American Society of Civil Engineers


Damage Size Prediction of Reinforced Concrete Slabs under Blast Loads Using Artificial Neural Networks


by Ahmed Ibrahim, (Department of Civil Engineering and Construction, Bradley University, 206 Jobst Hall, Peoria, IL, 61625. E-mail: aibrahim@bradley.edu), Hani Salim, (Department of Civil and Environmental Engineering, University of Missouri, E2509 Lafferre Hall, Columbia, MO, 65211. E-mail: salimh@missouri.edu), and Ian Flood, (School of Building Construction, University of Florida, Gainesville, FL 32611. E-mail: flood@ufl.edu)
Section: Extreme Loads, pp. 1530-1537, (doi:  http://dx.doi.org/10.1061/41171(401)133)

     Access full text
     Purchase Subscription
     Permissions for Reuse  

Document type: Conference Proceeding Paper
Part of: Structures Congress 2011
Abstract: There are a few related researches that provide well-defined models to predict the damage size under close-in explosions. This paper presents a prediction of the damage size experienced by reinforced concrete (RC) slabs subjected to close-in detonations using numerical data and a neural network—based model. To train and validate the artificial neural network (ANN), a data base is developed through a series of measurements of the damage diameter (crater/spalling) size induced in reinforced concrete two-way slabs under blast loads. The data was obtained by performing various simulations using the dynamic explicit finite element code LS-DYNA. The principle parameters controlling the breaching size are charge weight, standoff distance, and slab thickness, which were used to develop the ANN training input data set. The trained and validated neural network was used to develop an ANN model capable of predicting the breach size of concrete slabs under close-in detonations.


ASCE Subject Headings:
Damage
Predictions
Reinforced concrete
Concrete slabs
Blast loads
Neural networks
Artificial intelligence