Data Driven Aerodynamic Modeling Using Mamdani Fuzzy Inference Systems

In this paper, an application of Mamdani fuzzy model has been presented for aerodynamic modeling of the fixed wing aircraft. Here, Mamdani model is used to represent the nonlinear dynamics of the aircraft. Efficacy of the rule based model has been demonstrated for the identification of the yawing moment coefficient of Advanced Technologies Testing Aircraft System (ATTAS) aircraft from the recorded flight data. The input and output spaces are divided uniformly and Gaussian type MFs are generated from the training data set. Fivefold cross validation method is used to access the adequacy of the generated fuzzy model. The parameter tracking trends and mean square errors for training and testing data sets show commendable modeling capability of Mamdani fuzzy model for extraction of aerodynamic derivatives.