1
.TH arsimul 1 "April 1993" "Scilab Group" "Scilab Function"
4
arsimul - armax simulation
7
[z]=arsimul(a,b,d,sig,u,[up,yp,ep])
8
[z]=arsimul(ar,u,[up,yp,ep])
13
: an armax process. See armac.
16
: is the matrix[Id,a1,...,a_r] of dimension (n,(r+1)*n)
19
: is the matrix[b0,......,b_s] of dimension (n,(s+1)*m)
22
: is the matrix[Id,d_1,......,d_t] of dimension (n,(t+1)*n)
25
: is a matrix (m,N), which gives the entry u(:,j)=u_j
28
: is a (n,n) matrix e_{k} is an n-dimensional Gaussian process with variance I
31
: optional parameter which describe the past.
32
up=[ u_0,u_{-1},...,u_{s-1}];
33
yp=[ y_0,y_{-1},...,y_{r-1}];
34
ep=[ e_0,e_{-1},...,e_{r-1}];
35
if they are omitted, the past value are supposed to be zero
40
simulation of an n-dimensional armax process
41
A(z^-1) z(k)= B(z^-1)u(k) + D(z^-1)*sig*e(k)
43
A(z)= Id+a1*z+...+a_r*z^r; ( r=0 => A(z)=Id)
44
B(z)= b0+b1*z+...+b_s z^s; ( s=-1 => B(z)=[])
45
D(z)= Id+d1*z+...+d_t z^t; ( t=0 => D(z)=Id)
47
z et e are in R^n et u in R^m
49
a state-space representation is constructed and ode with the option
50
"discr" is used to compute z