This article focuses on the development of a comprehensive method for optimization of casting parameters including stirring time and speed of stirrer. Particulate AA6061 aluminum alloy matrix composites were produced by compocasting. First, the effects of extrusion and particles coating on the microstructures and mechanical properties of the composites were investigated. Then, a hybrid algorithm based on PSO and GA was implemented in order to solve the global problems and optimize the coefficients of equations with much better performance, resulting in higher possibility for industry application. PSO evolved the population over a certain number of generations, retained the best M particles and excluded the remaining pop size-M particles. Selection, crossover and mutation GA operators generated pop size M new individuals and combined them with the best M particles to form a new population for the next generation. The model based on combination of GA and PSO is capable to predict with greater reliability than single optimization methods including ACO and multiple linear regression.