---

In this paper the performance of Artificial Neural Networks (ANNs) and Adaptive Neuro- Fuzzy Inference Systems (ANFIS) in simulating the inverse dynamic behavior of Magneto- Rheological (MR) dampers is investigated. MR dampers are one of the most applicable methods in semi active control of seismic response of structures. Various mathematical models are introduced to simulate the dynamic behavior of MR dampers. The Modified Bouc-Wen model is an appropriate model that has an acceptable accuracy in calculating the generated force of dampers compared to others. In this model displacement and voltage of a MR damper are known while the force generated by MR damper is considered as the unknown. Because of highly nonlinear characteristics of modified bouc-wen model determination of inverse dynamic behavior of MR dampers are generally done using ANNs and ANFIS. Since the ANNs and ANFIS have different mechanisms for emulating desired functions, their responses may be different. In this research the performance of a Back Propagation Neural Network (BPNN), Radial Basis Functions Neural Network (RBFNN) and ANFIS in estimating the inverse dynamic behavior of MR dampers are compared. The results emphasize on the advancement of ANFIS to the other methods studied in estimation of inverse dynamic behavior of MR dampers.

---

In the area of semi-active control of civil structures, Magneto-Rheological (MR) damper has been an efficient mechanism for reducing the seismic response of structures. In this paper, an effective method based on defining an optimization problem for designing MR dampers has been proposed. In the proposed method, the parameters of semi-active control system are determined so that the maximum response of structure is minimized. To solve the optimization problem, the Genetic algorithm (GA) has been utilized. The modified Bouc-Wen model has been used to represent the dynamic behavior of MR damper while to determine the input voltage at any time step, the clipped optimal control algorithm with LQR controller has been applied. To evaluate the performance of the proposed method, a ten-storey shear frame subjected to the El-Centro excitation and for two different kinds of objective functions, optimal MR dampers have been designed. Then the performance of optimal MR damper has been tested under different excitations. The results of the numerical simulations have shown the effectiveness of the proposed method in designing optimal MR dampers that have the capability of reducing the response of the structures up to a significant level. In addition, the effect of selecting a proper objective function to achieve the best performance of MR dampers in decreasing different responses of structure has been shown.

---

Semi-active base isolation system has been proposed mainly to mitigate the base drift of isolated structures while in most cases, its application causes the maximum acceleration of superstructure to be increased. In this paper, designing optimal semi-active base isolation system composed of linear base isolation system with low damping and magneto-rheological (MR) damper has been studied for controlling superstructure acceleration and base drift separately and simultaneously. A multi-objective optimization problem has been defined for optimal design of semi-active base isolation system which considers a linear combination of maximum acceleration and base drift as objective function where Genetic algorithm (GA) has been used to solve the optimization problem. H₂/Linear Quadratic Gaussian (LQG) and clipped-optimal control algorithms have been used to determine the desired control force and the voltage of MR damper in each time step. For numerical simulation, a four-story base isolated shear frame has been considered and for different values of weighting parameter in objective function, optimal semi-active base isolation system has been designed under various design earthquakes. The results show that by using base isolation system and supplemental MR damper, the superstructure acceleration and base drift can be suppressed significantly. Also, it has been concluded that by selecting proper values for maximum acceleration and base drift related weighting parameters in objective function, it is possible to mitigate the maximum acceleration and base drift simultaneously. Furthermore, semi-active control system has worked successfully under testing earthquakes regarding design criteria.

---

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.

---

In this study, the response of semi-actively controlled structures is investigated, with a focus on the effects of magneto-rheological (MR) damper distribution on the seismic response of structures such as drift and acceleration. The proposed model is closed loop, and the structure's response is used to determine the optimal MR damper voltage. A Fuzzy logic controller (FLC) is employed to calculate the optimum voltage of MR dampers. Drifts and velocities of the structure’s stories are used as FLC inputs. The FLC parameters and the distribution of MR dampers across stories are determined using the NSGA-II, when the structure is subjected to the El-Centro earthquake, so as to minimize the peak inter-story drift ratio and peak acceleration simultaneously. The efficiency of the proposed approach is illustrated through a twenty-story nonlinear benchmark structure. Non-dominated solutions are obtained to minimize the inter-story drift and acceleration of structures and Pareto front produced. Then, the non-dominated solutions are used to control the seismic response of the benchmark structure, which was subjected to the Northridge, Kobe, and Hachinohe earthquake records. In the numerical example the maximum drift and acceleration decrease by about 36.3% and 15%, respectively, in the El-Centro earthquake. The results also demonstrate that the proposed controller is more efficient in reducing drift than reducing acceleration.