Estimation of tensile strength of ductile iron friction welded joints using hybrid intelligent methods

Abstract

A hybrid intelligent method for evaluation of near optimal settings of friction welding process parameters of ductile iron was presented. The optimization of welding parameters was carried out in automatic cycle with the use of support vector regression (SVR), genetic algorithm (GA) and imperialist competitive algorithm (ICA). The method suggested was used to determine welding process parameters by which the desired tensile strength was obtained in the friction welding of ductile iron. The highest tensile strength (TS) of 256.93 MPa was obtained using SVR plus GA method for the following friction welding parameters: heating force 40 kN, heating time 300 s and upsetting force 10.12 kN. The samples were welded by friction and subjected to the tensile strength test. The optimized values obtained by means of these hybrid techniques were compared with the experimental results. The application of hybrid intelligent methods allowed to increase the tensile strength joints from 211 to 258 MPa for the friction welder ZT–14 type.