Optimization of Process Parameters of Friction Welding by Genetic Algorithm

Friction Welding is a variation of pressure welding method. The joint is formed in the solid state, without melting the metal by utilizing the heat generated by friction. Consequently, some experience has already been accumulated in the industrial application of friction welding as well as in the development of the corresponding theories, but still we are way behind to find the optimal friction. This work is a step forward to achieve the best possible design. The purpose of this study is to propose a method to decide near optimal settings of the welding process parameters in friction welding of austenitic stainless steel (AISI 304) by using a Genetic Algorithm. This method tries to find near optimal settings of the welding process parameters through experiments without a model between the input and output variable. It has an advantage of being able to carryout search without modifying the design space, which includes some irregular points. The method suggested in this study is used to determine the welding process parameters by which the desired tensile strength can be obtained in friction welding. The output variable is the tensile strength. The output variable can be determined according to the input variables, which are the Heating Pressure (HP), Heating Time (HT), Upsetting Pressure (UP) and Upsetting Time (UT). This study describes how to obtain near optimal welding conditions over a wide search space conducting relatively small number of experiments. The main consideration in this study is maximization of tensile strength. Also, experimental variation of tensile strength with friction time Is verified theoretically.