Insight into Fuzzy Logic and Response Surface Methodologies for Predicting Wool and Polyamide Dyeing Behaviors with a Biological Extract of Juglans Regia

In our previous work, we demonstrated that the dyeing of polyamide and wool fibers with methanolic extract of Juglans Regia fractions depended on several experimental conditions. In the current investigation, Fuzzy logic and response surface methodologies were compared and used to predict the dyeing behavior of wool and polyamide fibers with Juglans R. extract. The operational conditions studied here were: Juglans extract concentration (0.05–0.5 %), time of dyeing (5–45 min), and temperature (50–95 °C) as input variables. Data was checked by measuring the color strength ( K / S ) as an output variable. To carry out the best suitable model, the root mean square error (RMSE), the relative mean absolute error (RMAE), and the mean relative percent error (MRPE) were used as performance criteria. Results indicated that MRPE values ranged between 0.25 % and 0.6 % which could be considered low and significant, according to literature. The RMSE values were less than K / S standard deviation. Overall, both methodologies proved their ability to predict the color strength measurement. Comparing their performance criteria, fuzzy logic methodology gave the least errors values suggesting that this method was more powerful than response surface methodology.