---

This study investigates the prediction model of compressive strength of self–compacting concrete (SCC) by utilizing soft computing techniques. The techniques consist of adaptive neuro–based fuzzy inference system (ANFIS), artificial neural network (ANN) and the hybrid of particle swarm optimization with passive congregation (PSOPC) and ANFIS called PSOPC–ANFIS. Their performances are comparatively evaluated in order to find the best prediction model. In this study, SCC mixtures containing different percentage of nano SiO₂ (NS), nano–TiO₂ (NT), nano–Al₂O₃ (NA), also binary and ternary combining of these nanoparticles are selected. The results indicate that the PSOPC–ANFIS approach in comparison with the ANFIS and ANN techniques obtains an improvement in term of generalization and predictive accuracy. Although, the ANFIS and ANN techniques are a suitable model for this purpose, PSO integrated with the ANFIS is a flexible and accurate method due tothe stronger global search ability of the PSOPC algorithm.

---

The purpose of this study is to evaluate the long-term vertical deformations of segmented pre-tensioned concrete bridges by a new approach. It provides a practical and reliable method for calculating the amount of long-term deformation based on creep and shrinkage in segmented prestress bridges. There are various relationships for estimating the creep and shrinkage of concrete. The analytical results of existing models can be very different, and the results are not reliable. In this paper, the different existing relationships are written in MATLAB software. After calculation, the values of the creep and shrinkage are stored. Then a sample bridge is simulated in the CSI-Bridge software, and different values of creep and shrinkage are allocated separately. Therefore, the data are analyzed, and its maximum deformation value is extracted at a critical span (D_v-max). Assigning different amount of creep and shrinkage to the model results in different values  of D_v-max. In the next step, all D_v-max values  resulting from the change in creep and shrinkage contents should be re-introduced to MATLAB code to perform the calculation of the failure curve, and extract the corresponding D_v-max values at 95% probability. In a new approach, fragility curves are used to obtain the corresponding creep and shrinkage values corresponding to the desired probability percentage. Thus, instead of simulating several models, only one model is simulated. The results of the analysis of a bridge sample in this study indicate acceptable accuracy of the proposed solution for the 95% probability.

---

In this article, the optimum design of a reinforced concrete solid slab is presented via an efficient hybrid metaheuristic algorithm that is recently developed. This algorithm utilizes the mouth-brooding fish (MBF) algorithm as the main engine and uses the favorable properties of the colliding bodies optimization (CBO) algorithm. The efficiency of this algorithm is compared with mouth-brooding fish (MBF), Neural Dynamic (ND), Cuckoo Search Optimization (COA) and Particle Swarm Optimization (PSO). The cost of the solid slab is considered to be the objective function, and the design is based on the ACI code. The numerical results indicate that this hybrid metaheuristic algorithm can to construct very promising results and has merits in solving challenging optimization problems.