Iman Mansouri

Evaluation of peak and residual conditions of actively confined concrete using neuro-fuzzy and neural computing techniques

Abstract This paper investigates the ability of four artificial intelligence techniques, including artificial neural network (ANN), radial basis neural network (RBNN), adaptive neuro-fuzzy inference system (ANFIS) with grid partitioning, and ANFIS with fuzzy c-means clustering, to predict the peak and residual conditions of actively confined concrete. A large experimental test database that consists of 377 axial compression test results of actively confined concrete specimens was assembled from the published literature, and it was used to train, test, and validate the four models proposed in this paper using the mentioned artificial intelligence techniques. The results show that all of the neural network and ANFIS models fit well with the experimental results, and they outperform the conventional models. Among the artificial intelligence models investigated, RBNN model is found to be the most accurate to predict the peak and residual conditions of actively confined concrete. The predictions of each proposed model are subsequently used to study the interdependence of critical parameters and their influence on the behavior of actively confined concrete.

Analysis of influential factors for predicting the shear strength of a V-shaped angle shear connector in composite beams using an adaptive neuro-fuzzy technique

The V-shaped angle shear connector is recognized as to expand certain mechanical properties to the shear connectors, contains adequate ductility, elevate resistance, power degradation resistance under cyclic charging, and high shear transmission, more economical than other shear connectors, for instance, the L-shaped and C-shaped shear connectors. The performance of this shear connector had been investigated by previous researchers (Shariati et al. in Mater Struct 49(9):1–18, 2015), but the strength prediction was not clearly explained. In this investigation, the shear strength prediction of this connector was analyzed based on several factors. The ultimate purpose was to investigate the variations of different factors that were affecting the shear strength of this connector. To achieve this aim, the data (concrete compression strength, thickness, length, height, slope of inclination, and shear strength) were collected from the parametric studies using finite element analysis results for this purpose were input using the ANFIS method (neuro-fuzzy inference system). The finite element analysis results were verified by experimental test results. All variables from the predominant factors that were affected the shear strength of the shear connector (V-shaped angle) were also selected by using the ANFIS process. The results exhibited that the proposed shear connector (V-shaped angle) contained the potentiality to be used practically after several improvements. One option might be the improvement of the testing process for different predictive models with more input variables that will improve the predictive power of the created models.

Seismic Fragility Estimates of LRB Base Isolated Frames Using Performance-Based Design

With improving technology, the idea of using energy dissipater equipment has been strengthened in order to control the structures response in dynamic loads such as wind and earthquake. In this research, we dealt with seismic performance of base isolated structures with lead-rubber bearing (LRB) using incremental dynamic analysis (IDA). For this purpose, 3- and 9-story buildings have been utilized in the SAC project undergoing 22 earthquake records which were far-fault. Plotting the fragility curve for various states of design time period and isolator damping of LRB, it is observed that, by increasing damping, the isolator has not been activated in small spectrum acceleration, which shows that the annual exceedance probability is increased in immediate occupancy (IO) performance level and decreased in life safety (LS) performance level. The results show the reduction of determined failure probability in fragility curves for two levels of performance of uninterrupted use and lateral safety. Likewise obtained results show that, with increasing design time period of isolator, the amount of failure probability is decreased rather than the isolator with smaller design time period, for both LS and IO states. And the isolator illustrates better performance.

A New Method for Evaporation Modeling: Dynamic Evolving Neural-Fuzzy Inference System

Evaporation estimation is very essential for planning and development of water resources. The study investigates the ability of new method, dynamic evolving neural-fuzzy inference system (DENFIS), in modeling monthly pan evaporation. Monthly maximum and minimum temperatures, solar radiation, wind speed, and relative humidity data obtained from two stations located in Turkey are used as inputs to the models. The results of DENFIS method were compared with the classical adaptive neural-fuzzy inference system (ANFIS) by using root mean square error (RMSE), mean absolute relative error (MARE), and Nash-Sutcliffe Coefficient (NS) statistics. Cross validation was applied for better comparison of the models. The results indicated that DENFIS models increased the accuracy of ANFIS models to some extent. RMSE, MARE, and NS of the ANFIS model were increased by 11.13, 11.45, and 6.83% for the Antalya station and 20.11, 12.94%, and 8.29% for the Antakya station using DENFIS.

Effect of Soil Classification on Seismic Behavior of SMFs considering Soil-Structure Interaction and Near-Field Earthquakes

Seismic response of a structure is affected by its dynamic properties and soil flexibility does not have an impact on it when the bottom soil of foundation is supposedly frigid, and the soil flexibility is also ignored. Hence, utilizing the results obtained through fixed-base buildings can lead to having an insecure design. Being close to the source of an earthquake production causes the majority of earthquake’s energy to reach the structure as a long-period pulse. Therefore, near-field earthquakes produce many seismic needs so that they force the structure to dissipate output energy by relatively large displacements. Hence, in this paper, the seismic response of 5- and 8-story steel buildings equipped with special moment frames (SMFs) which have been designed based on type-II and III soils (according to the seismic code of Iran-Standard 2800) has been studied. The effects of soil-structure interaction and modeling of the panel zone were considered in all of the two structures. In order to model radiation damping and prevent the reflection of outward propagating dilatational and shear waves back into the model, the vertical and horizontal Lysmer–Kuhlemeyer dashpots as seen in the figures are adopted in the free-field boundary of soil. The selected near- and far-field records were used in the nonlinear time-history analysis, and structure response was compared in both states. The results obtained from the analysis showed that the values for the shear force, displacement, column axial force, and column moment force on type-III soil are greater than the corresponding values on type-II soil; however, it cannot be discussed for drift in general.

Evaluation of mechanical properties of concretes containing coarse recycled concrete aggregates using multivariate adaptive regression splines (MARS), M5 model tree (M5Tree), and least squares support vector regression (LSSVR) models

This paper investigates the application of three artificial intelligence methods, including multivariate adaptive regression splines (MARS), M5 model tree (M5Tree), and least squares support vector regression (LSSVR) for the prediction of the mechanical behavior of recycled aggregate concrete (RAC). A large and reliable experimental test database containing the results of 650 compressive strength, 421 elastic modulus, 152 flexural strength, and 346 splitting tensile strength tests of RACs with no pozzolanic admixtures assembled from the published literature was used to train, test, and validate the three data-driven-based models. The results of the model assessment show that the LSSVR model provides improved accuracy over the existing models in the prediction of the compressive strength of RACs. The results also indicate that, although all three models provide higher accuracy than the existing models in the prediction of the splitting tensile strength of RACs, only the performance of the LSSVR model exceeds those of the best-performing existing models for the flexural strength of RACs. The results of this study indicate that MARS, M5Tree, and LSSVR models can provide close predictions of the mechanical properties of RACs by accurately capturing the influences of the key parameters. This points to the possibility of the application of these three models in the pre-design and modeling of structures manufactured with RACs.

Assessment of Seismic Vulnerability of Steel and RC Moment Buildings Using HAZUS and Statistical Methodologies

Designer engineers have always the serious challenge regarding the choice of the kind of structures to use in the areas with significant seismic activities. Development of fragility curve provides an opportunity for designers to select a structure that will have the least fragility. This paper presents an investigation into the seismic vulnerability of both steel and reinforced concrete (RC) moment frames using fragility curves obtained by HAZUS and statistical methodologies. Fragility curves are employed for several probability parameters. Fragility curves are used to assess several probability parameters. Furthermore, it examines whether the probability of the exceedence of the damage limit state is reduced as expected. Nonlinear dynamic analyses of five-, eight-, and twelve-story frames are carried out using Perform 3D. The definition of damage states is based on the descriptions provided by HAZUS, which gives the limit states and the associated interstory drift limits for structures. The fragility curves show that the HAZUS procedure reduces probability of damage, and this reduction is higher for RC frames. Generally, the RC frames have higher fragility compared to steel frames.