Virtual sensor network (VSN) system and method

• US 8,036,764 B2
• Filed: 11/02/2007
• Issued: 10/11/2011
• Est. Priority Date: 11/02/2007
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Mason, James, Grichnik, Anthony J., Felty, Tim
• Primary Examiner(s): Decady; Albert
• Assistant Examiner(s): Lee; Douglas S.
• Application Number:
  US11/979,408
• Publication Number:
  US 20090118841A1
• Time in Patent Office: 1,439 Days
• Field of Search: 700/31, 700/48, 700/110, 702/179, 702/185, 702/196, 703/2, 706/15, 706/44
• US Class Current: 700/48
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods

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 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.

Claims

1. A 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;

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

presenting the determined first condition to the control system.

2. The method according to claim 1, 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.

3. The method according to claim 2, further including:

determining whether the overall footprint and accuracy is desired based on certain criteria;

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.

4. The method according to claim 3, wherein the repeating is governed by using one of a genetic algorithm and an input from an operator of the machine.

5. The method according to claim 1, wherein the data records include two sets of data:

a first set of training data, and a second set of testing data.

6. The method according to claim 1, 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 1, wherein determining the first condition further includes:

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.

8. The method according to claim 1, 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.

9. The method according to claim 8, 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.

10. The method according to claim 9, wherein calculating the validity metric includes calculating the Mahalanobis distance of the input parameter to a valid operating range of the virtual sensor network.

11. The method according to claim 9, wherein calculating the validity metric includes:

evaluating each input parameter against an established upper and lower bounds of the input parameter; and

performing a logical AND operation on a collection of evaluated input parameter to obtain the validity metric.

12. 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;

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

present the determined first condition to the control system.

13. 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.

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

determining whether the overall footprint and accuracy is desired based on certain criteria;

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.

15. 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.

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

monitor the interdependencies of the plurality of virtual sensors; and

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

17. The virtual sensor network system according to claim 12, 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.

18. 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.

19. 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;

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

present the determined first condition to the control system.

20. The machine according to claim 19, 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.

21. The machine according to claim 19, wherein, to determine the first condition, the controller is further configured to:

monitor the interdependencies of the plurality of virtual sensors; and

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

22. The machine according to claim 19, 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.

23. The machine according to claim 22, 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.

24. A machine, comprising:

at least two electronic control modules (ECMs) for respectively controlling machine systems to be coordinated;

a communications network between the ECMs;

a plurality of physical sensors providing physical sensing data to the multiple ECMs; and

a virtual sensor network system for providing predicted sensing data to the multiple ECMs, 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 ECMs; and

a controller configured to;

determine interdependencies among the plurality of virtual sensors;

obtain operational information of the plurality of virtual sensors;

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

present the determined condition to the control system.

25. The machine according to claim 24, wherein the controller is further configured to:

obtain input parameters from the multiple ECMs simultaneously over the communications network;

communicate output parameters to the multiple ECMs simultaneously over the communications network; and

communicate status information regarding the condition of the virtual sensor network to the multiple ECMs simultaneously.