Process model based virtual sensor and method

• US 7,499,842 B2
• Filed: 11/18/2005
• Issued: 03/03/2009
• Est. Priority Date: 11/18/2005
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Grichnik, Anthony J., Seskin, Michael
• Primary Examiner(s): FREJD, RUSSELL WARREN
• Application Number:
  US11/281,978
• Publication Number:
  US 20070118338A1
• Time in Patent Office: 1,201 Days
• Field of Search: 703/2, 706/44
• US Class Current: 703/2
• CPC Class Codes: F02D 41/1401 characterised by the control or regulation method F02D41/1473, F02D41/1477 take precedence
• CPC Class Codes: G05B 17/02 electric

Abstract

A method is provided for a virtual sensor system. The method may include establishing a virtual sensor process model indicative of interrelationships between a plurality of sensing parameters and a plurality of measured parameters, and obtaining a set of values corresponding to the plurality of measured parameters. The method may also include calculating the values of the plurality of sensing parameters simultaneously based upon the set of values corresponding to the plurality of measured parameters and the virtual sensor process model, and providing the values of the plurality of sensing parameters to a control system.

Claims

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

establishing a virtual sensor process model indicative of interrelationships between a plurality of sensing parameters and a plurality of measured parameters;

obtaining a set of values corresponding to the plurality of measured parameters;

calculating the values of the plurality of sensing parameters simultaneously based upon the set of values corresponding to the plurality of measured parameters and the virtual sensor process mode; and

providing the values of the plurality of sensing parameters to a control system,

wherein the establishing includes;

obtaining data records associated with one or more input variables and the plurality of sensing parameters;

selecting the plurality of measured parameters from the one or more input variables;

generating a computational model indicative of the interrelationships between the plurality of measured parameters and the plurality of sensing parameters;

determining desired statistical distributions of the plurality of measured parameters of the computational model; and

recalibrating the plurality of measured parameters based on the desired statistical distributions to define a desired input space.

2. The method according to claim 1, wherein selecting further includes:

pre-processing the data records; and

using a genetic algorithm to select the plurality of measured parameters from the one or more input variables based on a mahalanobis distance between a normal data set and an abnormal data set of the data records.

3. The method according to claim 1, wherein generating further includes:

creating a neural network computational model;

training the neural network computational model using the data records; and

validating the neural network computation model using the data records.

4. The method according to claim 1, wherein determining further includes:

determining a candidate set of the measured parameters with a maximum zeta statistic using a genetic algorithm; and

determining the desired distributions of the measured parameters based on the candidate set,

wherein the zeta statistic ζ

is represented by;

$\mathrm{\zeta <br><br>}=\underset{1}{\overset{j}{\sum <br><br>}}<br><br>\underset{1}{\overset{i}{\sum <br><br>}}<br><br><br><br>S_{\mathrm{ij}}<br><br><br><br>\left(\frac{{\mathrm{\sigma <br><br>}}_i}{{\stackrel{\_}{x}}_i}\right)<br><br>\left(\frac{{\stackrel{\_}{x}}_j}{{\mathrm{\sigma <br><br>}}_j}\right),$

provided that x_i represents a mean of an ith input;

x_j represents a mean of a jth output;

σ

_i represents a standard deviation of the ith input;

σ

_j represents a standard deviation of the jth output; and

|S_ij| represents sensitivity of the jth output to the ith input of the computational model.

5. The method according to claim 1, wherein the providing includes:

separately obtaining values of the plurality of sensing parameters from a physical sensor;

determining that the physical sensor has failed; and

providing the values of the plurality of sensing parameters from the virtual sensor process model to the control system.

6. The method according to claim 1, wherein the plurality of sensing parameters include a NO_x emission level.

7. The method according to claim 1, wherein the plurality of measured parameters include intake manifold temperature, intake manifold pressure, ambient humidity, fuel rates, and engine speeds.

8. A computer system for establishing a virtual sensor process model, comprising:

a database configured to store information relevant to the virtual sensor process model; and

a processor configured to;

obtain data records associated with one or more input variables and the plurality of sensing parameters;

select the plurality of measured parameters from the one or more input variables;

generate a computational model indicative of interrelationships between the plurality of measured parameters and the plurality of sensing parameters;

determine desired statistical distributions of the plurality of measured parameters of the computational model; and

recalibrate the plurality of measured parameters based on the desired statistical distributions to define a desired input space.

9. The computer system according to claim 8, wherein, to select the plurality of measured parameters, the processor is further configured to:

pre-process the data records; and

use a genetic algorithm to select the plurality of measured parameters from the one or more input variables based on a mahalanobis distance between a normal data set and an abnormal data set of the data records.

10. The computer system according to claim 8, wherein, to generate the computational model, the processor is further configured to:

create a neural network computational model;

train the neural network computational model using the data records; and

validate the neural network computation model using the data records.

11. The computer system according to claim 8, wherein, to determine the respective desired statistical distributions, the processor is further configured to:

determine a candidate set of the measured parameters with a maximum zeta statistic using a genetic algorithm; and

determine the desired distributions of the measured parameters based on the candidate set,

wherein the zeta statistic ζ

is represented by;

$\mathrm{\zeta <br><br>}=\underset{1}{\overset{j}{\sum <br><br>}}<br><br>\underset{1}{\overset{i}{\sum <br><br>}}<br><br><br><br>S_{\mathrm{ij}}<br><br><br><br>\left(\frac{{\mathrm{\sigma <br><br>}}_i}{{\stackrel{\_}{x}}_i}\right)<br><br>\left(\frac{{\stackrel{\_}{x}}_j}{{\mathrm{\sigma <br><br>}}_j}\right),$

provided that x_i represents a mean of an ith input;

x_j represents a mean of a jth output;

σ

_i represents a standard deviation of the ith input;

σ

_j represents a standard deviation of the jth output; and

is |S_ij| represents sensitivity of the jth output to the ith input of the computational model.

12. A machine, comprising:

a power source configured to provide power to the machine;

a control system configured to control the power source; and

a virtual sensor system including a virtual sensor process model indicative of interrelationships between a plurality of sensing parameters and a plurality of measured parameters, the virtual sensor system being configured to;

obtain a set of values corresponding to the plurality of measured parameters;

calculate the values of the plurality of sensing parameters simultaneously based upon the set of values corresponding to the plurality of measured parameters and the virtual sensor process model; and

provide the values of the plurality of sensing parameters to the control system, wherein the virtual sensor process model is established by;

obtaining data records associated with one or more input variables and the plurality of sensing parameters;

selecting the plurality of measured parameters from the one or more input variables;

generating a computational model indicative of the interrelationships between the plurality of measured parameters and the plurality of sensing parameters;

determining desired statistical distributions of the plurality of measured parameters of the computational model; and

recalibrating the plurality of measured parameters based on the desired statistical distributions to define a desired input space,

wherein the control system controls the power source based upon the values of the plurality of sensing parameters.

13. The machine according to claim 12, wherein selecting further includes:

pre-processing the data records; and

using a genetic algorithm to select the plurality of measured parameters from the one or more input variables based on a mahalanobis distance between a normal data set and an abnormal data set of the data records.

14. The machine according to claim 12, wherein generating further includes:

creating a neural network computational model;

training the neural network computational model using the data records; and

validating the neural network computation model using the data records.

15. The machine according to claim 12, wherein determining further includes:

determining a candidate set of the measured parameters with a maximum zeta statistic using a genetic algorithm; and

determining the desired distributions of the measured parameters based on the candidate set,

wherein the zeta statistic ζ

is represented by;

$\mathrm{\zeta <br><br>}=\underset{1}{\overset{j}{\sum <br><br>}}<br><br>\underset{1}{\overset{i}{\sum <br><br>}}<br><br><br><br>S_{\mathrm{ij}}<br><br><br><br>\left(\frac{{\mathrm{\sigma <br><br>}}_i}{{\stackrel{\_}{x}}_i}\right)<br><br>\left(\frac{{\stackrel{\_}{x}}_j}{{\mathrm{\sigma <br><br>}}_j}\right),$

provided that x_i represents a mean of an ith input;

x_j represents a mean of a jth output;

σ

_i represents a standard deviation of the ith input;

σ

_j represents a standard deviation of the jth output; and

|S_ij| represents sensitivity of the jth output to the ith input of the computational model.

16. The machine according to claim 12, wherein the plurality of sensing parameters include a NO_x emission level.

17. The machine according to claim 12, wherein the power source includes an engine.

18. The machine according to claim 12, wherein the plurality of measured parameters include intake manifold temperature, intake manifold pressure, ambient humidity, fuel rates, and engine speeds.

19. The machine according to claim 12, further including:

a data link between the control system and the virtual sensor system, wherein the virtual sensor system provides the values of the plurality of sensing parameters to the control system via the data link.

20. The machine according to claim 19, further including:

one or more physical sensors configured to independently provide corresponding values of the plurality of sensing parameters to the control system via the data link.

21. The machine according to claim 20, wherein the control system is further configured to:

determine that the one or more physical sensors have failed; and

control the power source based upon the values of the plurality of sensing parameters from the virtual sensor system.

22. The machine according to claim 12, wherein the control system includes the virtual sensor system.

23. A computer-readable storage medium for use on a computer system configured to establish a virtual sensor process model, the computer-readable storage medium having computer-executable instructions, which when executed, cause the computer to perform a method comprising:

obtaining data records associated with one or more input variables and the plurality of sensing parameters;

selecting the plurality of measured parameters from the one or more input variables;

generating a computational model indicative of interrelationships between the plurality of measured parameters and the plurality of sensing parameters;

determining desired statistical distributions of the plurality of measured parameters of the computational model;

recalibrating the plurality of measured parameters based on the desired statistical distributions to define a desired input space; and

providing the virtual sensor process model with the desired input space for providing control functions in a control system.

24. The computer-readable storage medium according to claim 23, wherein the selecting includes:

pre-processing the data records; and

using a genetic algorithm to select the plurality of measured parameters from the one or more input variables based on a mahalanobis distance between a normal data set and an abnormal data set of the data records.

25. The computer-readable storage medium according to claim 23, wherein the generating includes:

creating a neural network computational model;

training the neural network computational model using the data records; and

validating the neural network computation model using the data records.

26. The computer-readable storage medium according to claim 23, wherein the determining includes:

determining a candidate set of the measured parameters with a maximum zeta statistic using a genetic algorithm; and

determining the desired distributions of the measured parameters based on the candidate set,

wherein the zeta statistic ζ

is represented by;

$\mathrm{\zeta <br><br>}=\underset{1}{\overset{j}{\sum <br><br>}}<br><br>\underset{1}{\overset{i}{\sum <br><br>}}<br><br><br><br>S_{\mathrm{ij}}<br><br><br><br>\left(\frac{{\mathrm{\sigma <br><br>}}_i}{{\stackrel{\_}{x}}_i}\right)<br><br>\left(\frac{{\stackrel{\_}{x}}_j}{{\mathrm{\sigma <br><br>}}_j}\right),$

provided that x_i represents a mean of an ith input;

x_j represents a mean of a jth output;

σ

_i represents a standard deviation of the ith input;

σ

_j represents a standard deviation of the jth output; and

|S_ij| represents sensitivity of the jth output to the ith input of the computational model.