File Exchange

image thumbnail

nnctrl

version 1.0.0.0 (377 KB) by Magnus Norgaard
The NNCTRL toolkit is a set of tools for design and simulation of neural network based control syste

12 Downloads

Updated 14 Apr 2003

No License

Neural Network Based Control System Design Toolkit Version 2

The NNCTRL toolkit is a set of tools for design and simulation of control systems based on neural networks. The following designs are available:

o Direct inverse control
o Internal model control
o Control by feedback linearization
o Optimal control
o Control using instantanous linearization (includes approximate pole placement, approximate minimum variance and approximate GPC control)
o Nonlinear Predictive Control
o Nonlinear Feedforward Control

The toolkit is an add-on to the NNSYSID toolbox; a toolbox for nonlinear system identification with neural networks. This version of the NNCTRL toolkit requires MATLAB 5.3 or higher. It is an advantage if Simulink and the Control System Design Toolbox is available (but they are not required). A manual (~35 pages, pdf format) accompanies the toolbox. Additional information can be found on www.iau.dtu.dk/research/control/nnctrl.html

Cite As

Magnus Norgaard (2021). nnctrl (https://www.mathworks.com/matlabcentral/fileexchange/86-nnctrl), MATLAB Central File Exchange. Retrieved .

Comments and Ratings (26)

Ashwin Sundarka

In the function apccon.m

In theory it says, to get a i step ahead prediction we need to solve the DIOPHANTINE equation for both E and F. In the function provided, we have initialized both the variable but later in the calculation we are not using 'E' at all. We are calculating everything with 'F'. Can you please provide any literature which explains the method you have implemented in the program?

Thank you for providing the whole framework. It is been really help in my thesis now.

Regards,
Ashwin

mohsen hadian

Thank you for your valuable toolbox. I was intrigued by its applicability in a wide range of well-known control strategies.

Christian Feudjio

Excellent program! Your work is an outstanding contribution. Nowadays they talk about Machine Learning Control as it is something "new" while decades ago people already investigated the field... I think it is quite common with everything "new" i guess :)

Amira benAmeur

thank you for your efforts

Mr Smart

Elsayed Hassan Ali

this files very imprtant

Nanang Firman

glanny Mangindaan

Thankyou

Rahul Sharma

R.Beulah Cresel

Nichol Estar

I AM TOO SORRY BUT POOR

Juan Wei Yang

i agree with that, you need to put comments on codes, cause there are a lot of codes inside the codes..

Ali Kahazaar

it seems to be that it need improvement

Tansel Yucelen

Hard To Understand (Because there are a lot of subcodes), Need Comments

vahid hassai

carlos de la cruz

gongnan Xie

Good for study and extension into real problem. I like it and now study it, since I want to use it to control my problem. Does anybody like to give me suggestion about IMC? thanks

ravi subban

ABDELAALI BOUHAFRA

ravi gupta

it is very useful toolbox for neural network

senthil rajan

please send nonlinear internal model control using fuzzy based inverse model

Liujia Hou

Saeed Beyty

puya afshar

essam abd elmawla

xingming zhao

MATLAB Release Compatibility
Created with R13
Compatible with any release
Platform Compatibility
Windows macOS Linux
Tags Add Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

NNCTRL20/CTRLDEMO/