DYNAMIC DATA FUSION
ANALYSIS METHOD FOR
CRACK TRACKING IN
REINFORCED CONCRETE
BASED ON DIC AND AE
Dongwei Shang, Ziping Wang,
Jiazhen Zhang, Qingwei Xia, Rahim
Gorgin, and Nataša R. Trišović
Monitoring cracks within concrete structures allows
for the assessment of performance and load-
bearing capacity changes, enabling early preventa-
tive measures to enhance safety and durability. This
paper addresses the challenges of using acoustic
emission (AE) technology alone to monitor full-field
strain changes at crack locations by implementing
a dynamic data fusion method combining digital
image correlation (DIC) and AE technology. This
method leverages the noncontact monitoring
capabilities of DIC with the energy parameter
analysis and circular trajectory localization of AE to
achieve data fusion on the same specimen. The
method is applied during four-point bending tests
on reinforced concrete beams to track crack devel-
opment at various stages. The results demonstrate
significant improvements in the accuracy of concrete
crack detection, precise tracking of crack evolution,
and detailed data analysis of crack position and size
at different stages of development. This provides
effective experimental support and a theoretical
basis for the health monitoring and safety assurance
of reinforced concrete structures.
KEYWORDS: AE DIC dynamic data fusion
crack tracking
https://doi.org/10.1080/09349847.2025.2513266
SPARSE-DATA DEEP
LEARNING STRATEGIES
FOR RADIOGRAPHIC
NONDESTRUCTIVE TESTING
Jacqueline Alvarez, Keith Henderson,
Maurice B. Aufderheide, Brian Gallagher,
Roummel F. Marcia, and Ming Jiang
Radiography is an imaging technique used in a
variety of applications, such as medical diagnosis,
airport security, and nondestructive testing. We
present a deep learning system for extracting
information from radiographic images. We perform
various prediction tasks using our system, including
material classification and regression on the dimen-
sions of a given object that is being radiographed.
Our system is designed to address the sparse-data
issue for radiographic nondestructive testing appli-
cations. It uses a radiographic simulation tool for
synthetic data augmentation, and it uses transfer
learning with a pretrained convolutional neural
network model. Using this system, our preliminary
results indicate that the object geometry regression
task saw an improvement of 70% in the R-squared
value when using a multi-regime model. In addi-
tion, we increase the performance of the object
material classification tasks by utilizing data from
different imaging systems. In particular, using
neutron imaging improved the material classifi-
cation accuracy by 20% when compared to X-ray
imaging.
KEYWORDS: radiography nondestructive
testing deep learning convolutional neural
networks
https://doi.org/10.1080/09349847.2025.2519070
SCANNER
|
RNDEABSTRACTS
20
M AT E R I A L S E V A L U AT I O N • A U G U S T 2 0 2 5
ANALYSIS METHOD FOR
CRACK TRACKING IN
REINFORCED CONCRETE
BASED ON DIC AND AE
Dongwei Shang, Ziping Wang,
Jiazhen Zhang, Qingwei Xia, Rahim
Gorgin, and Nataša R. Trišović
Monitoring cracks within concrete structures allows
for the assessment of performance and load-
bearing capacity changes, enabling early preventa-
tive measures to enhance safety and durability. This
paper addresses the challenges of using acoustic
emission (AE) technology alone to monitor full-field
strain changes at crack locations by implementing
a dynamic data fusion method combining digital
image correlation (DIC) and AE technology. This
method leverages the noncontact monitoring
capabilities of DIC with the energy parameter
analysis and circular trajectory localization of AE to
achieve data fusion on the same specimen. The
method is applied during four-point bending tests
on reinforced concrete beams to track crack devel-
opment at various stages. The results demonstrate
significant improvements in the accuracy of concrete
crack detection, precise tracking of crack evolution,
and detailed data analysis of crack position and size
at different stages of development. This provides
effective experimental support and a theoretical
basis for the health monitoring and safety assurance
of reinforced concrete structures.
KEYWORDS: AE DIC dynamic data fusion
crack tracking
https://doi.org/10.1080/09349847.2025.2513266
SPARSE-DATA DEEP
LEARNING STRATEGIES
FOR RADIOGRAPHIC
NONDESTRUCTIVE TESTING
Jacqueline Alvarez, Keith Henderson,
Maurice B. Aufderheide, Brian Gallagher,
Roummel F. Marcia, and Ming Jiang
Radiography is an imaging technique used in a
variety of applications, such as medical diagnosis,
airport security, and nondestructive testing. We
present a deep learning system for extracting
information from radiographic images. We perform
various prediction tasks using our system, including
material classification and regression on the dimen-
sions of a given object that is being radiographed.
Our system is designed to address the sparse-data
issue for radiographic nondestructive testing appli-
cations. It uses a radiographic simulation tool for
synthetic data augmentation, and it uses transfer
learning with a pretrained convolutional neural
network model. Using this system, our preliminary
results indicate that the object geometry regression
task saw an improvement of 70% in the R-squared
value when using a multi-regime model. In addi-
tion, we increase the performance of the object
material classification tasks by utilizing data from
different imaging systems. In particular, using
neutron imaging improved the material classifi-
cation accuracy by 20% when compared to X-ray
imaging.
KEYWORDS: radiography nondestructive
testing deep learning convolutional neural
networks
https://doi.org/10.1080/09349847.2025.2519070
SCANNER
|
RNDEABSTRACTS
20
M AT E R I A L S E V A L U AT I O N • A U G U S T 2 0 2 5
