Page 146 - Neural Network Modeling and Identification of Dynamical Systems
P. 146
136 4. NEURAL NETWORK BLACK BOX MODELING OF AIRCRAFT CONTROLLED MOTION
FIGURE 4.3 Neural network model design for F-16 aircraft, flight regime with airspeed V i = 500 km/h. (A) Training
sample for the ANN model. (B) Efficiency test for a closed-loop ANN model. Here α is the angle of attack, deg; E α is the
tracking error (difference between angle of attack values for the object and the ANN model), deg; δ e, act is command signal
for the actuator of the elevator; t is time, sec; the solid line is the output of the object; the dotted line is the output of the ANN
model.