Assessing performance of a system

Patent metadata

Field	Value
Publication number	US-9424694-B2
Application number	US-201314413989-A
Country	US
Kind code	B2
Filing date	Jul 10, 2013
Priority date	Jul 16, 2012
Publication date	Aug 23, 2016
Grant date	Aug 23, 2016

Abstract

A method of generating probability data for use in assessing performance of a system and a mission involving the system. The method includes receiving ( 302 ) a combined model describing a system diagnosis model describing symptoms, failures and link strengths (conditionals) of components/subsystems of the system, and a mission impact model, the mission impact model describing effects of the system on an ability to perform the mission. Observation data regarding a state of the system is also received ( 306 ) The observation data is used ( 308 ) in combination with the combined model to generate probability data for use in assessing performance of the system and the mission.

First claim

The invention claimed is:

1. A computer-implemented method of assessing performance of a vehicle system and a mission involving the vehicle system, the method including:
receiving, by a processor, a sensor signal generated by a sensor, the sensor signal representing an operational state of a component of the vehicle system;
receiving, by the processor, a single combined model describing a system diagnosis model that describes symptoms, failures, and link strengths (conditionals) of the component of the vehicle system, and a mission impact model, the mission impact model describing effects of the component of the vehicle system on an ability of the vehicle system to perform the mission;
generating, by the processor, probability data representing a probability of a failure of the component affecting the ability of the vehicle system to perform the mission by applying the sensor signal to the single combined model; and
generating, by the processor, a control signal for controlling the vehicle system based on the probability data.

2. A method according to claim 1 , wherein the sensor signal is one of a plurality of sensor signals, each sensor signal received from at least one sensor, and wherein each sensor signal is applied to the single combined model to generate the probability data.

3. A method according to claim 1 , wherein the single combined model indicates if a particular phase of the mission is affectable by at least one of the failure of the component and a symptom of the component.

4. A method according to claim 1 , wherein the single combined model further comprises a hierarchical model in which a top level represents the mission.

5. A method according to claim 4 , wherein a level below the mission top level of the hierarchical model represents at least one phase of the mission, wherein successful performance of the at least one phase affects whether or not the mission is successfully performed.

6. A method according to claim 5 , wherein a level below the at least one phase level represents at least one capability of the vehicle system, wherein successful provision of a said capability affects whether or not the phase is successfully performed.

7. A method according to claim 6 , wherein a level below the at least one capability level represents the component, wherein successful functioning of the component affects whether or not a said capability is successfully provided.

8. A method according to claim 7 , wherein generating the probability data includes performing inference to compute at least one of: posterior probability of the mission failing, posterior probability of a said phase of the mission failing; posterior probability of said capability failing, and posterior probability of a said component failing.

9. A method according to claim 1 , further including:
receiving diagnosis model data describing the symptoms, the failures, and the link strengths (conditionals) of the component;
receiving mission impact model data describing effects of the system on the ability to perform the mission; and
processing the receiving diagnosis model data and the mission impact model data to produce the single combined model.

10. A method according to claim 9 , wherein the single combined model is produced by compiling the system diagnosis model data and the mission impact model data into an Arithmetic Circuit.

11. A method according to claim 10 , further including:
computing a first prior probability of each said failure at commencement of the mission;
computing a second priori probability of the failure from the commencement of the mission to a said phase that the combined model indicates is affectable by the failure; and
storing the computed second prior probability in the single combined model.

12. A method according to claim 11 , wherein the prior probability of each failure at a beginning of the mission is calculated using a Mean Time Between Failure and a component cumulative operation time before commencement of the mission.

13. A non-transitory computer program product having instructions encoded thereon that when executed by one or more processors cause a process to be carried out, the process for assessing performance of a vehicle system and a mission involving the vehicle system, the process comprising:
receiving a single combined model describing a system diagnosis model that describes symptoms, failures, and link strengths (conditionals) of a component of the vehicle system, and a mission impact model, the mission impact model describing effects of the component of the vehicle system on an ability of the vehicle system to perform the mission;
receiving a sensor signal representing an operational state of the component of the vehicle system; and
generating probability data representing a probability of a failure of the component affecting the ability of the vehicle system to perform the mission by applying the sensor signal to the single combined model; and
generating a control signal for controlling the vehicle system based on the probability data.

14. Apparatus for assessing performance of a vehicle system and a mission involving the vehicle system, the apparatus including:
one or more memory devices comprising instructions; and
one or more processors configured to execute the instructions so as to cause a process to be carried out, the process comprising:
receive a single combined model describing a system diagnosis model that describes symptoms, failures, and link strengths (conditionals) of a component of the vehicle system, and a mission impact model, the mission impact model describing effects of the component of the vehicle system on an ability of the vehicle system to perform the mission;
receive a sensor signal representing an operational state of a component of the vehicle system;
generate probability data representing a probability of a failure of the component affecting the ability of the vehicle system to perform the mission by applying the sensor signal to the single combined model; and
generate a control signal for controlling the vehicle system based on the probability data.

15. Apparatus according to claim 14 , wherein the generated probability data is used to assess performance of the vehicle system and the mission, and a result of the assessment leads to an action being performed, the action being selected from a set including: an alarm being triggered; affecting a control of the vehicle; switching to a backup system.

16. Apparatus according to claim 14 , wherein the apparatus comprises at least one of a sensor configured to generate the sensor signal and part of a vehicle.

17. A non-transitory computer program product according to claim 13 , wherein the single combined model indicates if a particular phase of the mission is affectable by at least one of the failure of the component and a symptom of the component.

18. A non-transitory computer program product according to claim 13 , wherein the single combined model further comprises a hierarchical model in which a top level represents the mission, and wherein a level below the mission top level of the hierarchical model represents at least one phase of the mission, wherein successful performance of the at least one phase affects whether or not the mission is successfully performed, and wherein a level below the at least one phase level represents at least one capability of the system, wherein successful provision of a said capability affects whether or not the phase is successfully performed, and wherein a level below the at least one capability level represents

Assignees

• Bae Systems Plc

Inventors

• Senalp Erdem Turker
• Bovey Richard Lee

Classifications

• G06Q10/063 Primary

  Operations research, analysis or management · CPC title

• G05B23/0254

  based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks · CPC title

• G07C5/0808 Primary

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title

• G06Q10/06 Primary

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

• G06Q10/0639

  Performance analysis of employees; Performance analysis of enterprise or organisation operations · CPC title