System for analyzing and improving pharmaceutical and other capital-intensive manufacturing processes

• US 6,243,615 B1
• Filed: 09/09/1999
• Issued: 06/05/2001
• Est. Priority Date: 09/09/1999
• Status: Expired due to Term

• Current Assignee: Dassault Systemes Americas Corp. (Dassault Systemes SA)
• Original Assignee: Aegis Analytical Corp. (Dassault Systemes SA)
• Inventors: Neway, Justin O., Durfee, Steven L., Jahn, Gretchen L.
• Primary Examiner(s): Grant, William
• Assistant Examiner(s): PATEL, RAMESH B
• Application Number:
  US09/392,928
• Time in Patent Office: 635 Days
• Field of Search: 700/17, 700/51, 700/52, 700/83, 700/95, 700/96, 700/104, 700/108, 700/109, 700/110, 700/111, 707/102, 707/103, 707/104, 705/1, 705/7, 705/8-9, 705/11
• US Class Current: 700/108
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/06393 Score-carding, benchmarking or key performance indicator [KPI] analysis
• CPC Class Codes: G06Q 10/06395 Quality analysis or management
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method for displaying a visual process signature for ready visual recognition and communication of otherwise complex manufacturing process information. Process data may be stored in a plurality of data stores, each data store holding a plurality of records containing process data, each record associated with at least one process component. A proxy virtual database is created from copies of records selected from the data stores. Statistical analysis operations are applied to the selected records within the proxy virtual database to identify process components or combinations of process components having a significant effect on characteristics of a product produced as well as the magnitude of that effect. At least three characteristics of the identified process components including the outcome of the statistical analysis operations are selected and visually displayed in a static or animated three-dimensional representation shown on a two-dimensional display. The visual display indicates the directionality and the extent of the selected characteristics of the selected process components in relation to the selected characteristics of the product produced.

Claims

1. A system for analyzing manufacturing process data to identify manufacturing process components affecting characteristics of a product produced by a manufacturing process, the system comprising:

a plurality of data stores holding a plurality of records containing process data, each record associated with at least one of the process components;

a virtual database engine coupled to the plurality of data stores;

a user interface enabling a user to select records from within the data stores;

a proxy virtual database created by the virtual database engine, the proxy database comprising copies of the selected records;

a statistical analysis engine operatively coupled to the proxy virtual database to apply statistical analysis operations to the selected records within the proxy database and identify process components or combinations of process components having a significant effect on the characteristics of the product produced;

a first graphical interface component displaying a two-dimensional relationship between process components or groups of process components and characteristics of the product produced indicating directionality and extent of correlation between the identified process components and the characteristics of the product produced; and

a second graphical interface component enabling display of at least three dimensional relationships indicating directionality and extent of correlation between the identified process components and the characteristics of the product produced.

2. The system of claim 1 wherein one of the first and second graphical interfaces are animated.

3. The system of claim 2 wherein the animation comprises displaying frames ordered by the magnitude of a group of process outcomes.

4. The system of claim 2 wherein the animation comprises displaying frames ordered by the magnitude of a group of selected process components.

5. The system of claim 2 wherein the animation comprises displaying frames ordered by date of manufacture.

6. The system of claim 2 wherein the animation comprises displaying frames ordered by batch number.

7. The system of claim 2 wherein the animation comprises displaying frames ordered by lot number.

8. A method for displaying a visual process signature for ready visual recognition and communication of process data, the method comprising the steps of:

storing process data in a plurality of data stores, each data store holding a plurality of records containing process data, each record associated with at least one process component;

selecting records from within the plurality of data stores;

creating a proxy virtual database comprising copies of the selected records;

applying statistical analysis operations to the selected records within the proxy virtual database to identify process components or combinations of components having a significant effect on characteristics of a product produced,

selecting at least three characteristics of the identified process components; and

visually displaying process data associated with the three selected characteristics in a three-dimensional representation displayed on a two-dimensional display, the visual display indicating directionality and extent of the characteristics of the selected process components in relation to the selected characteristics of the product produced.

9. The method of claim 8 wherein the visual process signature is animated.

10. The method of claim 9 wherein the animation comprises displaying frames ordered in a manner selected from the group consisting of:

a moving average, a weighted moving average, a moving range, a moving standard deviation, and a moving variance, each ordered by the magnitude of a group of process outcomes.

11. The method of claim 9 wherein the animation comprises displaying frames ordered in a manner selected from the group consisting of:

a moving average, a weighted moving average, a moving range, a moving standard deviation, and a moving variance, each ordered by the magnitude of a group of process components.

12. The method of claim 9 wherein the animation comprises displaying frames in a manner selected from the group consisting of:

a moving average, a weighted moving average, a moving range, a moving standard deviation, and a moving variance, each ordered by the magnitude of the difference between the best and worst group of process outcomes from the smallest difference to the largest difference or vise versa.

13. The system of claim 9 wherein the animation comprises displaying frames in a manner selected from the group consisting of:

a moving average, a weighted moving average, a moving range, a moving standard deviation, and a moving variance, each ordered by the difference between the maximum and minimum of a selected group of process components or operations from the smallest difference to the largest difference or vice versa.

14. The system of claim 9 wherein the animation comprises displaying frames in a manner selected from the group consisting of:

a moving average, a weighted moving average, a moving range, a moving standard deviation, and a moving variance, each ordered by the date of manufacture, batch number or lot number.

15. A method for producing a visual process signature representing a manufacturing process, the method comprising the steps of:

providing a data source holding groups of data, each group representing process parameters of a manufacturing process;

selecting at least three characteristics of the groups of data;

generating a plurality of display frames, where each display frame represents the selected characteristics of a particular group of data in a three-dimensional representation; and

visually displaying the generated display frames in a sequential fashion to present an animated visual process signature to a user.

16. The method of claim 15 where each frame comprises first, second and third axes, the method further comprising the steps of:

displaying data from the data source in each frame so that the displayed position on the first axis is derived from the magnitude of the corresponding parameter;

displaying the data from the data source so that the data'"'"'s position on the second axis comprises a name for the parameter; and

displaying the data from the data source so that the data'"'"'s position on the third axis comprises a group statistic of the selected data in the corresponding group of data.

17. The method of claim 16 wherein the group statistic is selected from the group consisting of:

group mean, group range, group standard deviation, group relative standard deviation;

group variance;

group maximum;

group minimum;

group principle component regression loading;

group correlation coefficient; and

group P value.

18. The method of claim 16 wherein the visually displaying further comprises:

selecting one of the parameter names as represented on the second axis;

ordering the frames from highest to lowest according to the value of the data corresponding to the selected parameter name on the first axis; and

displaying the sequence in a sequential fashion determined from the ordering step.

19. The method of claim 18 wherein the selected parameter is indicated using a color distinct from the non-selected parameters during the displaying step.

20. The method of claim 16 wherein the visually displaying further comprises:

ordering the frames on a data group-by-data group basis according to a relative time at which the data in each of the data groups was gathered; and

displaying the sequence in a sequential fashion determined from the ordering step.

21. The method of claim 16 wherein the visually displaying further comprises:

selecting one of the parameter names as represented on the second axis;

determining a group having a best performance for the selected parameter;

determining a group having a worst performance for the selected parameter;

ordering the frames from highest to lowest according to a difference between the best and word performance of the selected process parameter; and

displaying the sequence in a sequential fashion determined from the ordering step.

22. The method of claim 15 wherein the displaying is performed on a two-dimensional display, the visual display indicating directionality and extent of the characteristics of the selected process components in relation to the selected characteristics of the product produced.

23. The method of claim 15 wherein the groups of data correspond to data associated with groups of production batches within the manufacturing process.