Function-based method for classifying and fusing system behavior information in product development

Patent metadata

Field	Value
Publication number	US-9317596-B2
Application number	US-201414551723-A
Country	US
Kind code	B2
Filing date	Nov 24, 2014
Priority date	Apr 3, 2014
Publication date	Apr 19, 2016
Grant date	Apr 19, 2016

Abstract

A method of automatically developing an ontology for product function and failure mode documentation for an apparatus. The apparatus is identified. A function-flow model is generated for the identified apparatus for identifying a composite structure of the apparatus. Functions and failure modes associated with the identified apparatus are enumerated. Failure data is obtained from a plurality of heterogeneous data sources. A semantic similarity module is applied to the enumerated failures by comparing a plurality of documents between the data sources. The semantic similarity module bridges a variety of terms used in the heterogeneous data to describe a respective failure. Failures associated with the enumerated apparatus functions are extracted from the plurality of documents between heterogeneous data sources. A composite of related terminology is generated for each identified failure mode. A failure mode information document is generated utilizing the composite of related terminology for each identified failure mode.

First claim

What is claimed is:

1. A method of automatically developing an ontology for product function and failure mode documentation for an apparatus, the method comprising the steps of:
identifying the apparatus;
generating a function-flow model for the identified apparatus for identifying a composite structure of the apparatus;
enumerating functions associated with the identified apparatus;
enumerating failure modes for the enumerated apparatus functions;
obtaining failure data from a plurality of heterogeneous data sources;
applying a semantic similarity module to the enumerated failures by comparing a plurality of documents between heterogeneous data sources, the semantic similarity module bridging a variety of terms used in the heterogeneous data to describe a respective failure;
extracting failures associated with the enumerated apparatus functions from the plurality of documents between heterogeneous data sources;
generating a composite of related terminology for each identified failure mode; and
generating a failure mode information document utilizing the composite of related terminology for each identified failure mode.

2. The method of claim 1 wherein the function-flow model identifies a functional composition relating to classification bins.

3. The method of claim 2 wherein each classification bin is a comprehensive failure structure for an associated function.

4. The method of claim 1 wherein the function-flow model identifies boundaries on how the identified apparatus should function.

5. The method of claim 4 wherein the function-flow model identifies primary functions of the identified apparatus.

6. The method of claim 4 wherein the function-flow model identifies indirect functions of the identified apparatus.

7. The method of claim 4 wherein the function-flow model identifies interactions with components interacting with the apparatus.

8. The method of claim 4 wherein the function-flow model identifies failure conditions of the identified apparatus.

9. The method of claim 1 wherein enumerating functions associated with the identified apparatus include identifying all functionality associated with the identified apparatus.

10. The method of claim 1 wherein enumerating failure modes for the enumerated apparatus functions includes identifying how the identified apparatus fails.

11. The method of claim 1 wherein obtaining failure data from the plurality of heterogeneous data sources includes obtaining standard and non-standard language of reported failures.

12. The method of claim 1 wherein obtaining failure data from the plurality of heterogeneous data sources includes a plurality of failure reporting entities.

13. The method of claim 1 wherein the plurality of failure reporting entities include customer entities that collect customer complaints.

14. The method of claim 1 wherein the plurality of failure reporting entities include customer entities that assemble the identified apparatus.

15. The method of claim 1 wherein generating a composite of related terminology for each identified failure mode includes fusing heterogeneous data from plurality of sources and classifying the failure according to a type of failure.

16. The method of claim 1 wherein generating a failure mode document includes generating a design failure effects and analysis document.

17. The method of claim 1 wherein generating a failure mode document includes generating a function-failure design method document.

18. The method of claim 1 wherein the semantic similarity module provides a degree of linking relationships between data of the heterogeneous data sources.

19. The method of claim 18 wherein the semantics similarity module conjugates verbs between the data of the heterogeneous data sources.

20. The method of claim 18 wherein the semantics similarity module enumerates synonyms between the data of the heterogeneous data sources.

21. The method of claim 18 wherein the semantics similarity module identifies misspellings for identifying related terms.

22. The method of claim 1 wherein the semantics similarity module assigns a part-of-speech tag to a respective term for determining whether the term is a part, symptom, action, or failure mode term.

23. The method of claim 1 wherein the semantics similarity module identifies a term as a focal term, the semantics similarity module determining co-occurring terms within a pre-determined distance of the selected focal terms, and where contextual information is collected enabling comparison of terms in similar context.

24. The method of claim 1 wherein the semantics similarity module identifies terms as critical phrases and non-critical phrases, and wherein the semantics similarity module disregards the non-critical phrases.

Assignees

• Gm Global Tech Operations Inc

Inventors

• Donndelinger Joseph A
• Cafeo John A
• De Soumen
• Rajpathak Dnyanesh
• Peranandam Prakash M
• Darden Kay L

Classifications

• G06Q10/06 Primary

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06F17/30336

  Physics · mapped topic

• G06F17/30734 Primary

  Physics · mapped topic

• G06F2201/80

  Database-specific techniques · CPC title

• G06F17/30604

  Physics · mapped topic