ANFIS modeling of rhamnolipid breakthrough curves on activated carbon

Owning to interesting properties of biosurfactants such as biodegradability and lower toxicity, they have broad application in the food industry, healthy products, and bioremediation as well as for oil recovery. The present study was aimed to develop a GA-ANFIS model for predicting the breakthrough curves for rhamnolipid adsorption over activated carbon. To that end, a set of 296 adsorption data points were utilized to train the proposed FIS structure. Different graphical and statistical methods were also used to evaluate the model's accuracy and reliability. Results were then compared to those of the previously reported Artificial Neural Network (ANN) and Group Method Data Handling (GMDH) models. Absolute average deviation percentage (%AAD) for the proposed model was 1.71% which demonstrates lower value compared to those of ANN and GMDH models. The present ANFIS model can be of immense value for investigating breakthrough curve of rhamnolipid and also it can help chemist who dealing with biosurfactants.