This paper presents a novel computational procedure for the maximum dry density of mixed soils containing oversize particles.At first,the large-scale compaction test data for mixed soils are analyzed by an artificial ...This paper presents a novel computational procedure for the maximum dry density of mixed soils containing oversize particles.At first,the large-scale compaction test data for mixed soils are analyzed by an artificial neural network to determine the main factors affecting the compaction.These factors are then imposed on a genetic programming method and a new mathematical equation emerges.The new equation has more conformity with the experimental data in comparison with the previous correction methods.Besides,the mixed soil dry density is associated with most base soil and oversize fraction specifications.With regard to the sensitivity analyses,if the mixed soil contains high percentages of oversize fraction,the mixed soil composition is governed by the specification of oversized grains,such as specific gravity and the maximum grain size and by increasing these factors,the mixed soil dry density is increased.In mixed soil with a low content of oversize,the base soil specification mainly controls the compaction behavior of mixed soil.Furthermore,if the base soil is inherently compacted with greater dry density,adding the oversize slightly improves the mixed soil dry density.In contrast,adding oversized grains to the base soil with a lower dry density produces a mixed soil with greater dry density.By increasing the maximum grain size difference between the oversize fraction and base soil,the dry density of mixed soil is enhanced.展开更多
In the present paper, two models based on artificial neural networks and genetic programming for predicting split tensile strength and percentage of water absorption of concretes containing Cr2O3 nanoparticles have be...In the present paper, two models based on artificial neural networks and genetic programming for predicting split tensile strength and percentage of water absorption of concretes containing Cr2O3 nanoparticles have been developed at different ages of curing. For purpose of building these models, training and testing using experimental results for 144 specimens produced with 16 different mixture proportions were conducted. The data used in the multilayer feed forward neural networks models and input variables of genetic programming models are arranged in a format of 8 input parameters that cover the cement content, nanoparticle content, aggregate type, water content, the amount of superplasticizer, the type of curing medium, age of curing and number of testing try. According to these input parameters, in the neural networks and genetic programming models the split tensile strength and percentage of water absorption values of concretes containing Cr2O3 nanoparticles were predicted. The training and testing results in the neural network and genetic programming models have shown that every two models have strong potential for predicting the split tensile strength and percentage of water absorption values of concretes containing Cr2O3 nanoparticles. It has been found that NN and GEP models will be valid within the ranges of variables. In neural networks model, as the training and testing ended when minimum error norm of network was gained, the best results were obtained and in genetic programming model, when 4 genes were selected to construct the model, the best results were acquired. Although neural network has predicted better results, genetic programming is able to predict reasonable values with a simpler method rather than neural network.展开更多
文摘This paper presents a novel computational procedure for the maximum dry density of mixed soils containing oversize particles.At first,the large-scale compaction test data for mixed soils are analyzed by an artificial neural network to determine the main factors affecting the compaction.These factors are then imposed on a genetic programming method and a new mathematical equation emerges.The new equation has more conformity with the experimental data in comparison with the previous correction methods.Besides,the mixed soil dry density is associated with most base soil and oversize fraction specifications.With regard to the sensitivity analyses,if the mixed soil contains high percentages of oversize fraction,the mixed soil composition is governed by the specification of oversized grains,such as specific gravity and the maximum grain size and by increasing these factors,the mixed soil dry density is increased.In mixed soil with a low content of oversize,the base soil specification mainly controls the compaction behavior of mixed soil.Furthermore,if the base soil is inherently compacted with greater dry density,adding the oversize slightly improves the mixed soil dry density.In contrast,adding oversized grains to the base soil with a lower dry density produces a mixed soil with greater dry density.By increasing the maximum grain size difference between the oversize fraction and base soil,the dry density of mixed soil is enhanced.
文摘In the present paper, two models based on artificial neural networks and genetic programming for predicting split tensile strength and percentage of water absorption of concretes containing Cr2O3 nanoparticles have been developed at different ages of curing. For purpose of building these models, training and testing using experimental results for 144 specimens produced with 16 different mixture proportions were conducted. The data used in the multilayer feed forward neural networks models and input variables of genetic programming models are arranged in a format of 8 input parameters that cover the cement content, nanoparticle content, aggregate type, water content, the amount of superplasticizer, the type of curing medium, age of curing and number of testing try. According to these input parameters, in the neural networks and genetic programming models the split tensile strength and percentage of water absorption values of concretes containing Cr2O3 nanoparticles were predicted. The training and testing results in the neural network and genetic programming models have shown that every two models have strong potential for predicting the split tensile strength and percentage of water absorption values of concretes containing Cr2O3 nanoparticles. It has been found that NN and GEP models will be valid within the ranges of variables. In neural networks model, as the training and testing ended when minimum error norm of network was gained, the best results were obtained and in genetic programming model, when 4 genes were selected to construct the model, the best results were acquired. Although neural network has predicted better results, genetic programming is able to predict reasonable values with a simpler method rather than neural network.
