Page 157 - Neural Network Modeling and Identification of Dynamical Systems

4.3 APPLICATION OF ANN MODELS TO ADAPTIVE CONTROL PROBLEMS UNDER UNCERTAINTY CONDITIONS 147

FIGURE 4.10 The results of a computational experiment for model reference adaptive control system with a compensator
(hypersonic research vehicle X-43, flight regime M = 6). Here α is angle of attack, deg; E α is the angle of attack tracking error,
deg; α ref is the angle of attack reference signal, deg; δ e, act is command signal for the elevator drive, deg; t is time, sec; the
solid line is the real plant; the dotted line is the ANN model.

are not typical, it seems reasonable to utilize a then the controller, trying to minimize a differ-
simpler PD compensator for these systems. ence between the behavior of the system and the
reference model, will produce too large values of
4.3.2.4 Estimation of the Influence of the the command signals for the control actuators,
Reference Model Parameters on the
which can lead to a significant deterioration of
Efficiency of the Synthesized
the control performance.
Control System
Taking these considerations into account, in
As we noted above, the desired behavior
Section 4.3.2.2 a reference model was introduced
of the considered system is defined by a ref- for the considered adaptive control schemes,
erence model. The computational experiments
which is a serial connection of the aperiodic-type
show that it is expedient to choose the refer-
and oscillatory-type units, i.e.,
ence model in such a way that the character of
the desired behavior determined by it would be
close enough to the behavior of the real con- ω 2 rm
trolled object. If this condition is not satisfied, W rm = (T pf p + 1)(p + 2ζ rm ω rm p + ω ) .
2
2
rm