Method using statistically analyzed product test data to control component manufacturing process

• US 6,615,096 B1
• Filed: 01/31/2000
• Issued: 09/02/2003
• Est. Priority Date: 01/31/2000
• Status: Expired due to Term

• Current Assignee: Teradata US, Inc. (Teradata Corporation)
• Original Assignee: NCR Corporation
• Inventors: Hill, Gerald L., Perez, Linda S., Durrant, Douglas J.
• Primary Examiner(s): Picard, Leo
• Assistant Examiner(s): Garland, Steven R.
• Application Number:
  US09/494,175
• Time in Patent Office: 1,310 Days
• Field of Search: 700/95, 700/115, 700/116, 700/215, 700/221, 700/224-227, 700/105-111, 700/121, 702/81, 702/84, 702/179, 702/180, 702/182, 702/183, 702/185, 702/187, 705/7, 705/28, 705/29, 707/104.1
• US Class Current: 700/115
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A method and system for providing a manufacturing information system is disclosed. The system comprises a means for receiving and storing in a data warehouse component identifiers for identifying component manufacturing parameters for a quantity of components. The system further includes product identifiers for identifying manufactured products. The system further comprises a relational means for relating the component identifiers with the product identifiers for the products in which the components are included. The system further comprises a means for receiving a sub-set of the product identifiers, wherein the sub-set of product identifiers is for identifying a sub-set of the products which have a variation in performance. The system further comprises an analytical tool for correlating at least one of the component identifiers with the received sub-set of product identifiers, thereby identifying the component manufacturing parameter identified by the at least one component identifier as a possible cause of the variation in performance.

Claims

1. A manufacturing information system for controlling the quality of components received from component suppliers and incorporated into products manufactured by a product manufacturer, said system comprising:

a means for receiving a plurality of component identifiers for identifying component lot data records for a plurality of components received from at least one component supplier, each component identifier for identifying a component lot data record for a sub-set of the plurality of components;

a plurality of product identifiers for identifying a plurality of products manufactured by said product manufacturer;

a data warehouse for storing the product identifiers and the component identifiers;

a relation means for relating the component identifiers of components incorporated into said products with the product identifiers for products in which the plurality of components are included;

a means for determining a sub-set of the product identifiers, the sub-set of product identifiers identifying a sub-set of the products which have a variation in performance; and

an analytical tool for correlating at least one of the component identifiers with the designated sub-set of product identifiers thereby identifying the component lot data record identified by the at least one component identifier as a possible cause of the variation in performance.

2. The system of claim 1, wherein the analytical tool comprises a statistical tool.

3. The system of claim 1, wherein the analytical tool comprises a visualization tool.

4. The system of claim 1, wherein the analytical tool comprises an on-line analytical processing tool.

5. The system of claim 1, wherein the analytical tool comprises an information broadcast tool.

6. The system of claim 1, wherein the analytical tool comprises a data mining tool.

7. The system of claim 6, wherein the data mining tool comprises a plurality of data mining sub-routines for executing to identify the at least one component identifier.

8. The system of claim 7, wherein each sub-routine comprises an algorithm defining a predictor for predicting the correlating between the at least one component identifier and the sub-set of product identifiers.

9. The system of claim 1, further comprising a correlation output means for presenting output from the analytical tool.

10. The system of claim 1, wherein the means for receiving the component identifiers comprises a network interface electrically connected to a network, the component suppliers electrically connected to the network over which the component identifiers are transmitted.

11. The system of claim 1, wherein the means for receiving the component identifiers is a data input terminal for entering the component identifiers into the data warehouse.

12. The system of claim 1, wherein the means for designating the sub-set of product identifiers comprises an input terminal for entering product identifiers for products which have the variation in performance.

13. The system of claim 1, wherein the means for designating the sub-set of product identifiers comprises a means for capturing failure analysis data from the products which have the variation in performance.

14. The system of claim 1, wherein the means for designating the sub-set of product identifiers comprises a means for entering product identifiers for products which have the variation in performance from an assembly line testing system.

15. The system of claim 1, wherein the means for designating the sub-set of product identifiers comprises a means for designating product identifiers for products which are returned to the manufacturer.

16. The system of claim 1, wherein each component lot data record includes an identification code and a plurality of parameter values for identifying component manufacturing parameters.

17. The system of claim 16, wherein the component manufacturing parameters comprise traceable factory, line and process parameters.

18. A component supplier information system for controlling the quality of components provided to a product manufacturer and incorporated into products manufactured by said product manufacturer, said system comprising:

a plurality of component identifiers corresponding to component lot data records for a plurality of components provided to said product manufacturer, each component identifier for identifying a component lot data record for a sub-set of the plurality of components;

a means for receiving product identifiers for identifying products in which the plurality of components are included;

a data warehouse for storing the product identifiers and the component identifiers;

a relational means for relating the component identifiers of components incorporated into said products with the product identifiers for products in which the components are included;

a means for determining a sub-set of the product identifiers, the sub-set of product identifiers identifying a sub-set of the products which have a variation in performance; and

an analytical tool for correlating at least one of the component identifiers with the designated sub-set of product identifiers thereby identifying the component lot data record identified by the at least one component identifier as a possible cause of the variation in performance.

19. The system of claim 18, wherein the analytical tool comprises a data mining tool.

20. The system of claim 19, wherein the data mining tool comprises a plurality of data mining sub-routines for executing to identify the at least one component identifier.

21. The system of claim 20, wherein each sub-routine comprises an algorithm defining a predictor for predicting the correlating between the at least one component identifier and the sub-set of product identifiers.

22. The system of claim 20, wherein each sub-routine is for correlating the at least one component identifier by testing for a selected type of correlation between the sub-set of product identifiers and the at least one component identifier.

23. In a manufacturing information system, a method for using statistically analyzed manufacturing data for controlling the quality of components received from component suppliers and incorporated into products manufactured by a product manufacturer, said method comprising the steps of

receiving component identifiers for identifying component lot data records for a plurality of components received from at least one component supplier, each component identifier for identifying a component lot data record for a sub-set of the plurality of components;

creating product identifiers for identifying products manufactured by the product manufacturer;

relating the component identifiers of components incorporated into said products with the product identifiers for the products which include the components;

determining a sub-set of product identifiers which identify products which have a variation in performance; and

correlating at least one of the component identifiers with the designated sub-set of product identifiers thereby identifying the component lot data record identified by the at least one component identifier as a possible cause of the variation in performance.

24. The method of claim 23, further comprising presenting the correlation.

25. The method of claim 24, wherein the step of correlating the at least one component identifier comprises executing a data-mining computer program comprising a plurality of data-mining algorithms.

26. In a manufacturing information system, a method for using statistically analyzed manufacturing data for controlling the quality of products manufactured by a product manufacturer and including components received from component suppliers, comprising the steps of

creating component identifiers for identifying component lot data records for a quantity of components received from at least one component supplier, each component identifier for identifying a component lot data record for a sub-set of the plurality of components;

creating product identifiers for identifying products manufactured by the product manufacturer;

relating the component identifiers of components incorporated into said products with the product identifiers for the products which include the components;

determining a sub-set of product identifiers which identify products which have a variation in performance; and

correlating at least one of the component identifiers with the designated sub-set of product identifiers thereby identifying the component lot data record identified by the at least one component identifier as a possible cause of the variation in performance.