Identification

Plant Output
0.15

0.1

0.05

0

-0.05

-0.1
20 40 60 80 100 120

Plant Input

0.15

0.1

0.05

0

-0.05

-0.1

-0.15

20 40

60 80

Samples

100

120

Figure 7.9. File AERO.c: I/O data set

This model structure is also compatible with the complexity estimation provided by the functions estorderiv.m (MATLAB^®) or estorderiv.sci (Scilab) (estimation with the method of instrumental variable with delayed inputs) that gives n = max (n_A,n_B+d) = 2 and n_A=1, n_B=2, d=0 respectively (see Figure 7.10).

Another identification is thus carried out with the same structure, method and adaptation gain, but with n_B=2, d=0, n_A=1.
The results obtained are as follows:


S = 1 M = 1 (RLS) A = 1 FILE:AERO.C NS = 128 DELAY D=0 COEFFICIENTS OF POLYNOMIAL A: A(1) = -0.6672 COEFFICIENTS OF POLYNOMIAL B: B(1) = 0.1736
B(2) = 0.0545
VALIDATION TEST: Whiteness of the residual error
System variance: 0.0035 Model variance: 0.0034 Error variance R(0): 3.991 E-04

NORMALIZED AUTOCORRELATION FUNCTIONS
Validation Criterion:Theor. Val.:|RN(i)|  0.192, Pract. Val.: |RN(i)|  0.15 RN(0) = 1.000000  RN(1) = -0.2284 
RN(2) = 0.1 RN(3) = 0.017
RN(4) = 0.0054