Calibration certificate for virtual sensor network (VSN)

• US 8,224,468 B2
• Filed: 07/31/2008
• Issued: 07/17/2012
• Est. Priority Date: 11/02/2007
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Grichnik, Anthony J., Mason, James, Felty, Tim
• Primary Examiner(s): Decady, Albert
• Assistant Examiner(s): LEE, DOUGLAS S
• Application Number:
  US12/222,007
• Publication Number:
  US 20090119065A1
• Time in Patent Office: 1,447 Days
• Field of Search: 700 30- 31, 700 40- 45, 700/48, 700/110, 700/266, 701/1, 701/29, 701/102, 701/106, 706/23, 706/25, 702/182, 714/47.2
• US Class Current: 700/48
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 17/02 electric

Abstract

A method is used for providing sensing data to a control system of a machine. The method may include providing a plurality of virtual sensors, each of which may have a model type, at least one input parameter, and at least one output parameter. The method may also include integrating the plurality of virtual sensors into a virtual sensor network; determining interdependencies among the plurality of virtual sensors; and obtaining operational information of the plurality of virtual sensors. Further, the method may include recording measurement data and performance information of the virtual sensor network and the plurality of virtual sensors; and generating one or more calibration certificate of the virtual sensor network based on the operational information, the measurement data, and the performance information.

Claims

1. A computer-implemented method for providing sensing data to a control system of a machine, comprising:

providing a plurality of virtual sensors each having a model type, at least one input parameter, and at least one output parameter;

integrating the plurality of virtual sensors into a virtual sensor network;

determining interdependencies among the plurality of virtual sensors;

obtaining operational information of the plurality of virtual sensors;

recording measurement data and performance information of the virtual sensor network and the plurality of virtual sensors;

generating, by at least one processor, a calibration certificate for the virtual sensor network based on the operational information, the measurement data, and the performance information, the calibration certificate comprising a document certifying that the virtual sensor network has been calibrated.

2. The method according to claim 1, wherein the calibration certificate includes normal ranges of operational parameters of the virtual sensor network and a plurality of standard uncertainties corresponding to the operational parameters.

3. The method according to 2, wherein the plurality of standard uncertainties from the calibration certificate further include:

sources of the plurality of uncertainties;

standard uncertainties based upon a Type A evaluation and a Type B evaluation, and;

standard uncertainties caused from random effects and systematic effects.

4. The method according to claim 2, wherein integrating includes:

obtaining data records corresponding to the plurality of virtual sensors;

obtaining model and configuration information of the plurality of virtual sensors;

determining applicable model types of the plurality of virtual sensors and corresponding footprints and accuracy;

selecting a combination of model types for the plurality of virtual sensors; and

calculating an overall footprint and accuracy of the virtual sensor network based on the combination of model types of the plurality of virtual sensors.

5. The method according to claim 4, further including:

determining whether the overall footprint and accuracy meets a desired threshold;

if it is determined that the overall footprint and accuracy is not desired, selecting a different combination of model types for the plurality of virtual sensors; and

repeating the step of calculating the overall footprint and accuracy and the step of selecting the different combination until a desired combination of model types is determined.

6. The method according to claim 2, wherein determining the interdependencies further includes:

determining a feedback relationship between the output parameter of one virtual sensor from the plurality of virtual sensors and the input parameter of one or more of other virtual sensors from the plurality of virtual sensor; and

storing the feedback relationship in a table.

7. The method according to claim 2, wherein

the data records include two sets of data including a first set of training data, and a second set of testing data;

and

the recording further includes;

determining a first condition under which the virtual sensor network is unfit to provide one or more virtual sensor output parameter to the control system based on the determined interdependencies and the operational information; and

presenting the determined first condition to the control system.

8. The method according to claim 7, the recording further including:

monitoring the interdependencies of the plurality of virtual sensors; and

determining occurrence of the first condition when two or more virtual sensors are both interdependent and providing the sensing data to the control system.

9. The method according to claim 8, the recording further including:

determining a second condition under which an individual virtual sensor from the virtual sensor network is unfit to provide the output parameter to the control system; and

presenting the determined second condition to the control system.

10. The method according to claim 9, wherein determining the second condition further includes:

obtaining values of the input parameter of a virtual sensors;

calculating a validity metric based on the obtained values;

determining whether the calculated validity metric is within a valid range;

determining the second condition if the calculated validity metric is not within the valid range.

11. A virtual sensor network system, comprising:

a plurality of virtual sensors, each having a model type, at least one input parameter, and at least one output parameter, integrated into a virtual sensor network;

an input interface to obtain data from corresponding physical sensors;

an output interface to provide data to a control system; and

a controller configured to;

determine interdependencies among the plurality of virtual sensors;

obtain operational information of the plurality of virtual sensors;

record measurement data and performance information of the virtual sensor network and the plurality of virtual sensors;

generate a calibration certificate for the virtual sensor network based on the operational information, the measurement data, and the performance information, the calibration certificate comprising a document proving that the virtual sensor network was calibrated according to a standard.

12. The virtual sensor network system according to claim 11, wherein the calibration certificate includes normal ranges of operational parameters of the virtual sensor network and a plurality of standard uncertainties corresponding to the operational parameters.

13. The virtual sensor network system according to claim 12, wherein the plurality of standard uncertainties from the calibration certificate further include:

sources of the plurality of uncertainties;

standard uncertainties based upon a Type A evaluation and a Type B evaluation, and;

standard uncertainties caused from random effects and systematic effects in the generating process.

14. The virtual sensor network system according to claim 12, wherein the plurality of virtual sensors are integrated by:

obtaining data records corresponding to the plurality of virtual sensors;

obtaining model and configuration information of the plurality of virtual sensor;

determining applicable model types of the plurality of virtual sensors and corresponding footprints and accuracy;

selecting a combination of model types for the plurality of virtual sensors; and

calculating an overall footprint and accuracy of the virtual sensor network based on the combination of model types of the plurality of virtual sensors.

15. The virtual sensor network system according to claim 13, further including:

determining whether the overall footprint and accuracy meets a desired threshold;

if it is determined that the overall footprint and accuracy is not desired, selecting a different combination of model types for the plurality of virtual sensors; and

repeating the step of calculating the overall footprint and accuracy and the step of selecting the different combination until a desired combination of model types is determined.

16. The virtual sensor network system according to claim 12, wherein, to determine the interdependencies, the controller is further configured to:

determine a feedback relationship between the output parameter of one virtual sensor from the plurality of virtual sensors and the input parameter of one or more of other virtual sensors from the plurality of virtual sensor; and

store the feedback relationship in a table.

17. The virtual sensor network system according to claim 12, wherein, to record the measurement data and the performance information, the controller is further configured to:

determine a first condition under which the virtual sensor network is unfit to provide one or more virtual sensor output parameter to the control system based on the determined interdependencies and the operational information by monitoring the interdependencies of the plurality of virtual sensors and determining occurrence of the first condition when two or more virtual sensors are both interdependent and providing the sensing data to the control system; and

present the determined first condition to the control system.

18. The virtual sensor network system according to claim 16, the controller is further configured to:

determine a second condition under which an individual virtual sensor from the virtual sensor network is unfit to provide the output parameter to the control system; and

present the second condition to the control system to indicate the determined second condition.

19. The virtual sensor network system according to claim 17, wherein, to determine the second condition, the controller is further configured to:

obtain values of the input parameter of a virtual sensor;

calculate a mahalanobis distance based on the obtained values;

determine whether the calculated mahalanobis distance is within a valid range;

determine the second condition if the calculated mahalanobis distance is not within the valid range.

21. The machine according to claim 19, wherein the calibration certificate includes normal ranges of operational parameters of the virtual sensor network and a plurality of standard uncertainties corresponding to the operational parameters.

20. A machine, comprising:

an engine to provide power for the machine;

an engine electronic control module (ECM) for controlling the engine;

a plurality of physical sensors providing sensing data to the engine ECM; and

a virtual sensor network system for providing predicted sensing data to the engine ECM, wherein the virtual sensor network system includes;

a plurality of virtual sensors, each having a model type, at least one input parameter, and at least one output parameter, integrated into a virtual sensor network;

an input interface to obtain data from the plurality of physical sensors;

an output interface to provide data to the engine ECM; and

a controller configured to;

determine interdependencies among the plurality of virtual sensors;

obtain operational information of the plurality of virtual sensors;

record measurement data and performance information of the virtual sensor network and the plurality of virtual sensors;

generate a calibration certificate for the virtual sensor network based on the operational information, the measurement data, and the performance information, the calibration certificate comprising a document proving that the virtual sensor network has been calibrated according to a standard; and

present the calibration certificate for the virtual sensor network to a user.