Manufacturing process analysis and optimization system

• US 7,672,745 B1
• Filed: 03/20/2006
• Issued: 03/02/2010
• Est. Priority Date: 03/20/2006
• Status: Active Grant

• Current Assignee: Steve W. Tuszynski
• Original Assignee: Steve W. Tuszynski
• Inventors: Tuszynski, Steve W.
• Primary Examiner(s): Jarrett; Ryan A
• Application Number:
  US11/384,749
• Time in Patent Office: 1,443 Days
• Field of Search: 700/33, 700/13, 700/97, 700/31, 700/51, 700/52, 700/90, 700/95, 700/108, 700/175, 700/29, 703/2, 703/7
• US Class Current: 700/97
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 2219/32201 Build statistical model of past normal proces, compare with actual process
• 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. The present invention, in one implementation, provides methods, apparatuses and systems directed to facilitating the optimization or improvement of manufacturing processes relative to one or more criteria. In some implementations, the present invention facilitates the optimization of manufacturing processes relative to one or more attributes—such as cycle time, cost, and performance—while still optimizing process output relative to design specifications for a given article characteristic.

Claims

1. 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 iterations of a process, wherein each of the iterations corresponds to a process condition set of a plurality of process condition sets and wherein each process condition set of the plurality of process condition sets is associated with one or more process optimization criteria;

receiving a selection of a predictor characteristic from the plurality of article characteristics;

determining a regression model between the predictor characteristic and a selected remaining article characteristics of the plurality of article characteristics;

associating points or regions of the regression model with corresponding process condition sets of the plurality of process condition sets;

generating and displaying on a display device a diagram of the regression model and the points or regions corresponding to the process condition sets; and

displaying at least one of the one or more process optimization criteria in association with identifiers corresponding to the process condition sets.

2. The method of claim of claim 1 further comprising

determining, relative to the regression model, a target intersection between the predictor characteristic and the selected remaining article characteristic.

3. The method of claim of claim 2 wherein the diagram indicates the target intersection between the predictor characteristic and the selected remaining article characteristic.

4. The method of claim 1 further comprising wherein the regression model includes lower and upper prediction boundaries

receiving into the memory at least one of lower and upper specification limits for at least one of the predictor characteristic and the selected remaining article characteristic;

and

locating, relative to the regression model between the predictor characteristic and the selected remaining article characteristic, the at least one of lower and upper specification limits.

5. The method of claim 1 wherein the regression model includes lower and upper prediction boundaries

receiving lower and upper specification limits for the predictor characteristic and the selected remaining article characteristic;

locating, relative to the regression model between the predictor characteristic and the selected remaining article characteristic, the compliance area bounded by the upper and lower specification limits associated with the selected remaining article characteristic and the predictor characteristic; and

locating the bounded regression area for the selected remaining characteristic defined by the upper and lower prediction boundaries of the regression model and the upper and lower specification limits for the predictor characteristic.

6. The method of claim 5 further comprising

receiving a selected process condition set from the plurality of process condition sets;

and

facilitating determination of one or more changes to move the point or region on the regression model corresponding to the selected process condition set relative to the compliance area.

7. The method of claim 1 further comprising

receiving a selected process condition set from the plurality of process condition sets;

and

facilitating determination of one or more changes to the process to reduce a distance between the point or region on the regression model corresponding to the selected process condition set and a target intersection between the predictor characteristic and the selected remaining article characteristic.

8. The method of claim 1 further comprising

facilitating selection of a process condition set from the plurality of processing conditions sets based on one or more of the one or more performance optimization criteria.

9. The method of claim 8 wherein selection of the process condition set is based on one or more of the following performance optimization criteria:

Operating Process Capability (Opk);

cycle time;

cost;

energy consumption;

wear on equipment used in the process;

maintenance;

strength;

visual appearance;

performance; and

, consistency.

10. The method of claim 1 further comprising

receiving into the memory indications of associations between groups of article characteristic values of the plurality of article characteristic values and corresponding process condition sets.

11. The method of claim 1 further comprising

calculating a correlation coefficient between all or a subset of the plurality of article characteristics;

determining, based on the calculated correlation coefficients, a value indicating the predictive capability of a first article characteristic relative to all other article characteristics of the plurality of article characteristics;

repeating determining a value indicating the predictive capability for said all or a subset of the plurality of article characteristics; and

selecting the predictor characteristic based at least in part on the values indicating the predictive capabilities of the article characteristics of the plurality of article characteristics.

12. The method of claim 1 further comprising

determining a target intersection between the predictor characteristic and the selected remaining article characteristic;

receiving a selection of a process condition set from the plurality of process condition sets; and

facilitating determination of one or more changes to the process, or one or more design specifications associated with the process, to reduce a distance between the point or region on the regression model corresponding to the selected process condition set and the target intersection between the predictor characteristic and the selected remaining article characteristic.

13. The method of claim 12 wherein one or more changes to the process comprises one or more changes to tooling used in the process.

14. The method of claim 1 further comprising

receiving a selected process condition set from the plurality of process condition sets;

and

facilitating determination of one or more changes to the process, or one or more design specifications associated with the process, to reduce a distance between the point or region on the regression model corresponding to the selected process condition set and a target intersection between the predictor characteristic and the selected remaining article characteristic.

15. The method of claim 14 wherein one or more changes to the process comprises one or more changes to tooling used in the process.

16. The method of claim 1 wherein the one or more process optimization criteria is one or more of process cycle time and process cost.

17. An apparatus comprising:

a processor;

a memory;

an 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 iterations of a process, wherein each of the iterations corresponds to a process condition set of a plurality of process condition sets and wherein each process condition set of the plurality of process condition sets is associated with one or more process optimization criteria;

receive a selection of a predictor characteristic from the plurality of article characteristics;

determine the regression model between the predictor characteristic and a selected remaining article characteristics of the plurality of article characteristics;

associate points or regions of the regression model with corresponding process condition sets of the plurality of process condition sets;

generate and display on a display device a diagram of the regression model and the points or regions corresponding to the process condition sets; and

display at least one of the one or more process optimization criteria in association with identifiers corresponding to the process condition sets.

18. The apparatus of claim 17 wherein the one or more process optimization criteria is one or more of process cycle time and process cost.

19. A computer program product, physically stored on a computer-readable medium, comprising instructions operable to cause a programmable 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 iterations of a process, wherein each of the iterations corresponds to a process condition set of a plurality of process condition sets and wherein each process condition set of the plurality of process condition sets is associated with one or more process optimization criteria;

receive a selection of a predictor characteristic from the plurality of article characteristics;

determine the regression model between the predictor characteristic and a selected remaining article characteristics of the plurality of article characteristics;

associate points or regions of the regression model with corresponding process condition sets of the plurality of process condition sets; and

generate and display on a display device a diagram of the regression model and the points or regions corresponding to the process condition sets; and

display at least one of the one or more process optimization criteria in association with identifiers corresponding to the process condition sets.

20. A method, 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 iterations of a process, wherein each of the iterations corresponds to a process condition set of a plurality of process condition sets and wherein each process condition set of the plurality of process condition sets is associated with one or more process optimization criteria;

determining a regression model between first and second article characteristics in the plurality of article characteristics;

associating points or regions of the regression model with corresponding process condition sets of the plurality of process condition sets;

determining a target intersection between the first and second article characteristics;

generating and displaying on a display device a diagram of the regression model and the points or regions corresponding to the process condition sets; and

displaying at least one of the one or more process optimization criteria in association with identifiers corresponding to the process condition sets.

21. The method of claim 20 further comprising

receiving a selected process condition set from the plurality of process condition sets;

and

facilitating determination of one or more changes to the process, or one or more design specifications associated with the process, to reduce a distance between the point corresponding to the selected process condition set and a target intersection between the first article characteristic and the second article characteristic.

22. The method of claim 21 wherein one or more changes to the process comprises one or more changes to tooling used in the process.

23. The method of claim 20 further comprising

facilitating selection of a process condition set from the plurality of processing conditions sets based on one or more of the one or more performance optimization criteria.

24. The method of claim 23 wherein selection of the process condition is based on one or more of the following performance optimization criteria:

Operating Process Capability (Opk);

cycle time;

Lowest cost;

energy consumption;

wear on equipment used in the process;

maintenance;

strength;

visual appearance;

performance; and

, consistency.

25. The method of claim of claim 20 wherein the diagram indicates the target intersection between the first article characteristic and the second article characteristic.

26. The method of claim 20 further comprising

receiving indications of associations between groups of article characteristic values of the plurality of article characteristic values and corresponding process condition sets.

27. The method of claim 20 wherein the one or more process optimization criteria is one or more of process cycle time and process cost.

28. An apparatus comprising:

a processor;

a memory;

an 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 iterations of a process, wherein each of the iterations corresponds to a process condition set of a plurality of process condition sets and wherein each process condition set of the plurality of process condition sets is associated with one or more process optimization criteria;

determine the regression model between first and second article characteristics in the plurality of article characteristics;

associate points or regions of the regression model with corresponding process condition sets of the plurality of process condition sets; and

determine a target intersection between the first and second article characteristics;

generate and display on a display device a diagram of the regression model and the points or regions corresponding to the process condition sets; and

display at least one of the one or more process optimization criteria in association with identifiers corresponding to the process condition sets.

29. A computer program product, physically stored on a computer-readable medium, comprising instructions operable to cause a programmable 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 iterations of a process, wherein each of the iterations corresponds to a process condition set of a plurality of process condition sets and wherein each process condition set of the plurality of process condition sets is associated with one or more process optimization criteria;

determine the regression model between first and second article characteristics in the plurality of article characteristics;

associate points or regions of the regression model with corresponding process condition sets of the plurality of process condition sets;

determine a target intersection between the first and second article characteristics;

generate and display on a display device a diagram of the regression model and the points or regions corresponding to the process condition sets; and

display at least one of the one or more process optimization criteria in association with identifiers corresponding to the process condition sets.

30. A method, the method comprising

inputting into a computer-readable memory accessible to a process analysis system 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 iterations of a process, wherein each of the iterations corresponds to a process condition set of a plurality of process condition sets and wherein each process condition set of the plurality of process condition sets is associated with one or more process optimization criteria;

selecting a predictor characteristic from the plurality of article characteristics; and

,

causing the process analysis system to determine the regression model between the predictor characteristic and a selected remaining article characteristic of the plurality of article characteristics;

causing the process analysis system to associate, and display, points or regions of the regression model with corresponding process condition sets of the plurality of process condition sets, and to determine, relative to the regression model, a target intersection between the predictor characteristic and the selected remaining article characteristic;

causing the process analysis system to display at least one of the one or more process optimization criteria in association with identifiers corresponding to the process condition sets;

selecting a process condition set from the plurality of process condition sets; and

determining one or more changes to the process, or one or more design specifications associated with the process, to reduce a distance between the point or region on the regression model corresponding to the selected process condition set and the target intersection between the predictor characteristic and the selected remaining article characteristic.