Abstract: A method of nonlinear multiple orthogonal regression assembling design was applied in the investigation of the resistance spot welding process on galvanized steel sheet.The indexes studied in experiments were nugget geometry and tensile-shear strength of spot welds.Furthermore,four process parameters,namely welding current,electrode force,welding current duration and preheat current,and interactions among them were considered as the factors impacting indexes.The experimental results showed that there was a more accurate prediction on nugget size and mechanical properties of spot welds by the models optimized.Based on these prediction results,the optimization of welding process also was realized by the analysis to the effect of parameters and interactions on the welding quality.