Soft Computing in Civil EngineeringSoft Computing in Civil Engineering
http://www.jsoftcivil.com/
Wed, 23 Jan 2019 15:14:09 +0100FeedCreatorSoft Computing in Civil Engineering
http://www.jsoftcivil.com/
Feed provided by Soft Computing in Civil Engineering. Click to visit.Developing Four Metaheuristic Algorithms for Multiple-Objective Management of Groundwater
http://www.jsoftcivil.com/article_64764_5935.html
Groundwater is one of the important sources of freshwater and accordingly, there is a need for optimizing its usage. In this paper, four multi-objective metaheuristic algorithms with new evolution strategy are introduced and compared for the optimal management of groundwater namely: Multi-objective genetic algorithms (MOGA), multi-objective memetic algorithms (MOMA), multi-objective particle swarm optimization (MOPSO), and multi-objective shuffled frog leaping algorithm (MOSFLA). The suggested evolution process is based on determining a unique solution of the Pareto solutions called the Pareto-compromise (PC) solution. The advantages of the current development stem from: 1) The new multiple objectives evolution strategy is inspired from the single objective optimization, where fitness calculations depend on tracking the PC solution only through the search history; 2) a comparison among the performance of the four algorithms is introduced. The development of each algorithm is briefly presented. A comparison study is carried out among the formulation and the results of the four algorithms. The developed four algorithms are tested on two multiple-objective optimization benchmark problems. The four algorithms are then used to optimize two-objective groundwater management problem. The results prove the ability of the developed algorithms to accurately find the Pareto-optimal solutions and thus the potential application on real-life groundwater management problems.Sun, 30 Sep 2018 20:30:00 +0100Optimum Design of Structures Against earthquake by Simulated Annealing Using Wavelet Transform
http://www.jsoftcivil.com/article_62820_5935.html
Optimization of earthquake-affected structures is one of the most widely used methods in structural engineering. In this paper optimum design of structures is achieved by simulated annealing method. The evolutionary algorithm is employed for optimum design of structures. To reduce the computational work, a discrete wavelet transform is used by means of which the number of points in the earthquake record is decreased. The loads are considered as earthquake loads. A time history analysis is carried out for the dynamic analysis. By discrete wavelet transform (DWT) the earthquake record is decomposed into a number of points. Then in the optimization process, the structures are analyzed for these points. To reconstruct the actual responses from these points, a reverse wavelet transform (RWT) was used. A number of space structures are designed for minimum weight and the results are compared with exact dynamic analysis. The result show, DWT and RWT were an effective approach for reducing the computational cost of optimization.Tue, 22 May 2018 19:30:00 +0100Site selection for limestone paper plant using AHP-Monte Carlo approach
http://www.jsoftcivil.com/article_76644_0.html
Paper played a crucial role in the history of the development of human society. Even in current times in the modern world, with Tablet, eBook readers and smart phones, the use of paper is still unavoidable. The wood needed for the production of the paper is provided by cutting down trees; hence, paper production has a cost to environment. Recently, a new technology has been developed which uses limestone instead of wood as the main material for paper production. This technology is environmentally friendly compared to the traditional paper-making technology. Choosing a suitable location for construction of such paper production plant based on different factors affecting paper quality is of great importance. To choose the desired location of such plant, it is proposed to use a combination of Monte Carlo and Analytical Hierarchic Process approaches. In this way, in the search area there is a distribution of rates for each pixel instead of a single rate which allows to determine appropriate location for different confidence levels. The proposed method has been applied on Bijar, one of the cites of Kurdistan province in Iran, and a suitable location of paper production plant is highlighted for various levels of confidence.Thu, 01 Nov 2018 20:30:00 +0100Prediction of Ultimate Bearing Capacity of Skirted Footing Resting on Sand Using Artificial ...
http://www.jsoftcivil.com/article_64822_5935.html
The paper presents the prediction of the ultimate bearing capacity of different regular shaped skirted footing resting on sand using the artificial neural network. The input parameters for the artificial neural network model were normalised skirt depth, area of the footing and the friction angle of the sand, while the output was the ultimate bearing capacity. The artificial neural network algorithm uses a back propagation model. The training of artificial neural network model has been conducted and the weights were obtained which described the relationship between the input parameters and output ultimate bearing capacity. Further, the sensitivity analysis has been performed and the parameters affecting the ultimate bearing capacity of different regular shaped skirted footing resting on the sand were identified. The study shows that the prediction accuracy of the ultimate bearing capacity of different regular shaped skirted footing resting on sand using artificial neural network model was quite good.Sun, 30 Sep 2018 20:30:00 +0100Prediction of Concrete and Steel Materials Contained by Cantilever Retaining Wall by Modeling ...
http://www.jsoftcivil.com/article_65561_5935.html
In this study, the Artificial Neural Network (ANN) application is implemented for predicting the required concrete volume and amount of the steel reinforcement within the inversed-T-shaped and stem-stepped reinforced concrete (RC) walls. For this aim, seven-different RC wall designs were approached differentiated within the wall heights and various internal friction angles of backfill materials. Each RC wall is proportionally designed and subjected to active lateral earth pressure defined with the Mononobe-Okabe approach foreseen by Turkish Specification for Building to be Built in Seismic Zones (TSC-2007)[14]. Following the stability analysis of the RC retaining walls, the structural and reinforced concrete analyses are performed according to the Turkish Standard on Requirements for Design and Construction in Reinforced Concrete Structures (TS500-2000)[15]. Input parameters such as concrete volumes, weights of the steel bars, soil and wall material properties are subjected to the ANN modeling. The prediction of the concrete volume and amount of the steel bars are achieved with the implementation of the ANN model trained with the Artificial Bee Colony (ABC) algorithm. As a result of this study, it is revealed that ANN models are useful for verifying the existing RC retaining wall designs or performing preliminary designs for the L-shaped and stem-stepped cantilever retaining walls.Sun, 30 Sep 2018 20:30:00 +0100Scale Effect and Anisotropic Analysis of Rock Joint Roughness Coefficient Neutrosophic Interval ...
http://www.jsoftcivil.com/article_81314_5935.html
In rock mechanics, mechanical properties of rock masses in nature imply complexity and diversity. The shear strength of rock mass is a key factor for affecting the stability of the rock mass. Then, the joint roughness coefficient (JRC) of rock indicates an important parameter in the shear strength and stability analysis of rock mass. Since the nature of the rock mass is indeterminate and incomplete to some extent, we cannot always express rock JRC by a certain/exact number. Therefore, this paper introduces neutrosophic interval statistical numbers (NISNs) based on the concepts of neutrosophic numbers and neutrosophic interval probability to express JRC data of the rock mass in indeterminate setting. Then we present the calculational method of the neutrosophic average value and standard deviation of NISNs based on neutrosophic statistics. Next, by an actual case, the neutrosophic average value and standard deviation of the rock JRC NISNs are used to analyze the scale effect and anisotropy of the rock body corresponding to different sample lengths and measuring directions. Lastly, the analysis method of the scale effect and anisotropy for JRC NISNs shows its effectiveness and rationality in the actual case study.Sun, 30 Sep 2018 20:30:00 +0100Application of adaptive Neuro-fuzzy inference system to estimate alongshore sediment transport ...
http://www.jsoftcivil.com/article_81315_5935.html
Many empirical models have been introduced by scientists during the recent decades for estimating longshore sediment transport rate, but these approaches have been calibrated and applied under limited conditions of the bed profile and specific range of the bed sediment size. The existing empirical relations are linear or exponential regressions based on the observation and measurements data and there’s a great potential to build more accurate models to predict sediment transport phenomena by means of soft computation approach. This paper presents a novel case study application of the adaptive Neuro-fuzzy inference system (ANFIS) as a superior modeling technique for estimation of the longshore sediment transport rate in the southern shorelines of the Caspian Sea. The results will be compared with top three popular existing empirical equations. Daily grab samples from four stations were collected in the period of March 2012 through June 2012. The trained ANFIS model outperformed the existing regression-type empirical equations for the estimation of the alongshore sediment transport rate due to the adaptive structure of the ANFIS model to better fit complex systems.Sun, 30 Sep 2018 20:30:00 +0100An Equation to Determine the Ultimate Flexural Load of RC Beams Strengthened with CFRP Laminates
http://www.jsoftcivil.com/article_76643_5935.html
In this paper, a new relationship is presented for determining the ultimate flexural load of reinforced concrete beams strengthened with CFRP laminates. An artificial neural network with a suitable performance was used to estimate this equation. First, a collection of laboratory results including 83 data was collected from valid references. This database was then divided into three groups of 51, 16, and 16, which were used to train, validation, and test the proposed equation, respectively. The final model had eleven inputs including concrete compressive strength, width of beam, effective depth, area of tension reinforcement, area of compression reinforcement, yield strength of steel, modulus of elasticity of steel, modulus of elasticity of CFRP sheet, width of CFRP sheet, total thickness of CFRP sheets and, length of CFRP sheet, which were applied to the network to determine the ultimate flexural load as the output of the model. The obtained results from the proposed relationship showed that it was able to use as a predictive equation for the considered target.Sun, 30 Sep 2018 20:30:00 +0100