In the present study, two mathematical models were developed to optimize the surface roughness for machining condition of Cedar of Lebanon pine (Cedrus libani). Taguchi approach was applied to examine the effect of CNC processing variables. Quality characteristics parameters were selected as arithmetic average roughness (R-a) and average maximum height of the profile (R-z) for wood material. Analysis of variance (ANOVA) was used to determine effective machining parameters. Developed mathematical models using response surface methodology (RSM) were optimized by a combined approach of the Taguchi's L-27 orthogonal array based simulated angling algorithm (SA). Optimum machining levels for determining the minimum surface roughness values were carried out three stages. Firstly, the desirability function was used to optimize the mathematical models. Secondly, the results obtained from the desirability function were selected as the initial point for the simulated angling algorithm. Finally, the optimum parameter values were obtained by using simulated angling algorithm. Minimum R-a value was obtained spindle speed of 17377 rpm, feed rate of 2,012 m/min, tool radius of 8 mm and depth of cut of 2,009 mm by using desirability function based simulated angling algorithm. For R-z these results were found as 16980 rpm, 2,004 m/min, 8,001 mm and 2,003 mm. The R-square values of the R-a and R-z were 95,91 % and 96,12 %, respectively. The proposed models obtained the minimum surface roughness values and provided better results than the observed values.