Aluminum can't successfully be arc welded in an air environment, due to the affinity for oxygen. If fusion welded in normal atmosphere oxidization readily happens and this outcome in both slag inclusion and porosity in the weld, greatly reducing its mechanical properties. To overcome these problems one of the most common ways of welding aluminum has been to a suggestion the friction stir welding. To work in this area needs to do a tremendous amount of experience and this thesis has provided general Specification of the process of friction stir welding pipes using three methods regression analysis (RA),Response surface methodology(RSM) and artificial neural networks (ANN) to infer the mechanical properties has this Specification so for the thickness of 2 to 4 mm, depending on the rotational speed from 485 to 1800(RPM) travel speed from 4 to 10 (mm/min to work comparative between three method ( (RA), (RSM) and (ANN)) through total erro (2) (PDF) Total Error Analysis Role of Predicting Mechanical Properties By Friction Stir Welded Aluminum pipes. Available from: https://www.researchgate.net/publication/317225616_Total_Error_Analysis_Role_of_Predicting_Mechanical_Properties_By_Friction_Stir_Welded_Aluminum_pipes