Scilab Home Page | Wiki | Bug Tracker | Forge | Mailing List Archives | Scilab Online Help | File Exchange
ATOMS : Identification Toolbox details
Please login or create an account

Identification Toolbox

Tools for identification of dynamical systems
(8286 downloads for this version - 12771 downloads for all versions)
Details
Version
1.1.1
Authors
Department of Control Engineering, CTU Prague
Martin Novotny
Owner Organization
N/A
Maintainers
Allan Cornet
Martin Novotny
License
Creation Date
September 28, 2012
Source created on
Scilab 5.4.x
Binaries available on
Scilab 5.4.x:
Windows 64-bit Windows 32-bit Linux 64-bit Linux 32-bit MacOSX
Scilab 5.5.x:
Windows 64-bit Windows 32-bit Linux 64-bit Linux 32-bit MacOSX
Install command
--> atomsInstall("identification")
Description
            ************************************
* Identification Toolbox 1.1 beta **
************************************

Identification Toolbox is used to construct mathematical models of LTI systems 
from measured input-output data sequences. There is also possible to combine the
identification based on measured input-output data with first principles
approaches.

Whereas, the tool is developed at the educational and research institution, it
serves primarily the new approaches and the development is focused particularly
in the innovations and testing.

The tool allows:
- Preprocessing of signals (resampling, filtering, detrending,...)
- Identification of LTI systems
- Validating of constructed models

Supported Models:
- ARX
- ARMAX
- State-space

Supported Methods:
- Prediction Error Method (PEM)
- Subspace State-Space System IDentification (4SID)
- Combining 4SID + PEM
- Errors in Variables (EIV) identification

New features:
- Use of Nonnegative Garrote Method (NNG) for order selection (reduction) of
ARX/ARMAX models
- Handling Certain Structure Information in 4SID Identification
- Handling Structure Information in Black-Box (BB) Modeling
- Estimating Physical Parameters of a System by BB

Future extensions:
- Graphical User Interface
- Other LTI models
- Other identification methods


            
Files (3)
[291.59 kB]
Source code archive
makes it available for Scilab 5.4
[328.22 kB]
OS-independent binary for Scilab 5.4.x
Binary version
Automatically generated by the ATOMS compilation chain

[292.98 kB]
OS-independent binary for Scilab 5.5.x
Binary version (all platforms)
Automatically generated by the ATOMS compilation chain

News (0)
Comments (3)     Leave a comment 
Comment from Yoshikazu Noguchi -- September 15, 2014, 06:27:17 AM    
Hello,

I am a begginer of Scilab. I am using Scilab 5.5.0 with m y windows 7 PC.

I would like to install identification tool box in my PC.

I downloadss Binary version and installed on my HDD and exec loader.sce.


-->exec loader.sce
 
-->// This file is released under the 3-clause BSD license. See COPYING-BSD.
 
-->// Generated by builder.sce: Please, do not edit this file
 
 
-->try
--> getversion("scilab");
-->catch
--> error("Scilab 5.0 or more is required.");
-->end;
 
 
-->exec(get_absolute_file_path("loader.sce")+"etc/"+"identification.start");
 
 Start identification   
 
 Load macros   
 
 Load help   
 
 

I am not sure that how can I run this identification tool box.
Comment from Matheus Granzotto -- April 16, 2016, 07:53:26 PM    
Hello,

I want to use the Identification Toolbox, for find A,B,C and D for a simulation, but for
this I have to find the Hankel matrix through the function findR. Every time I use the
output signal Y=[y1 y2 y3 y4 y5 y6], for which column is a different output, and every
line is a different instant, and My input signal is U=[u1 u2], tested for u1 and u2
separately, I receive a message of error 9999, ALG MUST BE SCALAR line 109 for function
findR. My OS is Windows 10 64bit, and I am using the Scilab 5.5.2 64bit.

If I try test the samples for the findR in Help, I receive the same error.

Please, someone have the same problem?

Thank You.
Comment from Brian Tremaine -- August 11, 2016, 05:04:16 PM    
Is there a version for Scilab 6.0 beta? I tried AtomsInstall("identification")
and no 
package was found.

Thanks,
Leave a comment
You must register and log in before leaving a comment.
Email notifications
Send me email when this toolbox has changes, new files or a new release.
You must register and log in before setting up notifications.