Virtual sensor network (VSN) based control system and method

• US 20100050025A1
• Filed: 08/20/2008
• Published: 02/25/2010
• Est. Priority Date: 08/20/2008
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Mason, James, Jayachandran, Amit, Grichnik, Anthony J., Felty, Tim, Kesse, Mary L., Wynkoop, Christopher L.
• Granted Patent: US 7,917,333 B2
• Time in Patent Office: Days
• US Class Current: 714/47
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G05B 2219/37537 Virtual sensor

Abstract

A method for providing a virtual sensor network based system. The method may include obtaining project data descriptive of a virtual sensor network to be used in a control system of a machine; establishing a virtual sensor network including a plurality of virtual sensors based on the project data. Each virtual sensor may have a model type, at least one input parameter, and at least one output parameter. The method may also include recording model information, measurement data, and performance information of the virtual sensor network including the plurality of virtual sensors; creating one or more calibration certificates of the virtual sensor network including a plurality of virtual sensors based on the model information, the measurement data, and the performance information; and generating a documentation package associated with the virtual sensor network. The documentation package may include at least an identification, the project data, and at least one calibration certificate of the virtual sensor network including a plurality of virtual sensors.

Claims

1. A method for providing a virtual sensor network based system, comprising:

obtaining project data descriptive of a virtual sensor network to be used in a control system of a machine;

establishing a virtual sensor network including a plurality of virtual sensors based on the project data, each virtual sensor having a model type, at least one input parameter, and at least one output parameter;

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

creating one or more calibration certificates of the virtual sensor network including a plurality of virtual sensors based on the model information, the measurement data, and the performance information; and

generating a documentation package associated with the virtual sensor network, wherein the documentation package includes at least an identification, the project data, and at least one calibration certificate of the virtual sensor network including a plurality of virtual sensors.

2. The method according to claim 1, wherein the recording includes:

deploying the virtual sensor network and the plurality of virtual sensors on a selected deployment target;

operating the virtual sensor network on the deployment target; and

logging the measurement and performance information during operation of the virtual sensor network.

3. The method according to claim 2, wherein the deployment target is a fixed-point component and the deploying includes:

converting data information of the virtual sensor network into fixed-point representation;

converting function information of the virtual sensor network into fixed-point representation; and

loading the converted virtual sensor network to the deployment target for fixed-point operation.

4. The method according to claim 1, wherein the recording includes:

verifying a passage of performance of the virtual sensor network based on the performance data;

creating the identification for the virtual sensor network; and

embedding the identification in the virtual sensor network such that the identification cannot be changed for the virtual sensor network.

5. The method according to claim 4, wherein the identification is a serial number.

6. The method according to claim 1, wherein the establishing includes:

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

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 sensors;

storing the feedback relationship in a table;

obtaining operational information of the plurality of virtual sensors;

monitoring the interdependencies of the plurality of virtual sensors;

determining an occurrence of a condition under which the output parameter of an individual virtual sensor is associated with the input parameter of an other virtual sensor from the virtual sensor network; and

determining that the other virtual sensor is unfit to operate based on the condition.

7. The method according to claim 6, before determining the occurrence, further comprising:

determining whether a value of the input parameter of the individual virtual sensor is not within a valid input space of the individual virtual sensor; and

determining that the individual virtual sensor is unfit to operate if the value is not within the valid input space.

8. The method according to claim 7, further comprising:

enabling internal data logging if an virtual sensor is determined to be unfit to operate.

9. The method according to claim 1, wherein the document package further includes a time stamp, virtual sensor network model information, and compliance data.

10. 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; and

an uncertainty of the output parameter is contributed to by an uncertainty of the input parameter.

11. The method according to 10, wherein the plurality of standard uncertainties from the calibration certificate further includes:

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.

12. 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;

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

selecting the combination if the overall footprint and accuracy are desired based on certain criteria.

13. A system for providing a virtual sensor network based system, comprising:

a storage unit configured to contain information associated with the virtual sensor network; and

a processor configured to;

obtain project data descriptive of a virtual sensor network to be used in a control system of a machine;

establish a virtual sensor network including a plurality of virtual sensors based on the project data, each virtual sensor having a model type, at least one input parameter, and at least one output parameter;

obtain logged information including model information, measurement data, and performance information of the virtual sensor network including the plurality of virtual sensors;

create one or more calibration certificates of the virtual sensor network including a plurality of virtual sensors based on the model information, the measurement data, and the performance information; and

generate a documentation package associated with the virtual sensor network, wherein the documentation package includes at least an identification, the project data, and at least one calibration certificate of the virtual sensor network including a plurality of virtual sensors.

14. The system according to claim 13, wherein, to obtain the logged information, the processor is further configured to:

deploy the virtual sensor network and the plurality of virtual sensors on a selected deployment target;

enable a log functionality of the virtual sensor network on the deployment target where the virtual sensor network is operating; and

receive the logged information from the virtual sensor network.

15. The system according to claim 14, wherein the deployment target is a fixed-point component and, to deploy, the processor is further configured to:

convert data information of the virtual sensor network into fixed-point representation;

convert function information of the virtual sensor network into fixed-point representation; and

load the converted virtual sensor network to the deployment target for fixed-point operation.

16. The system according to claim 13, wherein, to record, the processor is further configured to:

verify a passage of performance of the virtual sensor network based on the performance data;

create the identification for the virtual sensor network; and

embed the identification in the virtual sensor network such that the identification cannot be changed for the virtual sensor network.

17. The system according to claim 16, wherein the identification is a serial number.

18. The system according to claim 13, wherein, to establish, the processor is further configured to:

integrate the plurality of virtual sensors into the virtual sensor network;

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 sensors;

store the feedback relationship in a table;

obtain operational information of the plurality of virtual sensors;

monitor the interdependencies of the plurality of virtual sensors;

determine an occurrence of a condition under which the output parameter of an individual virtual sensor is associated with the input parameter of an other virtual sensor from the virtual sensor network; and

determine that the other virtual sensor is unfit to operate based on the condition.

19. The system according to claim 13, wherein the document package further includes a time stamp, virtual sensor network model information, and compliance data.

20. The system according to claim 13, 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; and

an uncertainty of the output parameter is contributed to by an uncertainty of the input parameter.

21. The system according to 20, wherein the plurality of standard uncertainties from the calibration certificate further includes:

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.

22. The system according to claim 14, wherein, to integrate, the processor is further configured to:

obtain data records corresponding to the plurality of virtual sensors;

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

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

select a combination of model types for the plurality of virtual sensors;

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

select the combination if the overall footprint and accuracy are desired based on certain criteria.