Re: Chaos and topographic diagrams

[Myron Tribus <mtribus@home.com>]

At 11:36 AM -0800 2/8/01, Jonathan Siegel wrote:
>A few issues:
>
>A. Chaos and Manufacturing Control
>
It is helpful to keep in mind the aim of these studies in chaos.  The 
aim is different from that of SPC.   Shewhart made it very clear in 
the first few pages:  He was trying to find a good way to decide if a 
system was in a 'steady state' (which he called a state of control). 
If a system has an underlying dynamic which produces 'chaos' but is 
stable, then spc will show that.

The studies based on chos theory are aiming at finding ways to 
predict what the system will do under the assumption that the chaotic 
behavior is just a manifestation of a system which sends packets of 
energy back and forth among several elements.  The classical example 
of a chaotic system is the compound pendulum or a system of pendula. 
Such systems exhibit a confusing pattern and from the response alone, 
it is difficult to figure out what is the underlying cause.  In SPC 
we don't try to undrstand why the system behaves as it does.  We only 
ask if it is 'stable', 'repeatable in a statistical sense'.

Myron Tribus,  350 Britto Terrace,  Fremont, CA 94539
Ph:510 651 3641  Fax: 510 656 9875   e-mail: mtribus@home.com
You can always count on the Americans to do the right thing -- after 
they have tried everything else. (Winston Churchill)