Manufacturing design and process analysis system

• US 7,917,234 B2
• Filed: 05/11/2007
• Issued: 03/29/2011
• Est. Priority Date: 02/04/2002
• Status: Expired due to Fees

• Current Assignee: Steve W. Tuszynski
• Original Assignee: Steve W. Tuszynski
• Inventors: Tuszynski, Steve W.
• Primary Examiner(s): Masinick; Michael D
• Application Number:
  US11/747,427
• Publication Number:
  US 20070219657A1
• Time in Patent Office: 1,418 Days
• Field of Search: 700/33, 703/2
• US Class Current: 700/33
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 19/41865 characterised by job scheduling, process planning, material flow
• CPC Class Codes: G05B 2219/32058 Execute program as function of deviation from predicted state, result
• CPC Class Codes: G06F 2111/08 Probabilistic or stochastic CAD
• CPC Class Codes: G06F 2113/22 Moulding
• CPC Class Codes: G06F 30/00 Computer-aided design [CAD]
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

Methods, apparatuses and systems that facilitate the design, production and/or measurement tasks associated with manufacturing and other processes. In one embodiment, the present invention provides an understanding of how the multiple characteristics of a given process output are related to each other and to process inputs. This knowledge facilitates a reduction in measurement costs. It also facilitates an understanding of the sometimes complex interrelationships between design targets, design tolerances, process inputs, process control variables, average process output and variation in the process output. As disclosed in more detail below, embodiments of the present invention facilitate 1.) determination of design target values, 2.) determination of design application limits, 3.) design of process inputs, 4.) determination of process control variable settings, and/or 5.) reduction of measurement costs.

Claims

1. A method facilitating design and manufacturing processes, the method comprising

receiving into a computer-readable memory a plurality of article characteristic values associated with a set of articles having a range of variation as to a plurality of article characteristics resulting from a process;

evaluating, using a computing device, correlations between the plurality of article characteristics based on analysis of the plurality of article characteristic values;

selecting, using the computing device, a predictor characteristic from the plurality of article characteristics based on the correlations between the plurality of article characteristics;

determining the regression model(s) between the predictor characteristic and at least one of the remaining article characteristics in the plurality of article characteristics; and

generating a diagram of the regression model(s) for display on a display device.

2. The method of claim 1 further comprising

identifying a range for the predictor characteristic over which at least one remaining article characteristic is within design specifications;

and

generating a representation of the range for display on the display device.

4. The method of claim 1 further comprising

identifying a range for the predictor characteristic over which a plurality of remaining article characteristics are within design specifications;

qualifying articles resulting from the process are within design specifications based on corresponding values of the predictor characteristic relative to the identified range.

3. A method, comprising

receiving into a computer-readable memory a plurality of article characteristic values associated with a set of articles having a range of variation as to a plurality of article characteristics resulting from a process;

evaluating, using a computing device, correlations between the plurality of article characteristics based on analysis of the plurality of article characteristic values;

selecting, using the computing device, a predictor characteristic from the plurality of article characteristics based on the correlations between the plurality of article characteristics;

determining the regression model(s) between the predictor characteristic and at least one of the remaining article characteristics in the plurality of article characteristics;

identifying a range for the predictor characteristic over which a plurality of remaining article characteristics are within design specifications; and

generating a representation of the range for display on a display device.

5. The method of claim 3 further comprising

determining the respective upper and lower prediction intervals associated with the regression model(s) between the predictor characteristic and at least one of the remaining article characteristics.

6. The method of claim 5 further comprising

receiving lower and upper specification limits for said at least one of the remaining article characteristics;

locating the lower and upper specification limits associated with said at least one of the remaining article characteristics;

receiving lower and upper specification limits for the predictor characteristic;

locating the upper specification limit associated with the predictor characteristic; and

determining a maximum article characteristic value for the predictor characteristic by selecting the lesser of (1) the upper specification limit for the predictor characteristic and (2) the value of the predictor characteristic at which the upper prediction interval intersects the upper specification limit for said at least one remaining article characteristic.

7. The method of claim 6 further comprising

repeating the determining a maximum article characteristic value step for a desired number of remaining article characteristics in the plurality of article characteristics;

and

determining the most constraining maximum article characteristic value for the predictor characteristic by selecting the lowest maximum article characteristic value.

8. The method of claim 6 further comprising

receiving lower and upper specification limits for at least one of the remaining article characteristics;

locating the lower specification limit associated with the predictor characteristic; and

determining a minimum article characteristic value for the predictor characteristic by selecting the greater of (1) the lower specification limit for the predictor characteristic and (2) the value of the predictor characteristic at which the lower prediction interval intersects the lower specification limit for said at least one remaining article characteristic.

9. The method of claim 8 further comprising

determining an allowable range for the predictor characteristic by subtracting the minimum article characteristic value from the maximum characteristic value.

10. The method of claim 8 further comprising

repeating the determining a minimum article characteristic value step for a desired number remaining article characteristics in the plurality of article characteristics;

and

determining the most constraining minimum article characteristic value for the predictor characteristic by selecting the greatest minimum article characteristic value.

11. The method of claim 10 further comprising

determining the maximum allowable range for the predictor characteristic by subtracting the most constraining minimum article characteristic value from the most constraining maximum characteristic value.

12. The method of claim 11 further comprising

determining the target manufacturing value for the predictor characteristic by selecting a value between the most constraining minimum and maximum article characteristic values for the predictor characteristic.

13. The method of claim 11 further comprising

determining the target manufacturing value for the predictor characteristic by selecting the midpoint value between the most constraining minimum and maximum values for the predictor characteristic.

21. The method of claim 3 further comprising qualifying articles resulting from the process based on corresponding values of the predictor characteristic relative to the identified range.

14. An apparatus facilitating design, manufacturing, and other processes comprising:

a processor;

a memory;

a software application, physically stored in the memory, comprising instructions operable to cause the processor and the apparatus to;

receive a plurality of article characteristic values associated with a set of articles having a range of variation as to a plurality of article characteristics resulting from a process;

evaluate correlations between the plurality of article characteristics;

receive a selection of a predictor characteristic from the plurality of article characteristics based on the correlations between the plurality of article characteristics; and

,

determine the regression model(s) between the predictor characteristic and at least one of the remaining article characteristics in the plurality of article characteristics; and

generate a diagram of the regression model(s) for display on a display device.

15. The apparatus of claim 14 wherein the software application further comprises instructions operable to cause the processor and the apparatus to identify a range for the predictor characteristic over which at least one remaining article characteristic is within design specifications.

16. The apparatus of claim 14 wherein the software application further comprises instructions operable to cause the processor and the apparatus to identify a range for the predictor characteristic over which a plurality of remaining article characteristics are within design specifications.

17. An apparatus facilitating design, manufacturing, and other processes comprising:

a processor;

a memory;

a software application, physically stored in the memory, comprising instructions operable to cause the processor and the apparatus to;

receive a plurality of article characteristic values associated with a set of articles having a range of variation as to a plurality of article characteristics resulting from a process;

evaluate correlations between the plurality of article characteristics;

receive a selection of a predictor characteristic from the plurality of article characteristics based on the correlations between the plurality of article characteristics; and

,

determine the regression model(s) between the predictor characteristic and at least one of the remaining article characteristics in the plurality of article characteristics;

identify a range for the predictor characteristic over which a plurality of remaining article characteristics are within design specifications; and

generate a representation of the range for display on a display device.

18. A computer readable storage medium, for facilitating design, manufacturing, and other processes, comprising instructions operable, when executed, to cause a programmable processor to:

receive into a computer-readable memory a plurality of article characteristic values associated with a set of articles having a range of variation as to a plurality of article characteristics resulting from a process;

evaluate correlations between the plurality of article characteristics based on analysis of the plurality of article characteristic values;

receive a selection of a predictor characteristic from the plurality of article characteristics based on the correlations between the plurality of article characteristics;

determine the regression model(s) between the predictor characteristic and at least one of the remaining article characteristics in the plurality of article characteristics; and

generate a diagram of the regression model(s) for display on a display device.

19. The computer readable storage medium of claim 18 further comprising instructions operable, when executed, to cause a programmable processor to identify a range for the predictor characteristic over which a plurality of remaining article characteristics are within design specifications.

20. The computer readable storage medium of claim 18 further comprising instructions operable, when executed, to cause a programmable processor to identify a range for the predictor characteristic over which at least one remaining article characteristic is within design specifications.

22. A method comprising:

receiving into a computer-readable memory a plurality of article characteristic values associated with a set of articles having a range of variation as to a plurality of article characteristics resulting from a process;

receiving, by a computing device, a selection of an article characteristic of the plurality of article characteristics as a predictor characteristic for one or more of the remaining article characteristics in the plurality of article characteristics;

determining, using the computing device, the regression model(s) between the predictor characteristic and at least one of the remaining article characteristics in the plurality of article characteristics;

assessing, using the computing device, the process using the determined regression model(s) between the predictor characteristic and remaining article characteristics, including at least one of

(1) determining whether the values of at least one of the remaining article characteristics relative to the regression model(s) comply with respective specification limits for all corresponding values of the predictor characteristic for articles that may be generated by the process;

(2) determining whether the articles with predictor characteristic values and remaining article characteristic values relative to the regression model(s) can be manufactured within specification limits;

(3) determining a minimum value of the predictor characteristic such that the value of one or more of the remaining article characteristic relative to the regression model(s) complies with a corresponding specification limit for the process,

(4) determining a maximum value of the predictor characteristic such that the value of one or more of the article characteristics relative to the regression model(s) complies with a corresponding specification limit for the process, and

(5) determining a distance between a target specification value for the predictor characteristic and one or more of the remaining article characteristic and a regression line of the regression model(s).

23. The method of claim 22 further comprising

identifying a range for the predictor characteristic over which at least one remaining article characteristic is within design specifications;

and

generating a representation of the range for display on the display device.

24. The method of claim 23 further comprising

evaluating correlations between the plurality of article characteristics based on analysis of the plurality of article characteristic values.

25. The method of claim 24 wherein the evaluating the correlations comprises computing, for each of the article characteristics, a predictor capability value indicating the ability of the article characteristic to be a predictor of the remaining article characteristics of the plurality of article characteristics, wherein the computing the predictor capability value includes calculating the correlation coefficients between each of the article characteristics and the remaining article characteristics.

26. An apparatus, the apparatus comprising:

a processor;

a memory;

computer program code, stored on a non-transitory data storage medium, comprising instructions for execution by the processor, the computer program code comprising;

a data input module comprising instructions operative to cause the processor to receive a plurality of article characteristic values associated with a set of articles having a range of variation as to a plurality of article characteristics resulting from a process;

a correlation module comprising instructions operative to cause the processor to compute, for each of the article characteristics, a predictor capability value indicating the ability of the article characteristic to be a predictor of the remaining article characteristics of the plurality of article characteristics;

a user interface module comprising instructions operative to cause the processor to display the plurality of article characteristics on a display device, and receive a selection of an article characteristic of the plurality of article characteristics as a predictor characteristic for one or more of the remaining article characteristics in the plurality of article characteristics;

a regression module comprising instructions operative to cause the processor to determine the regression model(s) between the values of the predictor characteristic and at least one remaining article characteristic value in the plurality of article characteristics; and

wherein the computer program code further comprises instructions operative to cause the processor to;

assess the process using the determined regression model(s) between the predictor characteristic and remaining article characteristics, including at least one of

(1) determining whether the values of at least one of the remaining article characteristics relative to the regression model(s) comply with respective specification limits for all corresponding values of the predictor characteristic for articles that may be generated by the process;

(2) determining whether the articles with predictor characteristic values and remaining article characteristic values relative to the regression model(s) can be manufactured within specification limits;

(3) determining a minimum value of the predictor characteristic such that the value of one or more of the remaining article characteristic relative to the regression model(s) complies with a corresponding specification limit for the process,

(4) determining a maximum value of the predictor characteristic such that the value of one or more of the article characteristics relative to the regression model(s) complies with a corresponding specification limit for the process, and

(5) determining a distance between a target specification value for the predictor characteristic and one or more of the remaining article characteristic and a regression line of the regression model(s).

27. The apparatus of claim 26 wherein the computer program code further comprises instructions operative to cause the processor to:

identify a range for the predictor characteristic over which at least one remaining article characteristic is within design specifications; and

generate a representation of the range for display on the display device.

28. The apparatus of claim 26 wherein the computer program code further comprises instructions operative to cause the processor to:

evaluate correlations between the plurality of article characteristics based on analysis of the plurality of article characteristic values.

29. The apparatus of claim 28 wherein the computer program code further comprises instructions operative to cause the processor to:

calculate the correlation coefficients between each of the article characteristics and another one of the article characteristics.