Pouyan PressJournal of Soft Computing in Civil Engineering2588-28723420191001Fuzzy-Based Approach to Predict the Performance of Shear Connectors in Composite Structures11110385010.22115/scce.2020.215906.1165ENSeyed Meisam KalantariDepartment of Civil and Environmental Engineering, Western University, Ontario, CanadaSeyedmehdi MortazaviPh.D. Candidate, Faculty of Civil Engineering, Semnan University, Semnan, Iran0000-0003-2239-0997Mohammadsoroush TafazzoliAssistant Professor, School of Design and Construction Management, Washington State University, Washington, United StatesJournal Article20200115Shear connectors in steel-concrete composite frames are essential elements to transfer the shear between steel and concrete. Several parameters must be considered in predicting the strength of these connectors. This research aims to estimate the performed rib shear strength of connectors in composite frames. To this end, four variables including the compressive strength of concrete, area of dowels, the transverse area in rib holes, and also connector height, are applied to a neuro-fuzzy model and the shear strength is selected as the target of the system. The model is trained using an experimental database and validated with an acceptable error. The estimated shear strength of connectors were satisfactorily similar to the measurements reported by the laboratories.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28723420191001Physical and Physic-Chemical Based Optimization Methods: A Review122710345610.22115/scce.2020.214959.1161ENBehrooz VahidiProfessor, Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran0000-0002-9430-9468Amin Foroughi NematolahiPh.D. Student, Department of Electrical Engineering, Amirkabir University of Technology, Tehran, IranJournal Article20200108Optimization techniques can be divided to two groups: Traditional or numerical methods and methods based on stochastic. The essential problem of the traditional methods, that by searching the ideal variables are found for the point that differential reaches zero, is staying in local optimum points, can not solving the non-linear non-convex problems with lots of constraints and variables, and needs other complex mathematical operations such as derivative. In order to satisfy the aforementioned problems, the scientists become interested on meta-heuristic optimization techniques, those are classified into two essential kinds, which are single and population-based solutions. The method does not require unique knowledge to the problem. By general knowledge the optimal solution can be achieved. The optimization methods based on population can be divided into 4 classes from inspiration point of view and physical based optimization methods is one of them. Physical based optimization algorithm: that the physical rules are used for updating the solutions are:, Lighting Attachment Procedure Optimization (LAPO), Gravitational Search Algorithm (GSA) Water Evaporation Optimization Algorithm, Multi-Verse Optimizer (MVO), Galaxy-based Search Algorithm (GbSA), Small-World Optimization Algorithm (SWOA), Black Hole (BH) algorithm, Ray Optimization (RO) algorithm, Artificial Chemical Reaction Optimization Algorithm (ACROA), Central Force Optimization (CFO) and Charged System Search (CSS) are some of physical methods. In this paper physical and physic-chemical phenomena based optimization methods are discuss and compare with other optimization methods. Some examples of these methods are shown and results compared with other well known methods. The physical phenomena based methods are shown reasonable results.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28723420191001Application of Random Forest Regression in the Prediction of Ultimate Bearing Capacity of Strip Footing Resting on Dense Sand Overlying Loose Sand Deposit28408997510.22115/scce.2019.137910.1080ENRakesh KumarDuttaProfessor, Department of Civil Engineering, National Institute of Technology, Hamirpur, Himachal Pradesh, India0000-0002-4611-9950Tammineni GnananandaraoResearch Scholar, Department of Civil Engineering, National Institute of Technology, Hamirpur, Himachal Pradesh, India0000-0002-3332-8083Ajay SharmaPG Student, Department of Civil Engineering, National Institute of Technology, Hamirpur, Himachal Pradesh, IndiaJournal Article20180628The paper presents the prediction of the ultimate bearing capacity of the strip footing resting on layered soil (dense sand overlying loose sand) using random forest regression (RFR). In this study, 181 data collected from literature were used. 71 % of the total data was randomly selected for training the model and the rest of the data were utilized for the testing purpose. The various input parameters were friction angle of the dense sand layer (<em>f</em><sub>1</sub>), friction angle of the loose sand layer (<em>f</em><sub>2</sub>), unit weight of the dense sand layer (<em>g</em><sub>1</sub>), unit weight of the loose sand layer (<em>g</em><sub>2</sub>), ratio of the thickness of the dense sand layer below base of the footing to the width of footing (<em>H/B</em>), ratio of the depth of the footing to the width of the footing (<em>D/B</em>) and (<em>H+D</em>)/<em>B</em>. Ultimate bearing capacity was the output in this study. Performance measures were used in order to make the comparison with the artificial neural network (ANN) and M5P model tree. The result of this study revealed that the performance of the RFR was superior to M5P and ANN. The results of the sensitivity analysis reveals that the unit weight and the friction angle of the loose sand layer were the most important parameters affecting the output ultimate bearing capacity of the strip footing resting on the layered soils.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28723420191001Life Cycle Cost GA Optimization of Repaired Reinforced Concrete Structures Located in a Marine Environment415010082110.22115/scce.2020.212823.1149ENAtiye FarahaniAssistant Professor, Department of Civil Engineering, Tafresh University, Tafresh, Iran0000-0003-1658-7021Journal Article20191222Life-Cycle-Cost (LCC) analysis of corroded structures located in corrosive marine environments considers the time-dependent resistance and loading affect, and repair and maintenance scenarios applied during life time of these structures. Finding the optimum repair and maintenance scenario for a corroded reinforced concrete (RC) structure is a significant process to select a repair and maintenance scenario with minimum LCC and maximum service lifetime. For this purpose, a finite element (FE) model is applied to assess the time-dependent capacity of corroded RC circular column using nonlinear analysis. In corrosion initiation phase, empirical chloride diffusion and surface chloride concentration models obtained for silica fume RC under long-term exposure in splash zone of Bandar-Abbas coasts, located in south side of Iran, and in corrosion propagation phase, empirical corrosion current density model for splash zone of a marine environment in literature is used for modeling of corrosion process. In this analysis, the influence of a number of repair or rehabilitation scenarios on the performance of a corroded circular RC column due to chloride-induced corrosion, including five different concrete surface coatings used on the external surface of concrete, four different increasing concrete cover thickness and using the new longitudinal and horizontal reinforcements after the initial cracking of concrete cover are investigated. These 11 different scenarios with considering a scenario without any repair are optimized by Genetic Algorithm (GA) based on minimum LCC cost and 40 years failure time in terms of corrosion.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28723420191001Selecting the Suitable Tunnel Supporting System Using an Integrated Decision Support System, (Case Study: Dolaei Tunnel of Touyserkan, Iran)516610184710.22115/scce.2020.212995.1150ENSina Shaffiee HaghshenasM.Sc. Student of Civil Engineering, Department of Civil Engineering, University of Calabria, Rende, Italy0000-0003-2859-3920Reza MikaeilAssociate Professor of Mining Engineering, Faculty of Mining and Metallurgical Engineering, Urmia University of Technology (UUT), Urmia, Iran0000-0001-8404-3216Mehdi Abdollahi KamranAssistant Professor of Industrial Engineering, Faculty of Industrial Engineering, Urmia University of Technology (UUT), Urmia, IranDepartment of Logistics, Tourism, and Service Management, Faculty of Business and Economics, German University of Technology (GUtech), Muscat, OmanSami Shaffiee HaghshenasM.Sc. Student of Civil Engineering, Department of Civil Engineering, University of Calabria, Rende, Italy0000-0002-9301-8677Hojjat Hosseinzadeh GharehgheshlaghAssistant Professor of Mining Engineering, Faculty of Mining and Metallurgical Engineering, Urmia University of Technology (UUT), Urmia, Iran0000-0002-7763-9596Journal Article20191223The main goal of this study is the selection of an appropriate tunnel supporting system according to the combination of FDAHP method (Fuzzy Delphi Analytic Hierarchy Process) and ELECTRE (Elimination and Choice Expressing Reality) technique. This integrated decision support system provides useful support for selecting a tunnel supporting system. The weights of the criteria was determined by FDAHP method, and a suitable tunnel supporting system for Dolaei tunnel of Touyserkan in Iran was determined by the ELECTRE. The study was supported by the results obtained from a questionnaire carried out to understand the opinions of experts in this subject. According to surveys in this regard, six significant criteria and five alternatives such as reinforced shotcrete, metal frames, concrete prefabricated segments, in situ reinforced concrete implementation, rock bolt and reinforced shotcrete implementation have been examined. The obtained results showed that the rock bolt with reinforced shotcrete supporting system is the most suitable.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28723420191001Predicting the Earthquake Magnitude along Zagros Fault Using Time Series and Ensemble Model677710184610.22115/scce.2020.213197.1152ENAydin ShishegaranPh.D. Candidate, Environmental Engineering, School of Civil Engineering, Iran University of Science and Technology, Tehran, IranHamed TaghavizadeResearch Assistant, Geotechnical Earthquake Engineering, International Institute of Earthquake Engineering and Seismology, Tehran, IranAlireza BigdeliMaster of Science Student, Structural Engineering, School of Civil Engineering, Iran University of Science and Technology, Tehran, IranArshia ShishegaranMaster of Science Student, Structural Engineering, School of Civil Engineering, Islamic Azad University, Tehran, IranJournal Article20191225Predicting the earthquake magnitude is a complex problem, which has been carried out in recent years. The machine learning, geophysical, and regression methods were used to predict earthquake magnitude in literature. Iran is located in a highly seismically active area; thus, earthquake prediction is considered as a great demand there. In this study, two time series algorithms are utilized to predict the magnitude of the earthquake based on previous earthquakes. These models are autoregressive conditional heteroscedasticity (GARCH), autoregressive integrated moving average (ARIMA), and the combination of ARIMA and GARCH by multiple linear regression (MLR) technique (model 3). The 9017 events are used to train and predict earthquake magnitude. On the other hand, 6188 events are applied for training models, and then 2829 events are utilized for testing it. The statistical parameters, such as correlation coefficient, root mean square error (RMSE), normalized square error (NMSE), and fractional bias, are calculated to evaluate the accuracy of each model. The results demonstrate that the ARIMA and model 3 can predict future earthquake magnitude better than other models.Pouyan PressJournal of Soft Computing in Civil Engineering2588-28723420191001GIS 3D and Science of Augmented Reality: Modeling a 3D Geospatial Environment788710374710.22115/scce.2020.212254.1148ENAdel FridhiNational Engineers School of Tunis, LRSITI (ENIT), TunisiaAli FrihidaNational Engineers School of Tunis, LRSITI (ENIT), TunisiaJournal Article20191217The objective of this paper is to integrate all the 3D data into a Geographic Information System (GIS), from *.skp files that it modeled by applying augmented reality (AR). The application of the RA to a 3D model integrated into the GIS will be a valuable means of communication for the enhancement of our learning environment. Accessible to all, including those who cannot visit the site, it allows discovering for example ruins in a pedagogical and relevant way. From an architectural point of view, the 3D model provides an overview and a perspective on the constitution of the environment, which a 2D document can hardly offer. 3D navigation and the integration of 2D data into the model make it possible to analyze the remains in another way, contributing to the faster establishment of new hypotheses. Complementary to the other methods already exploited in geology, the analysis by 3D vision is, for the scientists, a non-negligible gain of time which they can thus devote to the more in-depth study of certain hypotheses put aside.