In this thesis wavelet neural network were used to predict viscosity of the fluid mixture in a wide range of temperature and pressure. Wavelet neural networks (WNN) combing the properties of the wavelet transform and the advantages of Artificial Neural Networks (A) have attracted great interest and become a popular tool for various fields of mathematics and engineering. Using this method, with the inputs temperature, density and, molar fraction output viscosity was predicted. kind of artificial neural network algorithm that was used, the propagation error algorithm with the gradient descent algorithm , that this type of algorithm algorithms with supervisor ( observer) is. The activation functions of the wavelet nodes in the hidden layer are derived from a Morlet mother wavelet. The results of the computational process with this type of artificial neural network algorithm with the results of equations in predicting viscosity of articles in a wide range of pressure and temperature were compared. Comparing these results showed that wavelet neural networks used, have many power in prediction of viscosity and the ability to compete with methods using equations of theoretical and experimental. Other advantage use of artificial neural networks in addition predict better results for the viscosity of the fluid mixture is in, solved need to provide potential models and complex calculations to obtain the integral and in a word, this networks with regard to high expansion they reduce need to the complex equatio can also used as a tool for simultaneous prediction thermodynamics properties.