This paper presents a deep learning-based concrete crack detection technique using hybrid images. The hybrid images combining vision and infrared (IR) thermography images are able to improve crack detectability while minimizing false alarms. Large scale concrete-made infrastructures such as bridge, dam, and etc. can be effectively inspected by spatially scanning the hybrid imaging system including vision camera, IR camera and continuous-wave line laser. However, the decision-making for the crack identification often requires experts’ intervention. As a target concrete structure gets larger, automated decision-making becomes more necessary in the practical point of view. The proposed technique is able to achieve automated crack identification by modifying a well-trained convolutional neural network using a set of crack images as a training image set, while retaining the advantages of hybrid images. The proposed technique is experimentally validated using a lab-scale concrete specimen developed with various-size cracks. The test results reveal that macro- and micro-cracks are automatically detected with minimizing false-alarms.
This paper proposes a new nonlinear ultrasonic technique for fatigue crack detection using a single piezoelectric transducer (PZT). The proposed technique identifies a fatigue crack using linear (α) and nonlinear (β) parameters obtained from only a single PZT mounted on a target structure. Based on the different physical characteristics of α and β, a fatigue crack-induced feature is able to be effectively isolated from the inherent nonlinearity of a target structure and data acquisition system. The proposed technique requires much simpler test setup and less processing costs than the existing nonlinear ultrasonic techniques, but fast and powerful. To validate the proposed technique, a real fatigue crack is created in an aluminum plate, and then false positive and negative tests are carried out under varying temperature conditions. The experimental results reveal that the fatigue crack is successfully detected, and no positive false alarm is
indicated.
This paper presents a noncontact laser lock-in thermography (LLT) technique for surface-breaking fatigue crack detection. LLT utilizes a modulated continuous wave (CW) laser as a heat source for lock-in thermography instead of commonly used flash and halogen lamps. LLT has following merits compared to conventional active thermography techniques: (1) the laser heat source can be precisely positioned at a long distance from a target structure thank to its directionality and low energy loss, (2) a large target structure can be inspected using a scanning laser heat source, (3) no special surface treatment is necessary to measure thermal wavefields and (4) background noises reflected from arbitrary surrounding heat sources can be eliminated. The LLT system is developed by integrating and synchronizing a modulated CW laser, galvanometer and infrared camera. Then, a holder exponent filter is proposed for crack identification, localization and quantification. Test results confirm that a surface-breaking fatigue crack on a steel plate is successfully evaluated using the proposed technique without any special surface treatment.
Electro-mechanical impedances and guided waves have been widely studied for detecting localized structural damages
due to their sensitivity to small structural changes. In this paper, an integrated impedance and guided wave (IIG) based
monitoring system is developed to improve the detectability of various damage types under varying temperature. First, a
hardware system, called the IIG system, was designed to achieve simultaneous measurements of electro-mechanical
impedance and guided wave signals. Then, the effects of temperature on guided waves and electro-mechanical
impedances were compensated using the passive imaginary part of the impedance signal. Finally, an automated damage
classification algorithm which incorporates temperature compensation was developed. To validate the proposed
algorithm, experimental investigations were performed for the detection of bolt loosening and crack in metallic structures
subjected to the temperature varying condition, in the range of -20 to 70°C.
Guided wave-based structural health monitoring (SHM) techniques have been widely studied by many
researchers. Recently, a new damage detection technique without comparison with baseline data is developed by
the author's group. Since the baseline-free technique does not require the baseline data obtained from the
healthy condition of a structure, this technique may reduce false alarms due to operational and environmental
variations of the structure. However, the previously developed technique requires the placements of two pairs of
collocated lead zirconate titanate transducers (PZTs), and each pair of PZTs should be properly collocated and
identical. These constraints make the previous technique susceptible to varying PZT conditions, and they cannot
be applied to structures such as pipelines and aircrafts where access to both surfaces of the structures is limited.
In this study, a new PZT called dual-PZT is designed so that the limitations of the previous baseline-free
technique can be overcome. To validate the applicability and robustness against undesirable variations in the
system, experimental studies with an aluminum plate subjected to varying temperature as well as loading
conditions are performed. Furthermore, the proposed baseline-free technique is applied to a decommissioned
bridge (Ramp-G Bridge in Korea) to verify the feasibility of the proposed techniques in a real bridge structure.
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.