Re: Fuzzy vs Neural


Subject: Re: Fuzzy vs Neural
From: Earl Cox (ecox@metus.com)
Date: Mon Jan 17 2000 - 06:17:42 MET


Edgar,

  You are correct, but the more fundamental question is: why are we still
debating issues about the application of fuzzy logic in control and decision
support, a decade after they have proved their robustness, stability,and
utility in a wide spectrum of commercial products? As an brief example: the
Sendai subway system's ATO (automatic train operator), hundreds of uses in
such areas as video image stabilization, elevator controls, space shuttle
docking, crane stability and management, anti-lock braking systems,
hydraulic plant controls, petrochemical plant controls, etc. etc.

  There are many examples where a fuzzy controller is used where a
mathematical model is known. Fuzzy controllers are often simpler and cheaper
to implement, are noise tolerant, take up less space, often easier to
maintain and extend, can be developed by control engineers instead of
control scientists, etc. Certainly you can find exceptions to each of my
statements. Fuzzy logic is not a panacea or a cure-all.

  The problem is pretty obvious from the exchanges with those "attacking"
fuzzy logic (and I use that term "attack" loosely). Most of these people
haven't even bothered to read a few books on the subject, or scan the web
for applications, or learn the basics of what fuzzy systems do and how they
work. The exchange with pandeyashish@my-deja.com is a perfect example.

  Anyway, the solution is also pretty obvious.
  Earl

Edgar Dohmann wrote in message
<97B370029EB28DF7.F23E1D2D42F35833.CC772BB4124715A6@lp.airnews.net>...
>In article <854u2k$otd$1@nnrp1.deja.com>, pandeyashish@my-deja.com wrote:
>
>
>
>>
>> I think you must have a good reason for using a FLC (this also remains
>> a grey area) Dont implement FLC just cause they sound cute as there is
>> no justification for their use in processes where mathematical models
>> exists.
>>
>
>A rather broad-brush statement with no meaning IMHO. One could just as
>easily state that there is no justification for using any other particular
>solution for a process where a mathematical model exists.
>
>If you want to control a process with a computer algorithm, you have to
>select something. There may be many justifiable reasons for selecting FLC
>over some other workable solution, one doesn't have to JUST look around
>for a problem that can ONLY be solved with fuzzy logic in order for FLC to
>be justifiable.
>
>Edgar Dohmann

############################################################################
This message was posted through the fuzzy mailing list.
(1) To subscribe to this mailing list, send a message body of
"SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
(2) To unsubscribe from this mailing list, send a message body of
"UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"
to listproc@dbai.tuwien.ac.at
(3) To reach the human who maintains the list, send mail to
fuzzy-owner@dbai.tuwien.ac.at
(4) WWW access and other information on Fuzzy Sets and Logic see
http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
(5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html



This archive was generated by hypermail 2b25 : Thu Apr 06 2000 - 15:59:38 MET DST