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

Abstract

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.

Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives

“…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.…”

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

“…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.…”

“…In a recent study, Hamidia et al 40 utilized GFDs derived from crack maps of damaged joints in RCMFs to assess and evaluate the extent of damage. Hamidia and Ganjizadeh utilized fractal-based procedures to quantify the peak drift ratio 41 and post-earthquake residual stiffness 42 in nonductile RCMF joints. GFDs have been also incorporated for the estimation of residual stiffness, 39,43 and strength 44 in RC columns.…”

Vision‐based probabilistic post‐earthquake loss estimation for reinforced concrete shear walls

“…In order to quantify the maximum drift ratio and updated stiffness and strength of RCSWs, the GFDs of the maps of the cracking patterns on RCSWs are employed. 45,46 Additionally, Hamidia and Ganjizadeh presented peak drift ratio, 47 and energy dissipation 48,49 prediction equation for non-ductile RCMFs by deterministic methods based on GFDs. Also, for the estimation of residual stiffness, 50 strength, 51 and drift ratio 52,53 of RC columns, GFDs have been used.…”