Adaptive neuro-fuzzy inference system to compute quasi-TEM characteristic parameters of microshield lines with practical cavity sidewall profiles

Neural networks have recently been introduced to the microwave area as a fast and flexible vehicle to microwave modeling, simulation and optimization. In this paper, a new approach based on adaptive neuro-fuzzy inference system (ANFIS) was presented for the quasi-TEM characteristics of microshield lines with practical cavity sidewall profiles. The proposed ANFIS model combines the neural network adaptive capabilities and the fuzzy qualitative approach. The ANFIS models were presented to produce a good approximator of the nonlinear relationship between the geometrical parameters and the quasi-TEM characteristics (characteristic impedance and cavity capacitance sensitivity) of microshield lines. The results of the ANFIS models for the characteristic impedance and the cavity capacitance sensitivity of the microshield lines and the results available in the literature obtained by using conformal-mapping technique (CMT) were compared. The drawn conclusions confirmed that the proposed ANFIS models could provide an accurate computation of the characteristic impedance and the cavity capacitance sensitivity of the microshield lines.