Araei A.A.,Housing and Urban Development Research Center
International Journal of Geomechanics | Year: 2014
In this paper, the feasibility of developing and using artificial neural networks (ANNs) for modeling the monotonic behaviors of various angular and rounded rockfill materials is investigated. The database used for development of the ANN models is comprised of a series of 82 large-scale, drained triaxial tests. The deviator stress-volumetric strain versus axial strain behaviors were first simulated by using ANNs. A feedback model using multilayer perceptrons for predicting drained behavior of rockfill materials was developed in the MATLAB environment, and the optimal ANN architecture was obtained by a trial-and-error approach in accordance with error indexes and real data. Reasonable agreement between the simulated behaviors and the test results was observed, indicating that the ANNs are capable of capturing the behavior of rockfill materials. The ability of ANNs to predict the constitutive hardening-soil model parameters, residual deviator stresses, and corresponding volumetric strain was also investigated. Moreover, the generalization capability of ANNs was also used to check the effects of items not tested, such as dry density, grain-size distributions, and Los Angeles abrasion. © 2014 American Society of Civil Engineers.
Ahmadi B.,University of Tehran |
Sobhani J.,Housing and Urban Development Research Center |
Shekarchi M.,University of Tehran |
Najimi M.,University of Nevada, Las Vegas
Magazine of Concrete Research | Year: 2014
This paper reports on an experimental investigation into the performance of ternary concrete mixtures containing combinations of natural zeolite with silica fume or fly ash. The performance of the ternary mixtures is compared with the performance of binary mixtures with only one type of supplementary cementitious material (SCM) and a control mixture without any SCM. The experimental programme included strength and transport property evaluations of a control mixture, binary mixtures with 7.5% silica fume or 10% natural zeolite or 20% fly ash as partial replacements of Portland cement, and ternary mixtures containing 5% natural zeolite with 5% silica fume or 10% natural zeolite with 10% fly ash as partial replacements of Portland cement. The results of the study reveal considerable improvements in the transport properties of concrete through replacing a portion of Portland cement with combinations of natural zeolite with silica fume or fly ash. Generally, the ternary mixtures showed superior transport properties to those of the control and binary mixtures. Their compressive strengths, however, were lower than those of the binary mixtures.
Khorami M.,Islamic Azad University at Eslamshahr |
Sobhani J.,Housing and Urban Development Research Center
International Journal of Civil Engineering | Year: 2013
Worldwide, asbestos fibers utilized in fiber cement boards, have been recognized as harmful materials regarding the public health and environmental pollutions. These concerns motivate the researchers to find the appropriate alternatives to substitute the asbestos material towards the sustainability policies. In this paper, the applicability of asbestos replacement with three types of agricultural waste fibers, including bagasse, wheat and eucalyptus fibers were experimentally investigated. To this end, the flexural behaviour and microstructure of cement composite boards made by addition of 2% and 4% of waste agricultural fibers in combination with and without 5% replacement of silica fume by mass of cement were evaluated. The results of this study attested the applicability of utilized waste agricultural fibers in production of cement composite boards by improving the flexural and energy absorption characteristics, more or less, depending on the type of fibers. Moreover, it is found that application of silica fume in production of cement composite boards led to an increase in flexural strength.
Pourghasemi H.R.,Tarbiat Modares University |
Moradi H.R.,Tarbiat Modares University |
Fatemi Aghda S.M.,Kharazmi University |
Fatemi Aghda S.M.,Housing and Urban Development Research Center
Natural Hazards | Year: 2013
The current research presents a detailed landslide susceptibility mapping study by binary logistic regression, analytical hierarchy process, and statistical index models and an assessment of their performances. The study area covers the north of Tehran metropolitan, Iran. When conducting the study, in the first stage, a landslide inventory map with a total of 528 landslide locations was compiled from various sources such as aerial photographs, satellite images, and field surveys. Then, the landslide inventory was randomly split into a testing dataset 70 % (370 landslide locations) for training the models, and the remaining 30 % (158 landslides locations) was used for validation purpose. Twelve landslide conditioning factors such as slope degree, slope aspect, altitude, plan curvature, normalized difference vegetation index, land use, lithology, distance from rivers, distance from roads, distance from faults, stream power index, and slope-length were considered during the present study. Subsequently, landslide susceptibility maps were produced using binary logistic regression (BLR), analytical hierarchy process (AHP), and statistical index (SI) models in ArcGIS. The validation dataset, which was not used in the modeling process, was considered to validate the landslide susceptibility maps using the receiver operating characteristic curves and frequency ratio plot. The validation results showed that the area under the curve (AUC) for three mentioned models vary from 0.7570 to 0.8520 (AUCAHP = 75.70 %, AUCSI = 80.37 %, and AUCBLR = 85.20 %). Also, plot of the frequency ratio for the four landslide susceptibility classes of the three landslide susceptibility models was validated our results. Hence, it is concluded that the binary logistic regression model employed in this study showed reasonably good accuracy in predicting the landslide susceptibility of study area. Meanwhile, the results obtained in this study also showed that the statistical index model can be used as a simple tool in the assessment of landslide susceptibility when a sufficient number of data are obtained. © 2013 Springer Science+Business Media Dordrecht.
Ghafoori N.,University of Nevada, Las Vegas |
Najimi M.,University of Nevada, Las Vegas |
Sobhani J.,Housing and Urban Development Research Center |
Aqel M.A.,University of Toronto
Construction and Building Materials | Year: 2013
This paper is intended to compare robustness of linear and nonlinear regressions, and neural network prediction models in estimating rapid chloride permeability of self-consolidating concretes based on their mixture proportions. Several models were developed by varying number of independent variables and samples (mixtures) allotted to training and testing. The results of this study showed the superior performance of neural network models in comparison with the prediction models obtained by linear and nonlinear regressions, particularly when testing evaluations were chosen from the boundaries of mixture proportions. Within the linear and nonlinear prediction models, power relationships produced the most consistent performance. © 2013 Elsevier Ltd. All rights reserved.