Data-driven damage assessment of reinforced concrete shear walls using visual features of damage

Mansourdehghan, Sina; Dolatshahi, Kiarash M.; Asjodi, Amir Hossein

doi:10.1016/j.jobe.2022.104509

Cited by 24 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From another point of view, concrete, the main construction material for most higher-scale applications, has been also a popular subject of AI research. A number of published papers has been focused on the construction of models to estimate the seismic peak drift ratio [ 158 , 159 ], the penetration depth into concrete blocks [ 160 ], the shear capacity of steel fiber-reinforced concrete beams, tracing fire response of concrete structures [ 161 ] or the seismic response through a fragility analysis [ 162 ], while others aim on the accurate description of remaining fatigue life [ 163 , 164 ] or bearing-type bolted connections’ shear resistance. One should note that, while the investigation of previously noted instances were conducted by modelling measurements, in several occasions [ 160 , 163 , 165 ] the generated equations outperformed conventional employed formulas.…”

Section: Application In Science and Technologymentioning

confidence: 99%

Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives

Angelis

Sofos

Karakasidis

2023

Arch Computat Methods Eng

View full text Add to dashboard Cite

Symbolic regression (SR) is a machine learning-based regression method based on genetic programming principles that integrates techniques and processes from heterogeneous scientific fields and is capable of providing analytical equations purely from data. This remarkable characteristic diminishes the need to incorporate prior knowledge about the investigated system. SR can spot profound and elucidate ambiguous relations that can be generalizable, applicable, explainable and span over most scientific, technological, economical, and social principles. In this review, current state of the art is documented, technical and physical characteristics of SR are presented, the available programming techniques are investigated, fields of application are explored, and future perspectives are discussed.

show abstract

Section: Application In Science and Technologymentioning

confidence: 99%

Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives

Angelis

Sofos

Karakasidis

2023

Arch Computat Methods Eng

View full text Add to dashboard Cite

show abstract

“…This method of dividing the databank into training and testing datasets is commonly used to develop and validate predictive models. 24,34,54,[92][93][94][95] 7.1 | Plan I: modeling by D 0 and aspect ratio…”

Section: Proposed Predictive Equationsmentioning

confidence: 99%

Machine vision‐based automated earthquake‐induced drift ratio quantification for reinforced concrete columns

Hamidia,

Jamshidian,

Afzali

et al. 2023

Structural Design Tall Build

View full text Add to dashboard Cite

SummaryThis paper presents a novel method for estimating the seismic peak interstory drift ratio (IDR) in reinforced concrete (RC) columns after an earthquake using surface crack image analysis. The quantitative representation of the complexity and irregularity of crack images in damaged RC columns is obtained through the consideration of the generalized fractal dimensions. The authors have compiled a comprehensive database consisting of 445 crack maps obtained from cyclic experiments conducted on 110 rectangular RC column specimens exhibiting double‐curvature deformation mode. This database is utilized by the authors to develop and validate the proposed procedure. The research database contains a wide range of structural and geometric features. Five closed‐form equations are developed with the objective of estimating the peak IDR experienced by the RC columns during a seismic event. The predictive equations are derived through the utilization of symbolic regression technique, with the input parameters varying according to the availability of columns characteristic parameters. Results reveal that generalized fractal dimensions, especially D−1, are strong vision‐based indicator of damage in RC columns having correlation coefficients with IDR ranging from 0.82 to 0.92 across the considered plans. The seismic peak IDR obtained through the empirical equations can serve as the input engineering demand parameter (EDP) in the seismic loss estimation frameworks. This allows for the determination of the probability of exceeding damage states for structural and nonstructural components of concrete buildings. Finally, the practical implementation of the methodology is examined by its application to an actual case of a damaged column during the Kermanshah earthquake of magnitude 7.3 that occurred in 2017.

show abstract

“…The predictive equations are developed using 80% of the images randomly selected as the training data, and the remaining 20% of the images are considered as the testing data consistent with the similar computer vision-based studies. 68,74 The values of drift ratios underlined in Table A1 show the images randomly selected for testing dataset. Figure 12 shows the peak drift observation against the prediction of the proposed equations for training and testing dataset at each scenario.…”

Section: Predictive Equationsmentioning

confidence: 99%

“…In this paper, a coevolutionary algorithm employed by Schmidt and Lipson 73 is implemented that consists of three populations to accelerate the procedure of finding the most fitting solution: problem solutions, fitness predictors, and fitness trainers. The predictive equations are developed using 80% of the images randomly selected as the training data, and the remaining 20% of the images are considered as the testing data consistent with the similar computer vision‐based studies 68,74 . The values of drift ratios underlined in Table A1 show the images randomly selected for testing dataset.…”

Section: Predictive Equationsmentioning

confidence: 99%

Post‐earthquake damage evaluation of non‐ductile RC moment frames using surface crack patterns

Hamidia

Ganjizadeh

2022

Structural Contr & Hlth

View full text Add to dashboard Cite

In this paper, a methodology is developed for seismic damage identification of non-ductile reinforced concrete moment frames using surface crack images. A comprehensive database comprising 264 surface crack patterns from quasistatic test results of 61 non-ductile beam-column joint specimens at various damage levels is collected. The database covers a broad range of structural and geometric properties. Multifractal dimensions of the column and joint regions of damaged beam-column subassembly images are obtained and used as the complexity and irregularity index of the surface crack patterns. Predictive equations are developed that estimate the peak drift ratio during an earthquake using the multifractal dimensions of surface crack patterns. Six scenarios are considered for obtaining the predictive equations. The developed empirical equations rely on the multifractal dimensions along with the structural properties of the non-ductile beam-column joint. The peak drift ratio estimated by the proposed methodology can finally be used as the input engineering demand parameter to the existing fragility curves in the literature to identify the probability of exceedance from damage states of non-ductile reinforced concrete moment frames.

show abstract

Data-driven damage assessment of reinforced concrete shear walls using visual features of damage

Cited by 24 publications

References 36 publications

Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives

Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives

Machine vision‐based automated earthquake‐induced drift ratio quantification for reinforced concrete columns

Post‐earthquake damage evaluation of non‐ductile RC moment frames using surface crack patterns

Contact Info

Product

Resources

About