Control system and method

• US 7,565,333 B2
• Filed: 04/08/2005
• Issued: 07/21/2009
• Est. Priority Date: 04/08/2005
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Perez, Marco, Collins, Roy T., Grichnik, Anthony J., Seskin, Michael
• Primary Examiner(s): Vincent; David R
• Assistant Examiner(s): Kennedy; Adrian L
• Application Number:
  US11/101,532
• Publication Number:
  US 20060229769A1
• Time in Patent Office: 1,565 Days
• Field of Search: 706/12, 706/13, 706/15
• US Class Current: 706/12
• CPC Class Codes: G05B 17/02 electric

Abstract

A method is provided for a control system. The method may include obtaining data records associated one or more input variables and one or more output parameters, and selecting one or more input parameters from the one or more input variables. The method may also include generating a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records, and determining desired respective statistical distributions of the one or more input parameters of the computational model.

Claims

1. A computer implemented method for a control system, comprising:

obtaining data records associated with a plurality of input variables and one or more output parameters;

pre-processing the obtained data records to, at least one of, remove identical data records, remove records that are outside a preliminary desired statistical distribution, and remove erroneous records;

selecting a plurality of input parameters from the plurality of input variables as a subset of the input variables, a total number of the input parameters being less than a total number of the input variables;

generating a computational model indicative of interrelationships between the plurality of input parameters and the one or more output parameters based on the data records;

determining desired respective statistical distributions of the input parameters of the computational model corresponding to desired statistical distributions of the one or more output parameters;

generating an optimized computational model based at least in part on the previously determined desired respective statistical distributions of the input parameters of the computational model corresponding to desired statistical distributions of the one or more output parameters; and

using the generated optimized model'"'"'s output parameters to control the operation of a machine.

2. The method according to claim 1, further including:

generating a second computational model indicative of referential interrelationships between the plurality of input parameters and the one or more output parameters based on the data records.

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

controlling the machine using the values of the one or more output parameters from both the optimized computational model and the second computational model.

4. The method according to claim 3, wherein controlling includes:

determining a difference between the values of the one or more output parameters from the optimized computational model and the values of the one or more output parameters from the second computational model;

determining whether the difference is beyond a predetermined threshold; and

deciding a failure of the optimized computational model if the difference is beyond the threshold.

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

controlling the machine using the values of the output parameters from the second computational model.

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

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

7. The method according to claim 1, wherein generating the computational model 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.

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

providing a normal data set and an abnormal data set from the pre-processed data records; and

using a genetic algorithm to select the plurality of input parameters such that a mahalanobis distance between the normal data set and the abnormal data set, based on the selected plurality of input parameters, is maximized.

8. A computer-implemented method for a control system, comprising:

obtaining data records associated with one or more input variables and one or more output parameters;

selecting one or more input parameters from the one or more input variables;

generating a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records;

determining desired respective statistical distributions of the input parameters of the computational model; and

controlling operation of a machine based on the desired respective statistical distributions of the input parameters of the computational model,

wherein determining further includes;

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

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

wherein the zeta statistic ζ

is represented by;

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

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.

9. A control system, comprising:

one or more input elements configured to accept respective a plurality of input parameters to the control system;

one or more output elements configured to accept respective one or more output parameters; and

a processor configured to control a machine using the one or more output parameters based on a control model, wherein the control model is created by;

obtaining data records associating with the plurality of input parameters and one or more output parameters;

pre-processing the obtained data records to, at least one of, remove identical data records, remove records that are outside a preliminary desired statistical distribution, and remove erroneous records;

generating a computational model indicative of interrelationships between the plurality of input parameters and the one or more output parameters based on the data records;

determining desired respective statistical distributions of the plurality of input parameters of the computational model corresponding to desired statistical distributions of the one or more output parameters;

generating an optimized computational model based at least in part on the previously determined desired respective statistical distributions of the input parameters of the computational model corresponding to desired statistical distributions of the one or more output parameters, wherein output parameters of the generated optimized model are used to control the operation of the machine.

10. The control system according to claim 9, wherein creating the control model further includes:

generating a second computational model indicative of referential interrelationships between the plurality of input parameters and the one or more output parameters based on the data records.

11. The control system according to claim 10, the processor is further configured to:

determine a difference between the values of the one or more output parameters from the optimized computational model and the values of the one or more output parameters from the second computational model;

determine whether the difference is beyond a predetermined threshold;

decide that the optimized computational model has failed if the difference is beyond the threshold; and

control the machine using the values of the one or more output parameters from the second computational model.

12. The control system according to claim 11, wherein the processor is further configured to:

control the machine using the values of the one or more output parameters from the optimized computational model if the difference is not beyond the threshold.

13. The control system according to claim 9, wherein generating the computational model 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.

19. The control system according to claim 9, wherein the control system controls an engine system based on the control model and the one or more output elements.

20. The control system according to claim 19, wherein the engine system provides power for a machine.

14. A control system, comprising:

one or more input elements configured to accept respective one or more input parameters to the control system;

one or more output elements configured to accept respective one or more output parameters; and

a processor configured to control one or more hardware devices using the one or more output parameters based on a control model, wherein the control model is created by;

obtaining data records associating with the one or more input parameters and one or more output parameters;

generating a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records;

determining desired respective statistical distributions of the one or more input parameters of the computational model; and

recalibrating the one or more input parameters based on the desired statistical distributions,

wherein operation of a machine is controlled based on the desired respective statistical distributions of the one or more input parameters of the computational model,

wherein determining further includes;

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

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

wherein the zeta statistic ζ

is represented by;

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

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.

15. A computer system, comprising:

a database containing data records associating a plurality of input variables and one or more output parameters; and

a processor configured to;

pre-process the data records to, at least one of, remove identical data records, remove records that are outside a preliminary desired statistical distribution, and remove erroneous records;

select a plurality of input parameters from the plurality of input variables as a subset of the input variables, a total number of the input parameters being less than a total number of the input variables;

generate a computational model indicative of interrelationships between the plurality of input parameters and the one or more output parameters based on the data records;

determine desired respective statistical distributions of the plurality of input parameters of the computational model corresponding to desired statistical distributions of the one or more output parameters;

generate an optimized computational model based at least in part on the previously determined desired respective statistical distributions of the input parameters of the computational model corresponding to desired statistical distributions of the one or more output parameters; and

use the generated optimized model'"'"'s output parameters to control the operation of a machine.

16. The computer system according to claim 15, wherein, to select one or more the input parameters, the processor is further configured to:

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

17. The computer system according to claim 15, 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.

18. The computer system according to claim 15, wherein, to determine desired respective statistical distributions, the processor is further configured to:

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

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

wherein the zeta statistic ζ

is represented by;

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

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.