Machine learning-based seismic damage assessment of non-ductile RC beam-column joints using visual damage indices of surface crack patterns

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

doi:10.1016/j.istruc.2022.09.010

Cited by 23 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The values in the fourth and sixth columns of Table 3 are calculated by multiplying the sensitivity value with the positive or negative percentage. Noteworthy to mention that previous studies have widely incorporated symbolic regression method 24,28,34,[39][40][41][42][43][44]86,96 or machine learningbased models 45,46,92,94,95 for correlating the image-derived parameters to the level of damage in the structural components. The machine learning-based models are conventionally used when very complex relationship exists between the predictors.…”

Section: Plan Iii: Modeling By Two Gfds and Aspect Ratiomentioning

confidence: 99%

See 1 more Smart Citation

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

Hamidia,

Jamshidian,

Afzali

et al. 2023

Structural Design Tall Build

Self Cite

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

Section: Plan Iii: Modeling By Two Gfds and Aspect Ratiomentioning

confidence: 99%

“…GFDs have been also incorporated for the estimation of residual stiffness, 39,43 and strength 44 in RC columns. Furthermore, Hamidia et al 45 introduced a methodology based on machine learning techniques for evaluating damage in non-ductile RCMF joints. This methodology utilizes visual damage indices such as cracking length and crushing density.…”

mentioning

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…The fractal dimension, has been also employed by Hamidia and Gangizadeh for loss measurement 57 and residual stiffness estimation 58 of seismically damaged nonductile RCMFs. Also, Hamidia et al 59,60 employed machine learning regression models for the loss estimation of RCMFs based on information on cracking length and crushing density. All those studies have used a databank of beam-column joints where the damage is localized in the beam and joints and not in the columns.…”

Section: Introductionmentioning

confidence: 99%

Post‐earthquake stiffness loss estimation for reinforced concrete columns using fractal analysis of crack patterns

Hamidia

Afzali

Jamshidian

et al. 2023

Structural Concrete

Self Cite

View full text Add to dashboard Cite

The seismic damage to reinforced concrete (RC) components is conventionally quantified through various damage indices. In this paper, an image‐based procedure is developed for post‐earthquake residual stiffness quantification of RC columns. The proposed scenario‐based methodology is built upon the multifractal indices of the surface crack maps of the seismically damaged RC columns as the complexity measure for the images. An extensive databank from experiments on RC column specimens with a broad range of structural characteristics are collected and employed for generation and validation of the proposed procedure. Based on the availability of the structural information, five closed‐form regression‐aided equations are offered for estimating the stiffness loss in seismically damaged RC columns using predicting parameters among fractal indices, concrete strength, and the aspect ratio of the column. Results reveal that multifractal dimensions of crack maps are largely correlated with the stiffness degradation in RC columns. A sample specimen at various stiffness‐based damage indices is also presented as a case study to evaluate the predicted versus measured damage indices. The updated stiffness values acquired by the proposed equations can be utilized for stability evaluation, system identification, or further analysis of the seismically damaged RC buildings following an earthquake.

show abstract

“…This finding was later advanced by Mansourdehghan et al 20 to predict the performance level, peak drift ratio, and stiffness deterioration of RCSWs using the cracking length and crushing area as the input variables for the machine learning models. A similar approach was recently employed by Hamidia et al 21 to use visual damage features for predicting the peak drift ratio of beam-column joints using machine learning techniques. The study also correlated the cracking length and crushing areas to the post-earthquake damage states of beam-column subassemblies using FEMA P-58 and HAZUS guidelines.…”

Section: Introductionmentioning

confidence: 99%

“…to predict the performance level, peak drift ratio, and stiffness deterioration of RCSWs using the cracking length and crushing area as the input variables for the machine learning models. A similar approach was recently employed by Hamidia et al 21 . to use visual damage features for predicting the peak drift ratio of beam‐column joints using machine learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Three‐dimensional fragility surface for reinforced concrete shear walls using image‐based damage features

Asjodi

Dolatshahi

Burton

2023

Earthq Engng Struct Dyn

Self Cite

View full text Add to dashboard Cite

This paper proposes a new data-driven method to generate three-dimensional fragility surfaces for post-earthquake damage assessment of reinforced concrete (RC) shear walls (SWs) using image-based damage features. A research database comprised of 212 images corresponding to 66 damaged reinforced concrete shear walls tested under quasi-static cyclic loads is utilized. The walls are categorized into three damage states defined based on different load points along the backbone curve. Convolutional kernel-based filters are then employed to measure the crack patterns and crushed areas from images of the damaged walls. A set of 360,000 sub-cracks from the 212 images is analyzed using Gaussian mixture modeling to distinguish between shear and flexural cracking. These two types of cracking, along with crushing, are the prominent characteristics used to determine the damage states of the RCSWs. The extracted features of shear and flexural cracking are also compressed into a unique cracking index using the Principal Component Analysis theory for dimensionality reduction. Using the compressed feature of cracking and crushing, a new methodology for generating three-dimensional fragility surfaces, entitled the Box-counting method, is introduced, and the damage surfaces are developed based on visual damage features. The damage surfaces are finally formulated using statistical models or machine learning regression learners. The proposed fragility surface can be used for postearthquake damage state identification, risk assessment, and loss estimation of damaged RCSWs.

show abstract

Machine learning-based seismic damage assessment of non-ductile RC beam-column joints using visual damage indices of surface crack patterns

Cited by 23 publications

References 24 publications

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

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

Post‐earthquake stiffness loss estimation for reinforced concrete columns using fractal analysis of crack patterns

Three‐dimensional fragility surface for reinforced concrete shear walls using image‐based damage features

Contact Info

Product

Resources

About