جستجو در تالارهای گفتگو

A Mathematical Modeling for Plastic Analysis of Planar Frames by Linear Programming and Genetic Algorithm Leila Shahryari In this paper, a mathematical modeling is developed for plastic analysis of planar frames. To this end, the researcher tried to design an optimization model in linear format in order to solve large scale samples. The computational result of CPU time requirement is shown for different samples to prove efficiency of this method for large scale models. The fundamental concept of this model is obtained from moment distribution method which is a safe theorem based method, so in this mathematical modeling, the objective is finding the largest load which ensures equilibrium and yield conditions. Contrary to moment distribution method, calculation of load factor and the value of moments in the elements are completely automatic and not to need user decision. As the objective function and constraints of this model are linear so it can be solved by linear programming (LP) software such as LINGO that is shown in this paper and also the model is solved by genetic algorithm (GA) to compare two solutions منبع دانلود JSEG81313868600.pdf

Application of Support Vector Machine for Crash Injury Severity Prediction: A Model Comparison Approach. Aghayan I., Hadji Hosseinlou M., Metin Kunt M. J. Civil Eng. Urban., 5(5): 193-199, 2015; pii:S225204301500031-5 Abstract The study presented in this paper investigated the application of using support vector machine with different kernel functions for crash injury severity prediction. A support vector machine model was developed for predicting the injury severity related to individual crashes based on crash data. The models were developed using the input parameters of driver’s age and gender, the use of a seat belt, the type and safety of a vehicle, weather conditions, road surface, speed ratio, crash time, crash type, collision type and traffic flow. Also, three injury levels were considered as output parameters for this study (i.e. no injury, evident injury and fatality). The overall prediction accuracy of the support vector machine model was compared to the multi-layer perceptron, genetic algorithm, combined genetic algorithm and pattern search. The results demonstrated that the constructed multi-layer perceptron’s performance was slightly better than the support vector machine for injury severity prediction. Whereas, support vector machine involves much lower computational cost than multi-layer perceptron because of using a straight forward algorithm in learning phase. The percent of prediction accuracy for the multi-layer perceptron model was 86.2%, which was higher than the support vector machine model with polynomial kernel (81.4%) followed by the combination of the genetic algorithm and pattern search (78.6%) and genetic algorithm (78.1%). The classification results of the two-level (no-injury and evidence injury/fatality) support vector machine found to be 85.3% was higher than multi-class classification (81.4%). Keywords: Crash Injury Severity Prediction, Genetic Algorithm, Multi-Layer Perceptron, Pattern Search, Support Vector Machine [Full text-PDF] منبع: [Hidden Content] J. Civil Eng. Urban., 5 (5) 193-199, 2015.pdf

Development of Simulation-Optimization Model for Stormwater Treatment Measure Optimization (Case Study: Gold Coast City, Australia) Original Article, D41 Montaseri M, Afshar MH., Haddad O.B. J. Civil Eng. Urban. 4(3): 266-273. 2014 ABSTRACT: Urbanization and urban development builds large amounts of impervious areas, stopping the infiltrating of rainfall into soil process and consequently, requiring of the construction of large stormwater treatment measures. A new tendency in storm water management endorses ‘source control’ whereby small distributed water sensitive urban design systems are built throughout the subdivision to alleviate the effects of land use changes, and protect downstream water quality. Source control practices include use of water sensitive urban design practices like rainwater Tanks, vegetated swales, bio-retention systems, infiltration basins, and constructed wetlands in order to disconnect impervious areas from each other. These elements have different roles and costs. This paper presents a rule based method, to reduce the costs of urban stormwater management. For this purpose, two simulation and optimization model are linked together in the MatLab integrated development environment. Linking the simulation model (MUSIC) and the optimization model (Genetic Algorithm), allowed this simulation and optimization model (MUSIC-GA) to minimize the costs of various treatment devices. Results of usage of MUSIC-GA model on optimizing of urban stormwater treatment systems in about 1.7 hectares residential areas in Gold Coast City, Australia showed that optimized post development is at least 45 percent effective means for removal of pollutants from urban stormwater runoff. Also, small coefficient of variation (0.005) of the results of different runs indicated that there is a proper convergence of MUSIC-GA results toward the global optimal solution. Keywords: Urban stormwater, Water sensitive urban design, MUSIC, Constructed wetland, Genetic algorithm منبع: [Hidden Content] دانلود: [Hidden Content].,%204%20(3)%20266-273,%202014.pdf J. Civil Eng. Urban., 4 (3) 266-273, 2014.pdf

Optimal Cost Design of the Water Distribution Network Using the Meta-Heuristic Methods Original Article, C26 Daneshfaraz R. Journal. Civil Eng. Urban. 3(4):164-169. 2013 ABSTRACT:Today, optimal cost design of water distribution networks is one of the fundamental issues in water management plans. In recent years, high accuracy of meta-heuristic methods has gained attention of researchers. In this research, genetic algorithm and harmony search methods were used for optimal cost design of water distribution network in Kourtay village, Khoy. The results showed the significant ability of the methods, since the design costs were decreased by 8% and 10% using the genetic algorithm and harmony search algorithm, respectively. Furthermore, the Harmony search method was found more optimal and faster than the genetic algorithm. Keywords: Economic Optimization, Genetic Algorithm, Harmony Search Algorithm, Water Distribution Network منبع: [Hidden Content] دانلود: [Hidden Content].,26-164-169.pdf J. Civil Eng. Urban.,26-164-169.pdf