Methods and apparatus for monitoring system performance

• US 5,067,099 A
• Filed: 04/10/1989
• Issued: 11/19/1991
• Est. Priority Date: 11/03/1988
• Status: Expired due to Term

• Current Assignee: Dio Technology Holdings LLC (Intellectual Ventures LLC)
• Original Assignee: Alliedsignal Inc. (Honeywell International Inc.)
• Inventors: McCown, Patricia M., Jessen, Karl M., Conway, Timothy J.
• Primary Examiner(s): Black, Thomas G.
• Application Number:
  US07/335,464
• Time in Patent Office: 953 Days
• Field of Search: 364/550, 364/513, 364/150, 371/26, 371/25.1
• US Class Current: 702/183
• CPC Class Codes: G06F 11/2257 using expert systems
• CPC Class Codes: G06F 11/34 Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment

Abstract

Method and apparatus for performing system monitoring and diagnostics is disclosed. In performing system monitoring, data is acquired from the system under test and compared to an event model. The event model comprises a database having event records which pre-define events which can occur. Each event record includes a state vector dependency which lists the events which must occur prior to the pre-defined event occurring and one or more critical parameters defining the data which must occur during the system'"'"'s performance for the event to have occurred. Event recognition is performed by comparing each event record to acquired operational data and to events already recognized. Associated with each event record in the database is an intelligent data acquisition action which defines an action to be taken as a result of the event record being recognized. These actions can modify the performance of the system being monitored or the acquisition of data. Additionally, the results of the event recognition step can be further analyzed in a computer.

Claims

1. A method for monitoring a system'"'"'s performance, comprising the steps of:

(a) modeling the system'"'"'s performance with a database having a plurality of event records, each of said plurality of event records pre-defining an event that can occur during operation of the system by those events on whose occurrence the occurrence of said pre-defined event is dependent and by one or more critical parameters defining operational data which must occur during the system'"'"'s performance for said pre-defined event to occur;

(b) acquiring a plurality of operational data samples from the system during a period of operation with a data acquisition system;

(c) for a first of said plurality of event records, comparing said events on whose occurrence the occurrence of said pre-defined event is dependent to a list of prior recognized events, if said first of said plurality of event records is so pre-defined;

(d) for said first of said plurality of event records, comparing a first of said plurality of said acquired operational data samples to said one or more critical parameters in said first of said plurality of event records, if a match is found in step (c) or if step (c) need not be performed;

(e) recognizing said event pre-defined by said first of said event records as having occurred during operation of the system if a match is found between said first of said plurality of acquired operational data samples and said one or more critical parameters from said first of said plurality of event records and adding said recognized event to said list of recognized events;

(f) repeating steps (d) and (e) for each successive acquired operational data sample in said plurality of acquired operational data samples unless said first of said plurality of event records is recognized in step (e);

(g) repeating steps (c), (d), (e) and (f) for each successive event record in said plurality of event records; and

(h) analyzing said recognized events to determine the system'"'"'s performance.

2. The method as claimed in claim 1, further comprising the step of:

(i) modifying a performance parameter in the system as a result of said analyzing step (h) to obtain a desired performance level of the system.

3. The method as claimed in claim 1, further comprising the step of:

(i) modifying said data acquisition system to enable acquisition of a second plurality of operational data samples in accordance with the results of said analyzing step (h);

4. The method as claimed in claim 3, wherein said data acquisition system'"'"'s channel configuration is modified.

5. The method as claimed in claim 3, wherein said data acquisition system'"'"'s sampling rate is modified.

6. The method as claimed in claim 3, wherein said data acquisition system'"'"'s sampling window specifying said period of operation is modified.

7. The method as claimed in claim 1, wherein said model of the system is modified in accordance with the results of said analyzing step (h).

8. The method as claimed in claim 1, further comprising the step of:

(i) providing a warning to an operator of the system where said analyzing step (h) indicates an abnormal performance status for the system.

9. The method as claimed in claim 1, wherein said analysis step (h) is performed prior to said steps of data acquisition and event recognition and a result of said analysis step (h) specifying an action to be performed is associated with each of said plurality of event records, so that upon recognition of one of said pre-defined events said associated action can be performed.

10. The method as claimed in claim 9, wherein said steps of acquiring a plurality of operational data samples are performed in real time.

11. The method as claimed in claim 1, wherein only those event records from said plurality of event records which can logically occur during said period of operation in which said plurality of operational data samples are acquired are used in steps (c) and (d).

12. A method for monitoring a system'"'"'s performance, comprising the steps of:

(a) modeling the system'"'"'s performance with a database having a plurality of event records, each of said plurality of event records pre-defining an event that can occur during operation of the system by those events on whose occurrence the occurrence of said pre-defined event is dependent and by one or more critical parameters defining operational data which must occur during the system'"'"'s performance for said pre-defined event to occur, each of said plurality of event records further having a plurality of data defining actions to be performed;

(b) acquiring a plurality of operational data samples from the system during a period of operation with a data acquisition system;

(c) for a first of said plurality of event records, comparing said events on whose occurrence the occurrence of said pre-defined event is dependent to a list of prior recognized events, if said first of said plurality of event records is so pre-defined;

(d) for said first of said plurality of event records, comparing a first of said plurality of said acquired operational data samples to said one or more critical parameters in said first of said plurality of event records if a match is found in step (c) or if step (c) need not be performed;

(e) recognizing said event pre-defined by said first of said event records as having occurred during operation of the system if a match is found between said first of said plurality of acquired operational data samples and said one or more critical parameters from said first of said plurality of event records and adding said recognized event to said list of recognized events;

(f) repeating steps (d) and (e) for each successive acquired operational data sample in said plurality of acquired operational data samples unless said first of said plurality of event records is recognized in step (e);

(g) repeating steps (c), (d), (e) and (f) for each successive event record in said plurality of event records; and

(h) for each of said events recognized in step (e), performing the associated action.

13. The method as claimed in claim 12, wherein said actions modify said data acquisition system to enable the acquisition of a second plurality of operational data samples.

14. The method as claimed in claim 13, wherein said data acquisition system'"'"'s channel configuration is modified.

15. The method as claimed in claim 13, wherein said data acquisition system'"'"'s sampling rate is modified.

16. The method as claimed in claim 13, wherein said data acquisition system'"'"'s sampling window specifying said period of operation is modified.

17. The method as claimed in claim 12, wherein said actions provide a warning to an operator of the system where the system is operating abnormally.

18. The method as claimed in claim 12, wherein steps (b) through (h) are performed in real time.

19. The method as claimed in claim 12, wherein only those event records from said plurality of event records which can logically occur during said period of operation in which said plurality of operational data samples are acquired are used in steps (c) and (d).

20. The method as claimed in claim 12, further comprising the steps of:

(i) storing said acquired data once one of said pre-defined events is recognized; and

(j) analyzing said recognized events and said stored data to determine the system'"'"'s performance.

21. The method as claimed in claim 20, further comprising the step of:

(k) modifying said storing step (i) in accordance with an action from said step (h).

22. The method as claimed in claim 20, wherein said acquired data is stored using data compression and reduction techniques which allow for data reconstruction.

23. The method as claimed in claim 20, further comprising the step of:

(i) modifying a performance parameter in the system as a result of said analyzing step (h) to obtain a desired performance level of the system.

24. The method as claimed in claim 20, further comprising the step of:

(i) modifying said data acquisition system to enable acquisition of a second plurality of operational data samples in accordance with the results of said analyzing step (h);

25. The method as claimed in claim 20, wherein said model of the system is modified in accordance with the results of said analyzing step (h).

26. The method as claimed in claim 20, further comprising the step of:

(i) providing a warning to an operator of the system where said analyzing step (h) indicates an abnormal performance status for the system.

27. Apparatus for monitoring a system'"'"'s performance, comprising:

data acquisition means for collecting a plurality of operational data samples from the system during a period of operation;

an event record database for providing a plurality of event records, each of said plurality of event records pre-defining an event that can occur during operation of the system by those events on whose occurrence the occurrence of said pre-defined event is dependent and by one or more critical parameters defining operational data which must occur during the system'"'"'s performance for said pre-defined event to occur, each of said plurality of event records further having a plurality of data defining actions to be performed;

event recognition means for accessing successive event records in said plurality of event records and for each of said plurality of event records, comparing said event on whose occurrence the occurrence of said event pre-defined by said event record is dependent and if a match is found, then comparing said one or more critical parameters to each successive operational data sample and if a match is found, recognizing said event pre-defined by said event record as having occurred;

means for accessing said event records which pre-define each of said recognized events and performing the specified action.

28. The apparatus as claimed in claim 27, further comprising:

modifying means for changing a performance parameter in accordance with said action.

29. The apparatus as claimed in claim 27, further comprising:

modifying means for adjusting one or more parameters in said data acquisition means in accordance with said action to enable acquisition of a second plurality of operational data samples.

30. The apparatus as claimed in claim 29, wherein said data acquisition system'"'"'s channel configuration is modified.

31. The apparatus as claimed in claim 29, wherein said data acquisition system'"'"'s sampling rate is modified.

32. The apparatus as claimed in claim 29, wherein said data acquisition system'"'"'s sampling window specifying said period of operation is modified.

33. The apparatus as claimed in claim 27, further comprising:

memory means for storing said acquired data once one of said pre-defined events is recognized; and

analysis means for analyzing said recognized pre-defined events to determine the system'"'"'s performance.

34. The apparatus as claimed in claim 27, further comprising:

indicator means for warning an operator of the system of abnormal performance in accordance with said action.

35. Apparatus for monitoring a system'"'"'s performance, comprising:

data acquisition means for collecting a plurality of operational data samples from the system during a period of operation;

an event record database for providing a plurality of event records, each of said plurality of event records pre-defining an event that can occur during operation of the system by those events on whose occurrence the occurrence of said pre-defined event is dependent and by one or more critical parameters defining operational data which must occur during the system'"'"'s performance for said pre-defined event to occur;

event recognition means for accessing successive event records in said plurality of event records and for each of said plurality of event records, comparing said event on whose occurrence the occurrence of said event pre-defined by said event record is dependent and if a match is found, then comparing said one or more critical parameters to each successive operational data sample and if a match is found, recognizing said event pre-defined by said event record as having occurred;

analysis means for analyzing said recognized pre-defined events to determine the system'"'"'s performance.

36. The apparatus as claimed in claim 35, further comprising:

modifying means for changing a performance parameter in accordance with said an output from said analysis means.

37. The apparatus as claimed in claim 35, further comprising:

modifying means for adjusting one or more parameters in said data acquisition means in accordance with an output from said analysis means to enable acquisition of a second plurality of operational data samples.

38. The apparatus as claimed in claim 37, wherein said data acquisition system'"'"'s channel configuration is modified.

39. The apparatus as claimed in claim 37, wherein said data acquisition system'"'"'s sampling rate is modified.

40. The apparatus as claimed in claim 37, wherein said data acquisition system'"'"'s sampling window specifying said period of operation is modified.

41. The apparatus as claimed in claim 35, further comprising:

indicator means for warning an operator of the system of abnormal performance in accordance with said analysis means.