Provision of data for analysis

• US 20050049988A1
• Filed: 05/14/2004
• Published: 03/03/2005
• Est. Priority Date: 11/16/2001
• Status: Abandoned Application

• Current Assignee: ABB AB (ABB Limited)
• Original Assignee: ABB AB (ABB Limited)
• Inventors: Vallmar, Gerhard, Milanovic, Raiko, Dahlquist, Erik, Weidl, Galia
• Application Number:
  US10/845,519
• Publication Number:
  US 20050049988A1
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA

Abstract

A method of providing data for root cause analysis. Data is transferred from a structured data model into a causally oriented data model. The causally oriented data model is complemented with information associated with conditional probabilities between at least two objects of the causally oriented data model.

Claims

1. A method of providing data for root cause analysis, the method comprising:

transferring data from a structured data model into a causally oriented data model; and

complementing the causally oriented data model with information associated with conditional probabilities between at least two objects of the causally oriented data model.

2. The method according to claim 1, wherein the structured data model comprises a hierarchically structured data model.

3. The method according to claim 1, wherein the structured data model includes an event object that has at least one child object, each child object including information of hypothesis associated with possible root causes of the event and said child objects have further child objects including information associated with symptoms of said possible causes.

4. The method according to claim 1, wherein said data transfer comprises mapping of data from the structured data model to the causally oriented data model based on causality links between objects of the structured data model.

5. The method according to claim 1, wherein in the causally oriented data model a hypothesis object refers to at least one symptom object and said at least one symptom object refers to an event object.

6. The method according to claim 1, wherein the structured data model contains data regarding hypothesis and symptoms of the hypotheses, the method comprising mapping of the symptoms in the structured data model into symptom objects of the causally oriented data model, mapping of the hypotheses of the structured data model into root cause objects of the causally oriented data model and mapping of the relations between the symptoms and the hypothesis into causality links of the causally oriented data model.

7. The method according to claim 6, wherein the causality links are mapped in the direction from cause to effect.

8. The method according to claim 1, wherein the causally oriented data model comprises a graphical model.

9. The method according to claim 8, wherein the graphical model comprises a directed acyclic graph.

10. The method according to claim 1, wherein the completed causally oriented data model comprises a Bayesian Network.

11. The method according to claim 1, wherein the hierarchically structured data model comprises an extended mark-up language (XML) file.

12. The method according to claim 1, wherein the completion of the causally oriented data model is based on information associated with the causality relations of the objects.

13. The method according to claim 1, wherein said information comprises quantitative information from another type of structured data associated with conditional probability distributions between at least two objects.

14. The method according to claim 1, wherein the conditional probabilities are between symptom objects and root cause objects of the causally oriented data model.

15. The method according to claim 1, wherein the causally oriented data model is completed by at least one conditional probability table.

16. The method according to claim 15, wherein the conditional probability tables are generated based on knowledge about the subject of the analysis and/or information about previous failures and/or failure frequencies that are characteristic for the particular problem domain.

17. The method according to claim 15, wherein the completed causally oriented data model is provided by filling in uniform conditional probability tables with probability values.

18. The method according to claim 1, wherein the information associated with the conditional probabilities represents conditional probability distribution of objects in the causally oriented data model.

19. The method according to claim 1, wherein the transfer is accomplished such that the completed causally oriented data model reflects the hierarchical structure of the structured data model.

20. The method according to claim 1, wherein at least two root cause hypotheses are processed simultaneously based on at least one complemented causally oriented data model.

21. The method according to claim 1, comprising transportation of the causally oriented data model via a data network.

22. The method according to claim 21, wherein at least a part of the transportation occurs via internet protocol data communication environment.

23. The method according to claim 1, wherein causally oriented data models are generated and stored in a central storage entity based on information from a plurality of individual sources.

25. A computer program product comprising program code means for performing the steps of claim 1 when the program is run on a computer.

24. A translator engine for provision of data for root cause analysis, the translator engine comprising:

translator means for transferring data from a structured data model into a causally oriented data model; and

processor means for complementing the causally oriented data model with information associated with conditional probabilities between at least two objects of the causally oriented data model.

26. A method of analyzing a facility, comprising:

providing data for the analysis by transferring data that associates with the facility from a structured data model into a causally oriented data model and by complementing the causally oriented data model with information associated with conditional probabilities between at least two objects of the causally oriented data model; and

simultaneously analyzing at least two root cause hypotheses based on the complemented causally oriented data model.

27. The method according to claim 26, further comprising presenting a list of symptoms to a user.

28. The method according to claim 26, wherein the complementing of the causally oriented data model is accomplished adaptively based on updated information regarding the facility to be analysed.

29. The method according to claim 28, wherein said update of said information is automatic.

30. The method according to claim 26, wherein the analysis comprises a search for the most probable cause for an event by means of a Bayesian Network.

31. The method according to claim 26, wherein the hypothesis are ranked in probability order.

32. The method according to claim 31, wherein a user is notified about a change in the ranking of a hypothesis.

33. The method according to claim 26, further comprising transportation of data model via a data communication network.

34. The method according to claim 26, wherein an item of data is transmitted via a wireless interface.

35. The method according to claim 26, wherein observed symptoms are entered into the analysis in one evidence vector.

36. The method according to claim 26, wherein results of the analysis are presented for a user by means of a portable device.

37. The method according to claim 26, comprising presenting instructions to a user based on the analysis by means of user interface device.

38. The method according to claim 26, wherein causally oriented data models are stored as aspects of real world objects in a model describing the facility.

39. An analyzer arrangement for analyzing a facility, comprising an analyzer and data means for provision of data for the analyzer, wherein

the data means are arranged to transfer data that associates with the facility from a structured data model into a causally oriented data model and to complement the causally oriented data model with information associated with conditional probabilities between at least two objects of the causally oriented data model, and

the analyser is arranged to simultaneously analyse at least two root cause hypotheses based on said complemented causally oriented data model.

40. An analyzer arrangement according to claim 39, further comprising a user interface for presenting possible root causes of an event for a user.

41. An analyzer arrangement according to claim 40, the user interface comprising a portable device adapted for communication over a wireless interface.

42. The analyzer arrangement according to claim 39, wherein at least a part of the data form the analysis is provided from a remote data storage means.

43. An analyzer arrangement according to claim 42, wherein the data storage means is shared by a plurality of users.

44. A control system for controlling a facility, comprising an analyzer arrangement according to claim 39.

45. The control system according to claim 44, wherein the causally oriented data models are used for simulation of the impact of an action taken by an operator before any real action is performed.

46. A data signal for input in a root cause analysis, the data signal being for signaling a causally oriented data model that has been created by transferring data from a structured data model into a causally oriented data model and complementing the causally oriented data model with information associated with conditional probabilities between at least two objects of the causally oriented data model.

47. A portable user device for use in control of a facility, the user device comprising means for presenting to a user results of a root cause analysis performed based on a causally oriented data model that has been created by transferring data from a structured data model into a causally oriented data model and by complementing the causally oriented data model with information associated with conditional probabilities between at least two objects of the causally oriented data model.

48. The portable user device according to claim 47, further comprising input means for input of information for use by the root cause analysis.