---

The prediction of the ultimate bearing capacity of the pile under axial load is one of the important issues for many researches in the field of geotechnical engineering. In recent years, the use of computational intelligence techniques such as different methods of artificial neural network has been developed in terms of physical and numerical modeling aspects. In this study, a database of 100 prefabricated steel and concrete piles is available from existing publications to solve issues related to pile’s bearing capacity analysis. Three different artificial neural network algorithms were developed for comparing and verifying the obtained results at analyzing the bearing capacity of pile in soils. During the modeling process, the geometric properties of different piles, soil materials properties, friction angle and flap numbers (hammer blows) were selected as input parameters to the selected network and the output from the network was considered as the bearing capacity of the pile. Finally, the performance of radial base function type neural networks was compared with model tree method and predictive neural networks based on different learning algorithms such as Levenberg-Marquardt and Bayesian Regulation Back Propagation Algorithms. It was observed that the radial base neural network in some cases achieved better results from accuracy based on common statistical parameters such as correlation coefficient, mean absolute error percentage and root mean square error as compared to other stated methods and it showed the acceptable performance in modeling and predicting the desired output close to the target's results.

---

This article presents numerical studies on semi-active seismic response control of structures equipped with Magneto-Rheological (MR) dampers. A multi-layer artificial neural network (ANN) was employed to mitigate the influence of time delay, This ANN was trained using data from the El-Centro earthquake. The inputs of ANN are the seismic responses of the structure in the current step, and the outputs are the MR damper voltages in the current step. The required training data for the neural controller is generated using genetic algorithm (GA). Using the El-Centro earthquake data, GA calculates the optimal damper force at each time step. The optimal voltage is obtained using the inverse model of the Bouc-Wen based on the predicted force and the corresponding velocity of the MR damper. This data is stored and used to train a multi-layer perceptron neural network. The ANN is then employed as a controller in the structure. To evaluate the efficiency of the proposed method, three- story, seven- story and twenty-story structures with a different number of MR dampers were subjected to the Kobe, Northridge, and Hachinohe earthquakes. The maximum reduction in structural drifts in the three-story structure are 13.05%, 39.90%, 15.89%, and 8.21%, for the El-Centro, Hachinohe, Kobe, and Northridge earthquakes, respectively. As the control structure is using a pre-trained neural network, the computation load in the event of an earthquake is extremely low. Additionally, as the ANN is trained on seismic pre-step data to predict the damper's current voltage, the influence of time lag is also minimized.