Newsgroups: comp.ai.fuzzy
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!gatech!swrinde!elroy.jpl.nasa.gov!lll-winken.llnl.gov!ames!hpg30a.csc.cuhk.hk!hkuxb.hku.hk!hkuxa.hku.hk!h9216074
From: h9216074@hkuxa.hku.hk (K.Y. Lo - Andrew)
Subject: Limitation on Fuzzy Logic Control?
Message-ID: <D8H6I7.MDu@hkuxb.hku.hk>
Sender: usenet@hkuxb.hku.hk (USENET News System)
Nntp-Posting-Host: hkuxa.hku.hk
Organization: The University of Hong Kong
X-Newsreader: TIN [version 1.1 PL6]
Date: Fri, 12 May 1995 17:13:18 GMT
Lines: 25


Hello,

As far as I know from my course on fuzzy logic control, the performance
obtained when the number of logic rules increases is better and better.
However, I just wonder if there exists any optimum number or limit on the
number of sub-set of logic rules above which the performance got is not
worth in the viewpoint of economic consideration or memory storage 
requirement.

Besides, is there any criteria in which I can decide whether a particular
control system is capable of undergoing fuzzy logic control?  What I mostly
like is some objective rules or something like that.

Also, what is the role played by the non-crisp singleton inputs feeding
into the fuzzification?  I find this strange as from time to time, my 
course just mentions that the input being fed into the logic control is
a crisp singleton!

Any comment is welcome.

- Andrew.
University of Hong Kong
Department of Electrical and Electronic Engineering

