Analysing events

• US 20050043922A1
• Filed: 05/14/2004
• Published: 02/24/2005
• Est. Priority Date: 11/16/2001
• Status: Abandoned Application

• Current Assignee: ABB AB (ABB Limited)
• Original Assignee: ABB AB (ABB Limited)
• Inventors: Vollmar, Gerhard, Weidl, Galia
• Application Number:
  US10/845,518
• Publication Number:
  US 20050043922A1
• Time in Patent Office: Days
• US Class Current: 702/183
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

An arrangement for provision of information about causes of events in association with an equipment. The arrangement includes a data storage medium for storing beforehand prepared data that associates with the equipment. The data provides predetermined information about events that can associate with the equipment, hypotheses for the root causes of the events and symptoms for the hypotheses. A processor analyses a plurality of root cause hypotheses by processing information obtained from the data storage medium.

Claims

1. An arrangement for provision of information about causes of events in association with an equipment, comprising:

a data storage medium for storing beforehand prepared data that associates with the equipment, said data containing predetermined information about events that can associate with the equipment, hypotheses for the root causes of the events and symptoms for the hypotheses; and

a processor arranged to analyze a plurality of root cause hypotheses by processing information obtained from the data storage medium.

2. The arrangement according to claim 1, wherein at least two root cause hypotheses are processed simultaneously.

3. The arrangement according to claim 2, wherein said at least two root cause hypotheses share at least one common symptom.

4. The arrangement according to claim 1, wherein a predetermined number of variables is stored in the data storage medium.

5. The arrangement according to claim 4, wherein a fixed number of variables is stored in the data storage medium.

6. The arrangement according to claim 1, wherein the data is organized in objects, said objects being organized onto a model wherein at least one of the objects includes information about a possible event, at least one of the objects includes information of hypothesis associated with possible root causes of the event and at least one of the objects includes information associated with symptoms of said possible causes.

7. The arrangement according to claim 6, wherein the data model comprises a causally oriented data model.

8. The arrangement according to claim 7, wherein the causally oriented data model is generated by processing a structured data model.

9. The arrangement according to claim 6, wherein the causally oriented data model comprises a Bayesian Network.

10. The arrangement according to claim 6, wherein the causally oriented data model comprises conditional probability information, said information being provided by calculating probabilities based on quantitative data associated with the frequency and/or weightings of the events.

11. The arrangement according to claim 1, wherein data is stored as an aspect of an object in a model describing a facility.

12. The arrangement according to claim 1, wherein the data storage medium comprises a computer readable data carrier.

13. The arrangement according to claim 12, wherein the data storage medium is selected from the list of:

a memory chip, a memory card, a memory tape, a compact disk, digital video disk, diskette.

14. The arrangement according to claim 1, wherein the data storage medium comprises a data entity that is provided for the analysis via a data network.

15. The arrangement any preceding according to claim 1, wherein the data storage medium is prepared by an analysis information provision entity, said entity being arranged to gather information from various sources.

16. The arrangement according to claim 15, wherein information is gathered by means of measurement means and/or monitoring means and/or sensors and/or a control system and/or computations.

17. The arrangement according to claim 1, wherein the data storage medium contains at least one causally oriented data model and program code means for processing said at least one causally oriented data model.

18. The arrangement according to claim 1, wherein the data storage medium comprises a structured data model and said processor is provided with translation means for generating a causally oriented data model based on the structured data model.

19. The arrangement according to claim 1, wherein the processor and the storage medium are provided in association with the equipment to be analyzed.

20. The arrangement according to claim 1, wherein the processor and the storage medium are provided in association with a portable device.

21. The arrangement according to claim 1, further comprising input means for input of observed symptoms.

22. The arrangement according to claim 21, wherein the observed symptoms can be input in a substantially real-time manner for provision of a substantially real-time root cause analysis.

23. The arrangement according to claim 1, wherein the results of the root cause analysis can be updated by propagating observed symptoms through the causally oriented data model.

24. The arrangement according to claim 1, further comprising a display for presenting the results of the analysis.

25. The arrangement according to claim 1 providing a decision support tool for the operator of the equipment.

26. The arrangement according to claim 1, wherein a predictive root cause analysis is provided.

27. The arrangement according to claim 1, wherein a predefined action is to be taken in response to the results of the analysis.

28. A data storage medium for storing of data that has been prepared beforehand for use at an analyzer, the data storage medium containing predefined information regarding possible events in association with an equipment in a form of data model that comprises objects containing information about the possible events, about root cause hypotheses for said possible events and symptoms for said hypotheses, and causality links for provision of probabilistic associations between the objects.

29. The data storage medium according to claim 28, wherein the number of variables and/or of failure hypotheses is limited.

30. The data storage medium according to claim 28 or 29, wherein the data storage medium be generated based on information obtained through domain experience and/or expertise and/or other existing data about the subject of the analysis.

31. The data storage medium according to claim 28, wherein the data model with causality links between the objects has been generated based on a structured data model.

32. The data storage medium according to claim 31, wherein the structured data model comprises a mark-up language data file, preferably an XML document and said causally oriented data model comprises a Bayesian Network.

33. A method of providing information about events in association with an equipment, comprising:

preparing a data model that associates with the equipment, said data model containing information about possible events, hypotheses for the root causes of the possible events and symptoms for the hypotheses;

storing the data model on a data storage medium;

input of symptoms into an analyzer;

transferring data from the data storage medium to the analyzer; and

analysing hypotheses for root causes by processing the symptoms input into the analyzer and the data obtained from the data storage medium.

34. The method according to claim 33, wherein a plurality of root cause hypotheses is processed simultaneously.

35. A device comprising:

means for provision of the intended operation of the device;

data storage medium for storing of data that has been prepared beforehand for use in analysis of the device, the data storage medium containing predefined information regarding possible events in association with the device in a form of data model that comprises objects containing information about the possible events, about root cause hypotheses for said possible events and symptoms for said hypotheses; and

a processor for analyzing the operation of the device based on data stored in the data storage medium.

36. A movable device for provision of analysis regarding an equipment, the movable device comprising:

a data storage medium for storing of data that has been prepared beforehand for use in analysis of the equipment, the data storage medium containing predefined information regarding possible events in association with the equipment in a form of data model that comprises objects containing information about the possible events, about root cause hypotheses for said possible events and symptoms for said hypotheses; and

a processor for analyzing the operation of the equipment based on data stored in the data storage medium.

37. The movable device according to claim 36, further comprising a user interface for presenting results of the analysis and/or for input of symptoms for the analysis.

38. The movable device according to claim 37 being arranged to process in a substantially real-time manner the symptoms input into the device.

39. The movable device according to claim 37 wherein the symptoms are of a predictive character.

40. The movable device according to claim 36, arranged to presents at least one of the following:

an optimal sequence of actions;

an appropriate action to be taken by the user of the device;

probabilities of simulated effects from an intended action.