Multiple signal classification algorithm for non-destructive imaging of reinforcement bars and empty ducts in circular concrete columns

Agarwal, Krishna; Chen, Xudong; Pan, Li; Yeo, S.P.

doi:10.1109/ursigass.2011.6050841

Cited by 7 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The computer vision based methods use the feature extraction algorithm for the particular input, but it is much difficult to extract the high level features which is related to the damage location and its properties. In addition, the coders need to choose a suitable classification algorithm to get the output, which is a difficult task (Agarwal et al, 2011). Now a days these computer vision based methods are replaced with deep learning techniques because of its ability to deal with big data and to automate feature extraction steps.…”

Section: Introductionmentioning

confidence: 99%

Deep learning based thermal crack detection on structural concrete exposed to elevated temperature

Andrushia

Anand

Lublóy

et al. 2021

Advances in Structural Engineering

View full text Add to dashboard Cite

Health monitoring of concrete including, detecting defects such as cracking, spalling on fire affected concrete structures plays a vital role in the maintenance of reinforced cement concrete structures. However, this process mostly uses human inspection and relies on subjective knowledge of the inspectors. To overcome this limitation, a deep learning based automatic crack detection method is proposed. Deep learning is a vibrant strategy under computer vision field. The proposed method consists of U-Net architecture with an encoder and decoder framework. It performs pixel wise classification to detect the thermal cracks accurately. Binary Cross Entropy (BCA) based loss function is selected as the evaluation function. Trained U-Net is capable of detecting major thermal cracks and minor thermal cracks under various heating durations. The proposed, U-Net crack detection is a novel method which can be used to detect the thermal cracks developed on fire exposed concrete structures. The proposed method is compared with the other state-of-the-art methods and found to be accurate with 78.12% Intersection over Union (IoU).

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning based thermal crack detection on structural concrete exposed to elevated temperature

Andrushia

Anand

Lublóy

et al. 2021

Advances in Structural Engineering

View full text Add to dashboard Cite

show abstract

“…Recently, Bozza et al [21] developed no-sampling linear sampling method (nLSM) for electromagnetic fields in order to reconstruct cracks inside a slab, and Agarwal et al [22] applied Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/ndteint Multiple Signal Classification to detect reinforcement bars and empty ducts in circular columns.…”

Section: Introductionmentioning

confidence: 99%

Inhomogeneity reconstructions in tendon ducts via boundary integral equations

Yaman¹,

Weiland²

2014

NDT & E International

View full text Add to dashboard Cite

a b s t r a c tIn this study, as an alternative to the formerly presented investigations, Newton-type numerical algorithms are proposed to find location and shape of an air void inside of a tendon duct and to identify gathered metallic bars in a concrete column. The simulated structures are illuminated by four acoustic sources at a fixed frequency such that the scattered field is measured in a near-field region at 128 points. According to the nature of physical problems, the Dirichlet boundary condition is employed to model air-filled cavities and transmission conditions are assumed for metallic objects. Additionally, conductive boundary conditions are suggested for a more realistic representation of the inhomogeneities for the rusty metallic skin of the duct. Potential approaches are used to derive boundary integral equations. The proper treatment of the ill-conditioned equations is established via Tikhonov regularization. Applicability of the proposed inversion algorithms is tested with realistic parameters for different scenarios using noisy scattered field data and accurate numerical results are presented at 10 kHz for the unknown physical properties of the duct's skin.

show abstract

“…A strictly related problem can be met in civil-engineering applications, for example, to detect reinforcing bars within concrete pillars [1] or also in photonic bandgap devices where the absence of some elements leads to frequency-dependent scattering phenomena which are different from the expected behavior [2], [3].…”

Section: Introductionmentioning

confidence: 99%

MUSIC Algorithms for Grid Diagnostics

Solimene¹,

Leone²

2013

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

The problem of detecting and localizing missing scatterers (faults) inside a known grid of small cross-sectional perfect-electric-conducting cylinders is dealt with. The case of a TM scalar 2-D geometry is considered, and the Multiple Signal Classification (MUSIC) spectral estimation technique is employed. Two different scattering models are employed and compared. The first one aims at localizing present objects within a free-space background medium. The second one aims at detecting the faults and exploits the Green's function of the full grid. The limitations of the first approach are pointed out and connected to the maximum dimension of the data space. Then, the second approach performs successfully when the fault number is lower than scattering objects.

show abstract

Multiple signal classification algorithm for non-destructive imaging of reinforcement bars and empty ducts in circular concrete columns

Cited by 7 publications

References 12 publications

Deep learning based thermal crack detection on structural concrete exposed to elevated temperature

Deep learning based thermal crack detection on structural concrete exposed to elevated temperature

Inhomogeneity reconstructions in tendon ducts via boundary integral equations

MUSIC Algorithms for Grid Diagnostics

Contact Info

Product

Resources

About