performability analysis on two types of fixed structure and morphed wings

In this research, a novel computational intelligence-based approach is presented for modeling and predicting the aerodynamic performance of a fish-skeleton-inspired morphing wing. the primary objective is to develop an accurate and efficient model for estimating key aerodynamic parameters, namely the lift coefficient ( ) and drag coefficient ( ), based on structural and environmental inputs. to this end, the adaptive neuro-fuzzy inference system (anfis) is utilized due to its high capability in modeling complex and nonlinear systems. the main novelty of this research lies in the implementation and comparative analysis of two distinct anfis architectures: an independent model, where two separate anfis networks are trained in parallel to predict each output (  and ), and a dependent (cascaded) model, in which the predicted output from the first network is utilized as an additional input to the second network for predicting the second output. the performance evaluation results, conducted using simulation data and precise statistical metrics, indicate that the independent architecture provides significantly superior prediction accuracy and stability compared to the dependent model. the cascaded approach, despite its theoretical appeal, failed due to the destructive phenomenon of error propagation. owing to its consideration of the physical dependency between the output parameters. this research not only demonstrates the high efficiency of anfis in the field of bio-inspired aerospace structure design but also provides significant insight into the impact of model architecture selection on prediction accuracy and efficiency in multi-input multi-output problems.