Abstarct: The main cause of the damage in buildings during the earthquake is their response to earth movements, or, in other words, how the buildings deal with the earthquake forces. Today, one of the most common methods for analyzing and designing structures against earthquakes is spectral analysis, which for many years has been the basis for calculating earthquake forces on structures. One major drawback of the spectral analysis method for the analysis and design of structures is its inability to provide timely information on the response and structure behavior, which is the basis for the preparation of the response spectrum. On the other hand, possessing a signal corresponding to the design spectrum is one of the most important issues in nonlinear time histories analysis. Therefore, due to the advantages of using the time history analysis of the earthquake signal, and the lack of suitable signal in many areas, it is necessary in many cases to produce a number of artificial signals in some areas. In the proposed method, first, some recorded accelerograms are selected baxsed on the soil condition at the recording station. The soils in these stations are divided into two groups of soil and rock according to their measured shear wave velocity. These accelerograms are then analyzed using wavelet transform. Next, artificial neural networks ability to produce reverse signal from response spectra is used to produce wavelet coefficients. Furthermore, some evolutionary computing algorithm is employed to optimize the network weight and bias matrices by searching in a wide range of values and prevent neural network convergence on local optima. At the end site specific accelerograms are produced. In this dissertation a number of recorded accelerograms in Iran are employed to test the neural network performances and to demonstrate the effectiveness of the method. It is shown that using synthetic time series analysis, evolutionary computing algorithm, neural network and wavelet transform will increase the capabilities of the algorithm and improve its speed and accuracy in generating accelerograms compatible with site specific response spectra for different site conditions.