User`s guide

3 Linear Model Identification
Typically you try different model orders and compare results, ultimately
choosing the sim plest model that best describes the system dynam ics. The
following command specifies the estimation d ata set,
z8,andtheordersof
the A, B ,andC polynomials as
na, nb,andnc, respectiv ely. nk of [0 0 0]
specifies that there is no input delay for all three input channels.
m_armax=armax(z8,'na',4,...
'nb',[3 2 3],...
'nc',4,...
'nk',[0 0 0],...
'focus', 'simu lati on',...
'tolerance',1e-5,...
'maxiter',50);
covariance
, focus, tolerance,andmaxiter are o ptional arguments
specify additional information a bout the computation.
focus specifies
whetherthemodelisoptimizedforsimulationorpredictionapplications,
tolerance and maxiter specify when to stop estimation. For more
information about these properties, see the
algorithm prop erti es
reference page.
armax is a version of pem with simplified syntax for the AR MAX model
structure. The
armax method both constructs the idpoly model object
and estimates its parameters.
Tip Instead of s pe cifying model orders and delays as individual
property-value pairs, you can use the equivalent shorthand notation that
includes all of the order integers in a single vector, as follows:
m_armax=armax(z8,[4 3 2 3 4 0 0 0],...
'focus', 'simu lati on',...
'tolerance',1e-5,...
'maxiter',50);
3-68