VIRTUAL SENSOR SYSTEM AND METHOD

• US 20120323343A1
• Filed: 06/15/2011
• Published: 12/20/2012
• Est. Priority Date: 06/15/2011
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Mason, James Robert, GRICHNIK, Anthony James, Felty, Timothy Joe
• Granted Patent: US 8,793,004 B2
• Time in Patent Office: Days
• US Class Current: 700/30
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 13/042 in which a parameter or coefficient is automatically adjusted to optimise the performance
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G05B 2219/37537 Virtual sensor
• CPC Class Codes: G05B 23/0235 based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold

Abstract

A control system is disclosed. The control system may have a physical sensor configured to measure physical parameter values of a machine. The control system may also have a virtual sensor network system configured to receive the physical parameter values measured by the physical sensor as input parameter values, and generate output parameter values based on the input parameter values. Further, the control system may have an electronic control module configured to store an output parameter value default rate of change and an output parameter value threshold rate of change, compare a rate of change of the output parameter values generated by the virtual sensor network system to the output parameter value threshold rate of change, and control the machine based on the output parameter value default rate of change if the rate of change of the output parameter values exceeds the output parameter value threshold rate of change.

Claims

1. A virtual sensor network system comprising:

a memory configured to;

store a virtual sensor model, an output parameter value default rate of change, and an output parameter value threshold rate of change; and

a processor configured to;

receive, as input parameter values, physical parameter values of a machine measured from a physical sensor;

generate output parameter values based on the input parameter values and the virtual sensor model;

make a comparison between a rate of change of the output parameter values to the output parameter value threshold rate of change; and

generate a default output parameter value based on the comparison.

2. The virtual sensor network system of claim 1, wherein:

the processor is further configured to;

generate the default output parameter value based on the output parameter value default rate of change if the rate of change of the output parameter values exceeds the output parameter value threshold rate of change; and

send the default output parameter value to an electronic control module for the machine if the rate of change of the output parameter values exceeds the output parameter value threshold rate of change.

3. The virtual sensor network system of claim 1, wherein:

the memory is further configured to;

store an input parameter value default rate of change and an input parameter value threshold rate of change; and

the processor is further configured to;

compare a rate of change of the input parameter values to the input parameter value threshold rate of change; and

replace at least one of the input parameter values with a parameter value calculated based on the input parameter value default rate of change before generating the output parameter values if the rate of change of the input parameter values exceeds the input parameter value threshold rate of change.

4. The virtual sensor network system of claim 2, wherein the processor is further configured to calculate the rate of change of the output parameter values as a difference between a subsequent output parameter value and a preceding output parameter value divided by the time between measurements of the subsequent output parameter value and the preceding output parameter value.

5. The virtual sensor network system of claim 2, wherein the output parameter value threshold rate of change stored in the memory is determined based on a statistical analysis of data records including test data of the machine.

6. The virtual sensor network system of claim 2, wherein:

the virtual sensor model stored in the memory models an output from a modeled physical sensor, and

the output parameter value threshold rate of change stored in the memory is determined based on technical specifications of the modeled physical sensor.

7. A computer-implemented virtual sensor control method comprising:

receiving, as input parameter values, physical parameter values of a machine measured from a physical sensor;

generating output parameter values based on the input parameter values and a virtual sensor model; and

controlling the machine based on a comparison of a rate of change of the output parameter values to an output parameter value threshold rate of change.

8. The computer-implemented virtual sensor control method of claim 7, further including:

comparing a rate of change of the input parameter values to an input parameter value threshold rate of change; and

replacing at least one of the input parameter values with a parameter value calculated based on an input parameter value default rate of change before generating the output parameter values if the rate of change of the input parameter values exceeds the input parameter value threshold rate of change.

9. The computer-implemented virtual sensor control method of claim 7, further including:

determining whether the input parameter values are valid by comparing the input parameter values to a valid input space of the virtual sensor model; and

controlling the machine based on at least one of the output parameter values if one or more of the input parameter values are invalid.

10. The computer-implemented virtual sensor control method of claim 7, further including:

generating an output parameter value default rate of change if the rate of change of the output parameter values exceeds the output parameter value threshold rate of change; and

controlling the machine based on the output parameter value default rate of change.

11. The computer-implemented virtual sensor control method of claim 10, further including calculating the rate of change of the output parameter values as a difference between a subsequent output parameter value and a preceding output parameter value divided by the time between measurements of the subsequent output parameter value and the preceding output parameter value.

12. The computer-implemented virtual sensor control method of claim 10, further including calculating the rate of change of the output parameter values as a weighted moving average of two or more of the output parameter values.

13. The computer-implemented virtual sensor control method of claim 10, further including calculating the rate of change of the output parameter values as a second derivative with respect to time of the output parameter values.

14. The computer-implemented virtual sensor control method of claim 10, further including calculating the output parameter value default rate of change and the output parameter value threshold rate of change based on one or more data records that include test data of the machine.

15. A control system comprising:

a physical sensor configured to measure physical parameter values of a machine at a plurality of times;

a virtual sensor network system configured to;

receive the physical parameter values measured by the physical sensor as input parameter values; and

generate output parameter values based on the input parameter values; and

an electronic control module configured to;

store an output parameter value default rate of change and an output parameter value threshold rate of change;

compare a rate of change of the output parameter values generated by the virtual sensor network system to the output parameter value threshold rate of change; and

control the machine based on the output parameter value default rate of change if the rate of change of the output parameter values exceeds the output parameter value threshold rate of change.

16. The control system of claim 15, wherein:

the electronic control module is further configured to;

store an input parameter value default rate of change and an input parameter value threshold rate of change;

compare a rate of change of the input parameter values to the input parameter value threshold rate of change; and

replace at least one of the input parameter values with a replacement input parameter value calculated based on the input parameter value default rate of change if the rate of change of the input parameter values exceeds the input parameter value threshold rate of change; and

the virtual sensor network system is further configured to;

receive the replacement input parameter value from the electronic control module; and

generate the output parameter values based on the replacement input parameter values.

17. The control system of claim 15, wherein the electronic control module is further configured to calculate the rate of change of the output parameter values as a difference between a subsequent output parameter value and a preceding output parameter value divided by the time between measurements of the subsequent output parameter value and the preceding output parameter value.

18. The control system of claim 15, wherein

the electronic control module is further configured to calculate the rate of change of the output parameter values as a weighted moving average of two or more of the output parameter values.

19. The control system of claim 15, wherein the output parameter value default rate of change and the output parameter value threshold rate of change stored in the electronic control module are calculated based on test data of the machine.

20. The control system of claim 15, wherein

the virtual sensor network system models an output from a modeled physical sensor, and

the output parameter value default rate of change and the output parameter value threshold rate of change stored in the electronic control module are calculated based on a maximum rate of change of the modeled physical sensor.