Path: news.mathworks.com!not-for-mail
From: <HIDDEN>
Newsgroups: comp.soft-sys.matlab
Subject: Parameter estimation
Date: Wed, 14 Mar 2012 19:35:28 +0000 (UTC)
Organization: UDG
Lines: 21
Message-ID: <jjqru0$apl$1@newscl01ah.mathworks.com>
Reply-To: <HIDDEN>
NNTP-Posting-Host: www-02-blr.mathworks.com
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
X-Trace: newscl01ah.mathworks.com 1331753728 11061 172.30.248.47 (14 Mar 2012 19:35:28 GMT)
X-Complaints-To: news@mathworks.com
NNTP-Posting-Date: Wed, 14 Mar 2012 19:35:28 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 3380510
Xref: news.mathworks.com comp.soft-sys.matlab:760976

Hi there.

Well, I'm trying to use fminsearch to find the minimum of an objective function.
The problem here is that the objective function is a set of differential equation that have to be solved numerically.... and some experimental values of them.

Let's say I have the following nonlinear system (and represents some physical phenomena)

dx1/dt = a*exp( b/x2) -x1;
dx2/dt = b*sin(x1*x2);

and some experimetal dada stored in the vectors xep1 and xexp2

I want to find the minimum of the square of the residuals

R = (xep-x)'(xep-x)

where 
xexp = [xexp1 ; xexp2];
x = [x1 ; x2];

Any clue how to do this???