TECHNET Archives

March 2001

TechNet@IPC.ORG

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Lou Hart <[log in to unmask]>
Reply To:
TechNet E-Mail Forum.
Date:
Wed, 7 Mar 2001 17:15:55 -0500
Content-Type:
text/plain
Parts/Attachments:
text/plain (152 lines)
Mike, Ken

Although I have not read much of it, I'd recommend a book by Ed Schilling
on Statistical Acceptance Sampling, the exact title of which I forget.  It
was very comprehensive and included a description of one he developed
himself which has two features I like:  it allows acceptance only on zero
nonconformances and is defined by a Lot Tolerance Percent Defective (LTPD).
 LTPD (not a good choice of terminology) is the largest fraction
nonconforming that has a 0.1 or 0.05 (depending on the plan) probability of
acceptance.

For example, if you decide you cannot tolerate more than 8% nonconforming
material in a lot, you might say that you want a sampling plan that will
have a probability of 0.1 of accepting a lot with that % nonconforming.
 Following Schilling's recipe, you would calculate the number of units to
inspect (it depends on the lot size) and accept the lot if you found no
nonconformances in the sample.

The advantages to such an approach are:

sample size is relatively low

by working from an LTPD rather than an AQL (as in Z1.4), the plan is
oriented to protect the consumer rather than the producer

by accepting on zero nonconformances, you have at least not demonstrated
that there is one in the lot (Z1.4 allows acceptance, in some cases, with 1
or more nonconformances in the sample).

IPC has had a very simple table appearing in a number of documents over the
past two years that defines zero acceptance number sampling plans, although
based on an AQL.  It is on page 20 of 6012A, for example.  It has the two
virtues of a zero acceptance number and of being very easy to use.

If you are working with variable (something measured) rather than attribute
(pass or fail) data, ANSI/ASQC Z1.9 is worth knowing about.  (It is
comparable to MIL-STD-414.)  If quantitative measurements are available and
hard to make, this standard may be useful.

Beyond these, you could look into Skip Lot Sampling plans to use, which
would help you reduce inspection once a supplier's performance had been
established as acceptable.  ANSI/ASQC S1-1987 (or a later version, if one
exists) specifies such plans.  ASQ has a slender book by Kenneth Stephens
called "How to Perform Skip-Lot and Chain Sampling", ISBN 0-87389-325-5.

If your product is coming off the line in a continuous stream, rather than
in lots, you may want to look into "How to Perform Continuous Sampling",
also by Stephens, ISBN 0-87389-330-1 from ASQ.  MIL-STD-1235 specifies a
variety of plans.  I don't know if there is an ASQ equivalent.

Hope this helps some.
Lou

-----Original Message-----
From:   Keel, Mike [SMTP:[log in to unmask]]
Sent:   Wednesday, March 07, 2001 4:02 PM
To:     'TechNet E-Mail Forum.'; 'Lou Hart'
Subject:        RE: [TN] MIL- 105D or MIL-105E? What is new one?

Lou, we all benefit if you share

                -----Original Message-----
                From:   Lou Hart [mailto:[log in to unmask]]
                Sent:   Wednesday, March 07, 2001 7:06 PM
                To:     [log in to unmask]
                Subject:        Re: [TN] MIL- 105D or MIL-105E? What is new
one?

                Ken, 105 was cancelled 5 or 6 years ago.  Use Ansi/ASQC
Z1.4-1993, Sampling
                Procedures And Tables for Inspection by Attirbutes.  I don't
know that it
                has been revised since 1993.  You can get this from the
American Society
                for Quality.  Personally, I am not very fond of this
standard.  Other
                sampling methods are better, in my opinion.  If you or other
TechNetters
                want to know more, please say so.  Lou Hart

                -----Original Message-----
                From:   Ken Patel [SMTP:[log in to unmask]]
                Sent:   Wednesday, March 07, 2001 1:12 PM
                To:     [log in to unmask]
                Subject:        [TN] MIL- 105D or MIL-105E? What is new one?

                Quality Guru,
                Can anyone give me an update on sampling plan MIL- 105D or
MIL-105E? I
                heard
                that it was replaced by new standard? What is the name of
that document?

                re,
                ken patel


------------------------------------------------------------------------
                ---------
                Technet Mail List provided as a free service by IPC using
LISTSERV 1.8d
                To unsubscribe, send a message to [log in to unmask] with
following text in
                the BODY (NOT the subject field): SIGNOFF Technet
                To temporarily halt delivery of Technet send the following
message: SET
                Technet NOMAIL
                Search previous postings at: www.ipc.org > On-Line Resources
& Databases >
                E-mail Archives
                Please visit IPC web site
(http://www.ipc.org/html/forum.htm) for
                additional
                information, or contact Keach Sasamori at [log in to unmask] or
847-509-9700
                ext.5315

------------------------------------------------------------------------
                ---------


------------------------------------------------------------------------
----
-----
                Technet Mail List provided as a free service by IPC using
LISTSERV 1.8d
                To unsubscribe, send a message to [log in to unmask] with
following text in
                the BODY (NOT the subject field): SIGNOFF Technet
                To temporarily halt delivery of Technet send the following
message: SET Technet NOMAIL
                Search previous postings at: www.ipc.org > On-Line Resources
& Databases > E-mail Archives
                Please visit IPC web site
(http://www.ipc.org/html/forum.htm) for additional
                information, or contact Keach Sasamori at [log in to unmask] or
847-509-9700 ext.5315

------------------------------------------------------------------------
----
-----

---------------------------------------------------------------------------------
Technet Mail List provided as a free service by IPC using LISTSERV 1.8d
To unsubscribe, send a message to [log in to unmask] with following text in
the BODY (NOT the subject field): SIGNOFF Technet
To temporarily halt delivery of Technet send the following message: SET Technet NOMAIL
Search previous postings at: www.ipc.org > On-Line Resources & Databases > E-mail Archives
Please visit IPC web site (http://www.ipc.org/html/forum.htm) for additional
information, or contact Keach Sasamori at [log in to unmask] or 847-509-9700 ext.5315
---------------------------------------------------------------------------------

ATOM RSS1 RSS2