Data processing: measuring – calibrating – or testing – Measurement system in a specific environment – Quality evaluation
Reexamination Certificate
1996-11-20
2002-10-29
Stamber, Eric B. (Department: 3622)
Data processing: measuring, calibrating, or testing
Measurement system in a specific environment
Quality evaluation
C702S081000, C700S109000
Reexamination Certificate
active
06473703
ABSTRACT:
BACKGROUND OF THE INVENTION
This invention relates to a novel method for controlling a manufacturing process utilizing control charts.
INTRODUCTION TO THE INVENTION
Control charts are a well-known and important means for monitoring the state of a manufacturing process. An example of typical control charts is shown in
FIGS. 1A
,
1
B (numerals
10
,
12
).
In particular,
FIG. 1A
shows an {overscore (x)} control chart
10
comprising an ordinate time series of a manufacturing variable (sample number) and an abscissa control limit window (upper control limit UCL and lower control limit LCL). The
FIG. 1A
control chart
10
provides data in response to an inquiry: Is the manufacturing process centered?
FIG. 1B
shows an R-control chart
12
comprising an ordinate time series of a manufacturing variable (sample number) and an abscissa control limit window, and is complimentary to the
FIG. 1A
control chart
10
in that the control chart
12
provides data in response to the variability of the manufacturing process.
SUMMARY OF THE INVENTION
Our work centers on a critique of the capabilities of extant control charts, of the type illustratively shown in
FIG. 1
, to an end of disclosing novel methodology which can qualitatively extend and exploit their utility.
To this end, we note that present control charts have inherent problems or deficiencies, including:
1) A fraction of good manufactured products are incorrectly rejected due to false alarms which are inherent in the statistical nature of present control charts.
2) A fraction of unacceptable (bad) products are incorrectly accepted due to false alarms, etc.
3) Decisions for acceptance/rejection are binary, and therefore cannot incorporate an operatives prior knowledge and domain expertise or desired credence level.
As just alluded to, we have now discovered a novel method that can preserve the advantages and features of extant control charts, while it extends and more fully exploits their utility and potential capability.
The novel method comprises the steps of:
(1) constructing a control chart comprising a time series of a manufacturing variable of interest operated upon by process control limits;
(2) computing specified confidence intervals for the control limits; and
(3) generating a signal based on a comparison of a time series measurement of the manufacturing variable of interest with the specified confidence intervals computed for the control limits.
The invention, as defined, can realize significant advantages. For example, and with reference to problems and deficiencies of extant control charts of the type noted above—it can minimize the fraction of good manufacturing product falsely rejected; it can minimize the fraction of bad product which would otherwise be incorrectly accepted; and, it can enable users to utilize prior knowledge i.e., binary decisions are enriched. Other advantages are disclosed below.
REFERENCES:
patent: 4967381 (1990-10-01), Lane et al.
patent: 5199439 (1993-04-01), Zimmerman et al.
patent: 5225998 (1993-07-01), Singhal
patent: 5226118 (1993-07-01), Baker et al.
patent: 5257206 (1993-10-01), Hanson
patent: 5311759 (1994-05-01), Mangrulkar et al.
patent: 5392226 (1995-02-01), Hamilton
patent: 5440478 (1995-08-01), Fisher et al.
patent: 5442562 (1995-08-01), Hopkins et al.
patent: 5602761 (1997-02-01), Spoerre et al.
Joseph M. Juran,Quality Control Handbook,Third Edition (1974), McGraw-Hill Book Company, Chapters 9, 22 and 23, and Table B.
Neter et al.,Applied Statistics,Third Edition (1988), Simon & Schuster, pp. 279-287, 294-295, 443-451, and Table C.1.
Tom Bassett III, “Control Chart Techniques for High Volume, Multiple Process Wafer Fabrication Areas”, 1991 IEEE/SEMI Advanced Semiconductor Manufacturing Conference, pp. 132-142.
Kahraman et al., “Using Triangular Fuzzy Members in the Tests of Control Charts for Unnatural Patterns”, Proc. 1995 INRIA/IEEE Symposium on Emerging Technologies and Factory Automation, Oct. 1995, pp. 291-298.
Daniel Billings, “Initializing Control Charts in a Startup Environment With Pre-Control Concepts”, Proc. First International Symposium on Uncertainty Modeling and Analysis, Dec. 1990, pp. 177-182.
Martin et al., “Process Performance Monitoring Using Multivariate Statistical Process Control”, IEE Proc.-Control Theory Appl., vol. 143, No. 2, Mar. 1996, pp. 132-144.
William Nolte, “SPC with Enable”, Proceedings of the IEEE 1994 International Engineering Management Conference, Oct. 1994, pp. 170-176.
Cirulli et al., “A Successful Strategy for Implementing Statistical Process Controls”, IEEE/CHMT '89 IEMT Symposium, pp. 96-98.
Kurtzberg Jerome M.
Levanoni Menachem
International Business Machines - Corporation
Kaufman Stephen C.
Scully Scott Murphy & Presser
Stamber Eric B.
LandOfFree
Method for controlling a manufacturing process utilizing... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for controlling a manufacturing process utilizing..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for controlling a manufacturing process utilizing... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2958485