In power plants, flue gases cause a severe corrosion damage in its metallic parts such as flue duct, heat exchanger and boiler. Coating still one of the effective techniques to eliminate his damage. A robust fuzzy model of the surface roughness profile such average roughness; Ra and average of ten-point height; Rz of flue gas duct coated by protective composite coating from epoxy and Nano-particles was built based on the experimental data set. The proposed model consists of four different Nano-particles (ZnO, ZrO2, SiO2 and NiO) with 2%, 4%, 6%, and 8%. Response surface methodology (RSM) and Fuzzy logic system approach were used to optimize the process parameters and identify the optimal conditions for minimum surface roughness of this coated duct. In order to prove the superiority of the proposed fuzzy model, the model results are compared with those obtained by ANOVA. The coefficient of determination and the root mean square error (RMSE) are used as metrics of the comparison. For Ra, for the first output response, using ANOVA, the coefficient of determination values is 0.9137 for training value and 0.4037 for prediction value. Similarly, for Rz the second output response, the coefficient of determination results is 0.9695 and 0.4037, respectively, for training and prediction. In the Fuzzy modelling of Ra: the first output response, the RMSE values are 0.0 and 0.1455, respectively, for training and testing. The values for the coefficient of determination are 1.00 and 0.9807, respectively, for training and testing. The obtained results proved the superiority of fuzzy modelling. For modelling the second output response Rz, the RMSE values are 0.0 and 0.0421respectively for training and testing and the coefficient of determination values are 1.00 and 0.9959, respectively for training and testing. The observed R^2 value, adjusted R^2 , predicted R^2 , and F-values indicate that the developed