Info

Diese Frage ist geschlossen. Öffnen Sie sie erneut, um sie zu bearbeiten oder zu beantworten.

[Anfis] Optimize FIS

2 Ansichten (letzte 30 Tage)
Enrico
Enrico am 27 Dez. 2012
Geschlossen: Sam Chak am 15 Apr. 2025
Hi, I just created a file .fis .
Now, I have to optimise it through ANFIS .
My original fis is a Mamdani System, so I used the function:
mam2sug( . ).
Then, I had to change some things about my fis file, because Anfis doesnt accept all fis file .
After this, I loaded my fis file in Anfis, loaded my Data and clicked on train.
My problem is that the training doesn't work, the performance doesnt improve.
Is it normal? I dont think. Or Have i made some mistakes ?
This is the results: * ANFIS info: * Number of nodes: 40 * Number of linear parameters: 24 * Number of nonlinear parameters: 44 * Total number of parameters: 68 * Number of training data pairs: 1313 * Number of checking data pairs: 0 * Number of fuzzy rules: 4
Start training ANFIS ...
1 42.6173
2 1.#QNAN
3 1.#QNAN
4 1.#QNAN
5 1.#QNAN
6 1.#QNAN
7 1.#QNAN
8 1.#QNAN
9 1.#QNAN
10 1.#QNAN
Bye Thanks in advance
  1 Kommentar
chaks
chaks am 7 Jun. 2013
Please help me. I have similar kind of problem. Actually I need a mamdani system as I want to build the rule base myself. However, I want to train the system. But not getting any suitable command. Converting my mamdani system to sugeno type using mam2sug() does not help.
Please reply asap!!!

Antworten (0)

Diese Frage ist geschlossen.

Produkte

Community Treasure Hunt

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

Start Hunting!

Translated by