In this paper a semi-active structural damage control strategy using MR dampers and Neural Networks is presented. A multilayer feed-forward neural network has been designed. The input layer is relative displacement of stories and the output layer is the voltage needed for MR damper. The neural network is learned to predict the voltage needed for MR damper that can minimize the Park & Ang damage index of structure. Genetic Algorithm has been used to learn the neural network. The Park & Ang damage index of the structure has been used as the fittnees function of the genetic Algorithm. To evaluate the structural control system a nonlinear 3 story benchmark building has been selected. The results show the the proposed structural control system can effectively reduce the Park & Ang damage index of the structure.

Dimensional synthesis of mechanisms to trace given points is an important issue in mechanism and machine science. Having no exact solution makes this issue an optimization problem. This study offers an optimization approach for the dimensional synthesis of planar mechanisms. Four-bar mechanisms having one degree of freedom (DOF) are chosen as the configurations. The proposed method is implemented by establishing the objective functions with specified constraints and searching for the results by using an optimization Algorithm. Genetic Algorithm (GA) in Optimization Toolbox-Matlab® is selected as a solver. Different types of four-bar mechanisms like crank-rocker and double-crank including different target points are performed. Mechanisms are depicted by resulted parameters and a Matlab® script prepared plays their animations. As a result, it is proved that the mechanisms whose dimensional properties are obtained by the GA solver have a good tracing capability for the desired paths. This study has the property of being a design guide. Its application is not limited to four bar mechanism. Planar mechanisms with different configurations can be easily synthesized by using this technique.

One of the major factors on the amount of water resources is river flow which is so dependent to the hydrologic and meteorologic phenomena. Simulation and forecasting of river flow makes the decision maker capable to effectively manage the water resources projects. So, simulation and forecasting models such as artificial neural networks (ANNs) are commonly used for simulation and predicting the exact value of such factors. In this research, the Dez River basin was selected as the case study. This paper investigates the effectiveness of temperature, precipitation and inflow factors and the lag time of those factors in inflow simulation and forecasting. Genetic Algorithm (GA) has been thus used as an optimization tool, determining the optimum composition of the effective variables. Thus, in a flow simulation and forecasting model, the number of hidden layers, effective neurons in each layer, effective meteorologic and hydrologic parameters and also the lag time of each factor of flow simulation and forecasting has been considered as decision variables, and GA has been used to obtain the best combination of those variables. In this study, minimization of the total mean square error (MSE) has been considered as the objective function. Results show GA's effectiveness in flow simulation and forecasting with consistent accuracy. The value of R2 criterion has been obtained 0.86 and 0.79 in the simulation and forecasting models, respectively. The results also showed superiority replies obtained from the simulation model to the prediction model. One of the reasons for this superiority can be considering the meteorological factors in the current month in river flow simulation.

A Genetic Algorithm (GA) method for optimization of multi-reservoir systems operation is proposed in this paper. In this method, the parameters of operating policies are optimized using system simulation results. Hence, any operating problem with any sort of objective function, constraints and structure of operating policy can be optimized by GA. The method is applied to a 3-reservoir system and is compared with two traditional methods of Stochastic Dynamic Programming and Dynamic Programming and Regression. The results show that GA is superior both in objective function value and in computational speed. The proposed method is further improved using a mutation power updating rule and a varying period simulation method. The later is a novel procedure proposed in this paper that is believed to help in solving computational time problem in large systems. These revisions are evaluated and proved to be very useful in converging to better solutions in much less time. The final GA method is eventually evaluated as a very efficient procedure that is able to solve problems of large multi-reservoir system which is usually impossible by traditional methods. In fact, the real performance of the GA method starts where others fail to function.

The purpose of this paper is to predict stock prices using Hybrid GA-SVM Algorithm. Predicting time series such as stock price forecasting is one of the most important issues in financial field. In real life, identifying time series movements in stock price indices is very complex. Therefore, the use of a classical model alone cannot accurately predict stock price indices. Hence, by using combined methods, uncertainty in forecasting can be reduced. In stock price forecasting in financial sector, more than 100 indicators have been created to understand stock market behavior, so, identifying the appropriate indicators is a challenging problem. One of the techniques that has recently been studied for serial forecasting is support regression Vector (SVR) or machine support vector (SVM). This study uses the GA-SVM hybrid Algorithm to predict the stock price index. Experimental results show that Hybrid GA-SVM Algorithm provides a more appropriate and promising alternative to stock market forecasting.

In this article, a finite horizon, multi product and multi period economic order quantity like seasonal items is considered where demand rate is deterministic and known but variable in each period. The order quantities of items come in batch sizes and the end of the period order quantity and, consequently, demand of customers are zero. In addition, storage space is constrained and the problem was considered under all units discount (AUD) policy. The modeling technique used for this problem is mixed binary integer programming. The objective was to find the minimization optimal order quantities under time value of money over the finite horizon. The inventory control system costs include three costs: ordering cost, holding cost, and purchase cost. In order to solve the proposed model, a genetic Algorithm (GA) is applied. Finally, we provide a number of examples in order to illustrate the Algorithms further.

In this paper an optimized high frequency lumped model of Induction motor is presented. Model parameters are identified and optimized using Genetic Algorithm (GA). A novel model and approach in an improved high frequency based on GA for parameter identification are used. At first, parameters are limited and then fitted using GA for best fitting. The proposed model considered accurate simulation of both differential and common mode behavior in the EMI-frequency range from 100 Hz to 30MHz. Model parameters which extracted from GA are compared with experimental data in both magnitude and phase at the same time and results show a good accordance between the experimental results and simulation results of the proposed model. A least mean square (LMS) method was used with a GA optimization method to solve the identification problem. The proposed model is suitable to obtain the simulation models to predict high frequency conducted Electromagnetic Interference (EMI), over voltage on terminated motor and common mode current in cable fed induction motor.

In this paper we investigate the performance of simulated annealing (SA) and genetic Algorithm (GA) in preventive part replacement for minimum downtime maintenance planning. Therefore some evaluation criteria are explained in order to analyze the performance of the Algorithms. So it can be decided which Algorithm is more suitable to apply in preventive part replacement.

A teaching-learning-based optimization (TLBO) Algorithm is a new population-based Algorithm applied to some applications in the literature successfully. In this paper, a hybrid genetic Algorithm (GA) -TLBO Algorithm is proposed for the capacitated three-stage supply chain network design (SCND) problem. To escape infeasible solutions emerged in the problem of interest due to realistic constraints, a combination of a random key and priority-base encoding scheme is proposed. To assess the quality of the proposed hybrid GA-TLBO Algorithm, some numerical examples are conducted. Then, the results are compared with those of GA, TLBO and exact Algorithms.