جستجوی مقالات مرتبط با کلیدواژه « برنامه نویسی بیان ژن » در نشریات گروه « عمران »

Application of different stabilizers and additives such as cement, lime, and fly ash is one of the solutions for improving weak and problematic subgrade soils. In this study, a clay soil was stabilized using different percentages of cement and lime (0, 3, 5, 7 and 9%) and with different moisture content (optimum humidity level, wet side and dry side) and unconfined compressive strength (UCS) test was conducted at different curing times (7, 14, 21, 28 and 60 days). Then, the gene expression programming (GEP) method was employed to model the UCS of cement-stabilized and lime-stabilized clay soil. In the developed models, three variables of additive percentage, curing time and moisture content are used as the input variables to predict the UCS. The results of this study showed that the coefficient of determination (R2) for the model developed to predict the UCS of cement-stabilized clay soil is 0.935 and 0.926 for training and testing data, respectively. The R2 value for the model developed to predict the UCS of lime-stabilized clay soil is 0.911 and 0.884 for training and testing data, respectively. The results of the parametric study showed that the UCS increases with the increase in the percentage of cement and lime and the curing time and decreases with the increase in the moisture content.

Energy dissipation in stepped spillways is one of the primary goals of such structures. In this study, the accuracy of the artificial neural network (ANNs) method, the adaptive fuzzy neural inference model method based on the trained firewall optimization algorithm (ANFIS-FA) and the gene expression programming method (GEP) in estimating the energy loss of skimming flow regime on stepped spillways has been studied. Also, by performing sensitivity analysis, the importance of input parameters in predicting energy loss for each of the three mentioned methods has been investigated. For this purpose, 154 series of laboratory data have been used. The input parameters for each method include the hydraulic jump Froude number, the Drop number, the number of steps, the pseudo bottom slope and the ratio of the critical depth to the height of each step.. The results show that all three methods had a higher ability to predict energy loss than classical methods for estimating energy loss based on conventional regression methods. The accuracy of the ANFIS-FA (with) method is slightly higher than the GEP (with) method. The accuracy of the neural network is slightly lower than the above two methods.However, the highest accuracy obtained is related to the multilayer perceptron neural network with 3 hidden layers with the number of 12, 8 and 7 nodes in each layer, respectively. In all three methods, the most effective parameter is the waterfall number and the least effective parameter is the pseudo bottom slope.

Today, the importance of construction costs in construction projects is increasing day by day and it is necessary to study the estimation of construction costs and the factors affecting construction costs.This research has been done around the subject of estimate the construction costs by intelligence data driven methods named Artificial Neural Network (ANN), Support Vector Machine (SVM) and Gene Expression Programming (GEP) determine the effective factors on cost and cost optimization in east of Tehran. To estimate the costs of residential buildings, in this research it's used from 46 residential buildings which were implemented in west of Tehran and it's used from the artificial intelligence method to estimate the construction costs that is used from ANN, artificial neural network method, GEP, SVM and it was used from questionnaire and Friedman test method to diagnosis the effective factors on costs to prioritize factors that can optimize the costs by possessing these two factors, the effective factors on costs and construction costs estimation . After reviews and studies we resulted that costs estimation had been done by ANN, GEP, SVM methods and by comparing these methods, GEP cause of its less errors and more predictability, was the best method than others. The effective factors on costs were determined by Friedman test method that after reviews these factors, construction costs had been optimized.

With regard to the adverse environmental impacts of cement production, the use of geopolymer concrete (GPC) can be considered as a more environmentally friendly approach for concreting. This study deals with an experimental investigation on the effects of partial replacement of the GGBS (replaced with 5, 10, 15, 20, 25, and 30%) used in GPC with natural zeolite (NZ) and silica fume (SF) simultaneously with different concentration (4, 6 and 8 M) of sodium hydroxide (NaOH) together with sodium silicate (water glass) solution on the compressive strength. Results indicate that increasing concentration of NaOH yields decreases the compressive strength of the concrete. In contrast, adding NZ and SF into concrete results in increasing the compressive strength. In addition, gene expression programming (GEP) was employed to develop mathematical models for predicting the compressive strength of GPC based on GGBS. Using the experimental results, an extensive and reliable database of compressive strength of GGBS-based GPC was obtained. The database comprises the compressive strength results of 351 specimens produced from 117 different mixtures. The five most influential parameters i.e., age of specimens, NaOH solution concentration, NZ, SF and GGBS content of GPC, were considered as the input parameters for modeling. The results reflected that the proposed models are accurate and possess a high prediction capability. The findings of this study can enhance the re-use of GGBS for the development of GPC leading to environmental protection and monetary benefits.
1- Ground Granulated Blast- Furnance Slag

The construction and maintenance of structural pavement was a high-cost problem in last decade. The mechanical properties of self compacting concrete (SCC) required important factors .From its mechanical properties, the compressive strength (CS) is necessary to investigate experimental and computational intelligence analysis in construction materials. Developing models with accurate estimation for this key property caused to saving costs and time and producing an optimal blend. Because of the many advantages, using of SCC in structures is increasing. Construction of precast-prefabricated components, with the use of concrete has also recently been considered. Concrete properties have significant role in precast-prefabricated girders behavior. Exact prediction of these properties is the base of member’s analysis and design. The main purpose of this study is presents new formulation to estimate the compressive strength of self-compacting concrete containing rice husk ash (RHA) using robust variant of genetic programming, namely gene expression programming (GEP) method. To evaluate the performance of the GEP-based proposed model, prediction was also done using classical data driven methods named artificial neural network (ANN) and multiple linear regression (MLR) models.  A large and reliable experimental database containing the results of 156 compressive strength of SCC incorporating RHA is collated through an extensive review of the literature. The performance of proposed models of CS is then assessed using the database, and the results of this evaluation are presented using selected performance measures. New expressions for the estimation of CS of SCC are developed based on the database. To evaluate the modeling performances of the proposed GEP models for CS, different statistical metrics were used. Correlation coefficient (R), root mean square error (RMSE), mean absolute error (MAE) were used as the measure of precision. The results showed that the models developed using the aforementioned methods have accuracy over 90 percent in prediction of CS of SCC. The results of testing datasets are compared to experimental results and their comparisons demonstrate that the GEP model (R=0.94, RMSE= 4.308 and MAE=4.916) outperforms ANN (R=0.92, RMSE= 5.136 and MAE=5.624) and MLR (R=0.89, RMSE= 8.212 and MAE=9.472). Proposed models have a strong potential to predict compressive strength of self compacting concrete incorporating rice husk ash with great precision. The importance of different input parameters is also given for predicting the compressive strengths at various ages using gene expression programming. Performed sensitivity analysis to assign effective parameters on compressive strength indicates that cementitious binder content is the most effective variable in the mixture. The assessment results present that the performance of the proposed models are in close agreement with the experimental results. Moreover, the new GEP-based formulation provides improved estimates of the compressive strength of SCC compared to ANN and MLR models. The proposed design equation can readily be used for pre-design purposes or may be used as a fast check on deterministic solutions.