Neuro-Fuzzy Techniques for the Air-Data Sensor Calibration

The paper is concerned with an innovative air-data sensor calibration procedure, carried out through neuro-fuzzy techniques based on adaptive neuro-fuzzy inference system (ANFIS) and co-active neuro-fuzzy inference system (CANFIS) models. In particular, attention is focused on a beta sideslip angle virtual sensor, and data used for the calibration are obtained through a series of simulations performed by means of the nonlinear dynamic model in 6 degrees of freedom of a high-performance combat aircraft. Several ANFIS and CANFIS architectures have been developed, tested, and compared with each other. Results of numerical simulations show the remarkable effectiveness of neuro-fuzzy techniques in the sensor calibration.