A Hybrid ANN-GA Model for an Automated Rapid Vulnerability Assessment of Existing RC Buildings

Abstract

Determining the risk priorities for the building stock in highly seismic-prone regions and making the final decisions about the buildings is one of the essential precautionary measures that needs to be taken before the earthquake. This study aims to develop an Artificial Neural Network (ANN)-based model to predict risk priorities for reinforced-concrete (RC) buildings that constitute a large part of the existing building stock. For this purpose, the network parameters in the network structure have been optimized by establishing a hybrid structure with the Genetic Algorithm (GA). As a result, the ANN model can make accurate predictions with maximum efficiency. The suggested ANN model is a feedforward back-propagation network model. It aims to predict the risk priorities for 329 RC buildings in the most successful way, for which the performance score was calculated using the Turkey Rapid Evaluation Method (2013). In this paper, a GA-ANN hybrid model was implemented in which the ANN, using the most successful gene revealed by the model, produced successful results in calculating the performance score. In addition, the required input parameters for obtaining more efficient results in solving such a problem and the parameters that need to be used in establishing such an ANN network structure have been optimized. With the help of such a model, the operation process will be eliminated. The created hybrid model was 98% successful in determining the risk priority in RC buildings.

Seismic Fragility Assessment of RC Columns Exposed to the Freeze-Thaw Damage

“…Many studies [39][40][41][42][43][44] have shown that, D and C could be assumed to follow the lognormal distributions when analyzing their seismic fragility. Therefore, freeze-thaw cycles could be introduced as a variable to build a new seismic fragility function, as shown in Equation ( 16).…”

“…OpenSEES [38][39][40]42,43] is an efficient nonlinear seismic analysis software, which has the advanced modeling capabilities and contains many material models, elements and algorithms for the seismic assessments of RC structures. Therefore, OpenSEES was utilized to construct the nonlinear FE model of the bridge.…”

“…In this case, 50 FE models of the bridge were generated by employing the uniform design method [38,39,42,46]. For simplicity, this paper only studied the longitudinal curvature ductility demand of the columns, which can be defined as the ratio of the maximum curvature to the curvature at which the outermost tensile bars first reaching the yield strength [33,34,40,42,45,49]. Linear regression analysis was performed by using Equation (17) to obtain the relevant PSDMs of the columns.…”

The Effect of Different Heavy Overhang on Structural Performance in Reinforced Concrete Structures

“…The lower building area, especially on the ground storey, is replaced by larger building areas on the upper storeys. Heavy overhang status is clearly stated within the negativity parameters taken into account in the rapid assessment method [33], [34], [35], [36]. In this method, the presence of heavy overhangs is determined according to Figure 3.…”

Enhancing 3D Reconstruction Model by Deep Learning and Its Application in Building Damage Assessment after Earthquake

“…Li et al used remote sensing data before and after the earthquake through the decision tree method, in which the damaged buildings were divided into four grades [2]. The neural network of the genetic algorithm (GA) and the neural network composed of multi-layer perceptron (MLP) are used to predict the risk level of damage to reinforced-concrete (RC) structures [3,4]. The method achieves detailed investigation and inspection of buildings before the earthquake, reducing the loss of life and property.…”