dataset size and different training data and test data parameters (container dimensions and material properties). Furthermore, we perform a series of tests to understand the distribution of data parameters that need to be incorporated in training for enhanced model generalizability. This is investigated by training the model on a set of small- and large-container datasets regardless of the test data. We observe that the quantity of data partitioned for training must be of a good representation of the entire sets and sufficient to span through the input space. The result of the network also shows that the learning model with the training data on small containers delivers a sufficiently stable result on different feature interactions compared to the learning model with the training data on large containers. To check the robustness of the model, we tested the trained model to predict the ToF of different sound speed mediums, which shows excellent accuracy. Furthermore, to mimic real experimental scenarios, data are augmented by adding noise. We envision that the proposed approach will extend the applications of CNNs for ToF prediction in a broader range.
Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE Laboratory Directed Research and Development (LDRD) Program
Grant/Contract Number:
89233218CNA000001
OSTI ID:
2433939
Report Number(s):
LA-UR--24-24411
Journal Information:
Sensors, Journal Name: Sensors Journal Issue: 11 Vol. 24; ISSN 1424-8220
Publisher:
MDPI AGCopyright Statement
Country of Publication:
United States
Language:
English

References (21)

DOA estimation based on CNN for underwater acoustic array journal January 2021
Impact of dataset size and convolutional neural network architecture on transfer learning for carbonate rock classification journal February 2023
In Situ Monitoring of Chemical Reactions at a Solid–Water Interface by Femtosecond Acoustics journal October 2017
P Wave Arrival Picking and First-Motion Polarity Determination With Deep Learning journal June 2018
Automatic Waveform Classification and Arrival Picking Based on Convolutional Neural Network journal July 2019
Ultrasonic signal denoising based on autoencoder journal April 2020
CNN-based image analysis for malaria diagnosis conference December 2016
The Effect of Dataset Size on Training Tweet Sentiment Classifiers conference December 2015
How Does the Data set Affect CNN-based Image Classification Performance? conference November 2018
The Role of Activation Function in CNN conference December 2020
Noninvasive Acoustic Measurements in Cylindrical Shell Containers journal June 2021
Non intrusive measurements of the acoustic pressure and velocity fluctuations of fluids flowing in pipes conference January 1994
Machine learning in acoustics: Theory and applications journal November 2019
Convolutional neural network for earthquake detection and location journal February 2018
Performance of Firth-and logF-type penalized methods in risk prediction for small or sparse binary data journal February 2017
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions journal March 2021
A guide to the limits of resolution imposed by scattering in ray tomography journal February 1991
Generalized Seismic Phase Detection with Deep Learning journal August 2018
Pairwise Association of Seismic Arrivals with Convolutional Neural Networks journal January 2019
Impact of Dataset Size on Classification Performance: An Empirical Evaluation in the Medical Domain journal January 2021
A Comparison of Pooling Methods for Convolutional Neural Networks journal August 2022

Figures / Tables (11)

Figure 1(p. 5)figure Figure 1
Figure 2(p. 6)figure Figure 2
Table 1(p. 6)table Table 1
Figure 3(p. 7)figure Figure 3
Figure 4(p. 8)figure Figure 4
Figure 5(p. 9)figure Figure 5
Figure 6(p. 10)figure Figure 6
Figure 7(p. 11)figure Figure 7
Figure 8(p. 12)figure Figure 8
Figure 9(p. 13)figure Figure 9
Figure 10(p. 14)figure Figure 10

Similar Records

ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction
Conference · Thu Dec 07 23:00:00 EST 2017 · OSTI ID:1415704
Predicting Local Material Thickness from Steady-State Ultrasonic Wavefield Measurements Using a Convolutional Neural Network
Journal Article · Sun Jan 16 19:00:00 EST 2022 · Ultrasonics · OSTI ID:1841932
Noninvasive acoustic time-of-flight measurements in heated, hermetically-sealed high explosives using a convolutional neural network
Journal Article · Mon Aug 01 20:00:00 EDT 2022 · Machine Learning with Applications · OSTI ID:1881818

Related Subjects

47 OTHER INSTRUMENTATION
CNN-ToF
Convolutional neural networks
Time-of-Flight
generalizability