Detection of fatigue cracking in steel bridge girders: A support vector machine approach

Hasni, Hassene; Alavi, Amir H.; Jiao, Pengcheng; Lajnef, Nizar

doi:10.1016/j.acme.2016.11.005

Cited by 70 publications

(33 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Figure b shows the output generated by the sensor in response to a mechanical loading. Based on previous studies, the sensor output can be characterized by a cumulative density function (CDF):

italicCD F_{Gaussian} ((), g) = \frac{α}{2} ([], 1 - erf ((), \frac{g - μ}{σ \sqrt{2}})),

in which μ, σ, α, and g refer to the mean of the strain distribution, standard deviation (STD) with respect to load and frequency, total cumulative time of the applied strain measured by the entire gates, and the gate number, respectively. The CDF is then transformed into a probability density function (PDF):

italicPDF ((), g) = \frac{1}{σ \sqrt{2 π}} e^{- \frac{{((), g - μ)}^{2}}{2 σ^{2}}} .

…”

Section: Operation Principle Of the Self‐powered Sensormentioning

confidence: 99%

“…In a recent study on a steel plate subjected to an in‐plane tension, Alavi et al found that the PDFs corresponding to the sensors at the crack tip shift to the left and expand due to damage progression. Hasni et al developed an intelligent approach for fatigue crack detection in steel girder bridges based on the interpretation of these PDFs. However, the previous studies are merely focused on damage detection.…”

Section: Operation Principle Of the Self‐powered Sensormentioning

confidence: 99%

“…This new sensing technology uses certain piezoelectric materials to harvest mechanical energy from structures under ambient vibrations. Comparing with classical SHM solutions, this sensor has relatively small size and low cost that allows the deployment a dense network of sensors near the damage sensitive areas . Furthermore, the number of studies focused on damage localization and quantification are notably lower compared with those on damage detection.…”

Section: Introductionmentioning

confidence: 99%

“…Comparing with classical SHM solutions, this sensor has relatively small size and low cost that allows the deployment a dense network of sensors near the damage sensitive areas. [36][37][38][39][40] Furthermore, the number of studies focused on damage localization and quantification are notably lower compared with those on damage detection.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Damage localization and quantification in gusset plates: A battery-free sensing approach

Hasni

Jiao

Lajnef

et al. 2018

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

Summary This study presents a numerical approach for damage localization and quantification in gusset plates using data provided by a battery‐free sensing technology. A series of 3D finite element simulations are conducted to obtain the response of a gusset plate with a geometrical structure similar to U10W gusset plate of the I‐35W Highway Bridge in Minneapolis, MN, USA. Crack propagation is simulated using the extended finite element method. A network of sensing nodes is placed on the surface of the plate to extract strain‐time history for different damage stages. Subsequently, probability density functions (PDFs) are defined to characterize the output of the self‐powered sensor. A crack localization and quantification approach is proposed based on fusion of the data from a network of sensors. Based on the results, damage can be precisely detected and localized through tracking relative shifts of PDFs over time. Moreover, features extracted from PDFs can be used to measure the crack size.

show abstract

“…Figure b shows the output generated by the sensor in response to a mechanical loading. Based on previous studies, the sensor output can be characterized by a cumulative density function (CDF):

italicCD F_{Gaussian} ((), g) = \frac{α}{2} ([], 1 - erf ((), \frac{g - μ}{σ \sqrt{2}})),

italicPDF ((), g) = \frac{1}{σ \sqrt{2 π}} e^{- \frac{{((), g - μ)}^{2}}{2 σ^{2}}} .

…”

Section: Operation Principle Of the Self‐powered Sensormentioning

confidence: 99%

Section: Operation Principle Of the Self‐powered Sensormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Damage localization and quantification in gusset plates: A battery-free sensing approach

Hasni

Jiao

Lajnef

et al. 2018

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

show abstract

“…The energy harvesting unit is of great importance as it provides the required electric power to the wireless sensor without the limitation of battery lifetime or wiring harness. [12][13][14][15] In addition, the electric signal from the harvester can be controlled to correspond to a specific strain/deformation. Therefore, the strain, the snap-through of the beam is triggered generating, then, an electric signal that can be used to sense the change in the structural response due to potential damage.…”

Section: Introductionmentioning

confidence: 99%

An energy harvesting and damage sensing solution based on postbuckling response of nonuniform cross‐section beams

Jiao

Borchani

Alavi

et al. 2017

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

SummaryPostbuckling response of elastic beams has been widely used in many systems to develop efficient energy harvesting and damage sensing mechanisms under quasistatic excitations. In particular, the snap-through behavior of bilaterally constrained beams can be used to transform low-frequency and low-rate excitations into high-rate motions. Using a piezoelectric energy harvester, these motions are converted into electric power. However, the efficiency of buckling-based energy harvesters highly depends on the postbuckling behavior of the buckled elements. Inadequate control over the beam's response critically impedes the application of the mechanism. This study aims to control the location of the snap-throughs and the spacing between the transitions in order to increase the levels of the harvested energy and tune the sensitivity of the sensor. As uniform prismatic beams do not allow for such control, nonprismatic cross-section beams are herein investigated.An energy-based theoretical model is developed in this study to investigate the effect of different shapes and geometries on the postbuckling response of nonuniform beams. The total potential energy of the system is minimized under constraints that represent the physical confinement between the lateral boundaries. Experimental results prove that the theoretical model is accurate and can be used to optimize the buckling elements. Results show that the spacing between the transitions can be tuned. Furthermore, an optimal buckling element can improve the energy conversion efficiency by more than 290%.

show abstract

A data‐driven bond‐based peridynamic model derived from group method of data handling neural network with genetic algorithm

Zhou

2022

Numerical Meth Engineering

View full text Add to dashboard Cite

In the governing equation of motion of bond‐based peridynamics, the acceleration of a material point can be considered as the response function of all the displacements of material points in the horizon and a micro stiffness containing Young's modulus and length scale. A group method of data handling (GMDH) neural network is first developed to explicitly derive the discrete bond‐based peridynamic equation of motion based on measured data in this study rather than traditional complicated mathematical derivation. In order to discover the optimal structure more efficiently and to avoid exhaustive search, genetic algorithm is incorporated into GMDH structure. It is found that the prediction results obtained by GMDH model agree well with measured values both for training and testing data. Moreover, the derived equation of motion is expressed as the product of parameter composed of Young's modulus and length scale and linear combination of displacements of material points in the horizon, which is in accordance with the original bond‐based peridynamic formulation. Furthermore, numerical benchmarks associated with elastic deformation and crack problems are performed and compared with analytical solution or finite element analysis result to verify the validity and feasibility of the proposed model.

show abstract

Detection of fatigue cracking in steel bridge girders: A support vector machine approach

Cited by 70 publications

References 31 publications

Damage localization and quantification in gusset plates: A battery-free sensing approach

Damage localization and quantification in gusset plates: A battery-free sensing approach

An energy harvesting and damage sensing solution based on postbuckling response of nonuniform cross‐section beams

A data‐driven bond‐based peridynamic model derived from group method of data handling neural network with genetic algorithm

Contact Info

Product

Resources

About