Method and apparatus for monitoring performance characteristics of a system and identifying faults

• US 9,116,965 B2
• Filed: 03/18/2013
• Issued: 08/25/2015
• Est. Priority Date: 03/19/2012
• Status: Active Grant

• Current Assignee: GE Aviation Systems Limited (GE Aerospace)
• Original Assignee: GE Aviation Systems Limited (GE Aerospace)
• Inventors: Callan, Robert Edward
• Primary Examiner(s): Duncan, Marc
• Application Number:
  US13/846,482
• Publication Number:
  US 20130246860A1
• Time in Patent Office: 890 Days
• Field of Search: 714/26, 714/37, 714/47.1
• US Class Current: 1/1
• CPC Class Codes: G05B 23/021 adopting a different treatment of each operating region or a different mode of the monitored system, e.g. transient modes; different operating configurations of monitored system
• CPC Class Codes: G05B 23/0229 knowledge based, e.g. expert systems; genetic algorithms
• CPC Class Codes: G06F 11/3055 Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available error or fault processing without redundancy G06F11/0703; error detection or correction by redundancy in data representation G06F11/08; error detection or correction by redundancy in operation G06F11/14; error detection or correction by redundancy in hardware G06F11/16
• CPC Class Codes: G06F 11/3058 Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations thermal management in cooling arrangements of a computing system G06F1/206
• CPC Class Codes: G06F 11/3447 Performance evaluation by modeling

Abstract

A method of monitoring a system is disclosed, in particular to identify the cause of conditions outside expected operating conditions. The output of one or more sensors associated with a system is monitored and data from the one or more sensors is arranged as a plurality of modes with each mode being defined by a different condition in which the system may operate. Faulty conditions are identified by monitored data being outside one of the plurality of modes. The use of a plurality of modes enables operation of the system to be defined and tracked more precisely and false alarms may be reduced. At least one of the modes may be established to indicate a particular failure of the system. This failure mode may have a likely cause of the failure associated with it such that diagnosis and repair may be facilitated quickly and easily.

Claims

1. A method for monitoring a system, the method comprising:

monitoring an output data from one or more sensors associated with the system;

arranging the output data from the one or more sensors as a plurality of modes, each mode defined by a condition in which the system may operate, wherein the output data is modelled by assigning a fading weight to each output data sample; and

identifying faulty conditions by the monitored output data outside one of the plurality of modes.

2. The method according to claim 1, wherein the plurality of modes are each defined by a different ambient condition in which the system may operate.

3. The method according to claim 1, wherein each of the plurality of modes corresponds to a different physical configuration of the system.

4. The method according claim 1, wherein each of the plurality of modes corresponds to different operating conditions of the system.

5. The method according to claim 1, wherein at least one mode is indicative of a particular failure.

6. The method according to claim 1, wherein at least one mode is a failure mode indicative of a particular failure and each failure mode has a likely cause of the failure associated with it.

7. The method according to claim 1, wherein the output data is modelled using variables determined by calculating a difference between the sensed output data and at least one predicted value.

8. The method according to claim 1, wherein the output data is modelled by assigning a truth value to each data sample.

9. The method according to claim 1, wherein the output data is modelled by assigning a case weight to each data sample.

10. The method according to claim 1, wherein each output data sample is used to construct a Gaussian model, with each Gaussian function corresponding to a mode.

11. The method according to claim 1, wherein the output data from the one or more sensors is used to adapt an existing model.

12. The method according to claim 1, wherein a new component is added to the model if a new sample is a greater distance from a corresponding sample of the output data in the model than a predefined threshold.

13. An apparatus for monitoring a system, the apparatus comprising:

at least one controller arranged to monitor an output data of or more sensors associated with a system,

the controller configured to at least (i) arrange the output data from one or more sensors as a plurality of modes, wherein each mode is defined by a different condition in which the system may operate and the output data is modelled by assigning a fading weight to each output data sample, and (ii) identify faulty conditions by the monitored output data outside one of the plurality of modes.

14. An apparatus according to claim 13, wherein at least one of the modes is established to indicate a failure associated with the system.