Probabilistic modeling system for product design

• US 7,831,416 B2
• Filed: 07/17/2007
• Issued: 11/09/2010
• Est. Priority Date: 07/17/2007
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Jayachandran, Amit, Grichnik, Anthony J., Seskin, Michael
• Primary Examiner(s): Shah; Kamini S
• Assistant Examiner(s): Cothran; Bernard E
• Application Number:
  US11/826,614
• Publication Number:
  US 20090024367A1
• Time in Patent Office: 1,211 Days
• Field of Search: 706/15, 706/31, 706/34, 703/1
• US Class Current: 703/1
• CPC Class Codes: G06F 2111/08 Probabilistic or stochastic CAD
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30

Abstract

A method is provided for designing a product. The method may include obtaining data records relating to one or more input variables and one or more output parameters associated with the product; and pre-processing the data records based on characteristics of the input variables. The method may also include selecting one or more input parameters from the one or more input variables; and 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. Further, the method may include providing a set of constraints to the computational model representative of a compliance state for the product; and using the computational model and the provided set of constraints to generate statistical distributions for the one or more input parameters and the one or more output parameters, wherein the one or more input parameters and the one or more output parameters represent a design for the product.

Claims

1. A computer-implemented method for designing a product, comprising:

performing, by a processor associated with the computer, the steps of;

obtaining data records relating to a plurality of input parameters and a plurality of output parameters of components of a system associated with the product, the data records including time-series values of the input parameters and the output parameters;

pre-processing the data records, including;

identifying a target output parameter associated with a first component of the system;

determining respective lag times required for a current value of the target output parameter to correlate to corresponding values of the output parameters of second components of the system different from the first component;

identifying, using the obtained data records, values of the output parameters of the second components corresponding to the lag times;

identifying, among the obtained data records, a data record containing the current value of the target output parameter; and

replacing the values of the output parameters of the second components contained in the identified data record with the identified values corresponding to the lag times;

selecting one or more of the input parameters;

generating a computational model indicative of interrelationships between the selected input parameters and the output parameters based on the pre-processed data records;

providing a set of constraints to the computational model representative of a compliance state for the product; and

using the computational model and the provided set of constraints to generate statistical distributions for the selected input parameters and the output parameters, wherein the selected input parameters and the output parameters represent a design for the product.

2. The method of claim 1, wherein pre-processing further includes:

separating the data records into a plurality of data groups;

calculating a corresponding plurality of cluster centers of the data groups;

determining a respective plurality of distances between a data record and the plurality of cluster centers; and

processing the data records based on the plurality of distances.

3. The method of claim 2, wherein processing the data records includes:

creating a distance matrix with a plurality of columns respectively representing the plurality of data groups and a plurality of rows respectively representing the data records, each element of the distance matrix being a distance between a data record and a cluster center of a data group; and

replacing the data records with the distance matrix.

4. The method of claim 1, further including:

using the computation model to generate nominal values for the one or more input parameters and the one or more output parameters.

5. The method of claim 4, further including modifying the design for the product by adjusting at least one of the statistical distributions and the nominal values for any of the input parameters and the output parameters.

6. The method of claim 1, wherein using the computational model further includes:

obtaining respective ranges of the input parameters;

creating a plurality of model data records based on the respective ranges of the input parameters;

determining a candidate set of values of input parameters using the plurality of model data records with a maximum zeta statistic using a genetic algorithm; and

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

wherein the zeta statistic ζ

is represented by;

7. The method of claim 6, further including:

comparing the statistical distributions of the input parameters with the respective ranges of input parameters; and

determining whether the statistical distributions of the input parameters match the respective ranges of input parameters.

8. The method of claim 7, further including:

if the statistical distributions of the input parameters do not match the respective ranges of the input parameters, changing the respective ranges of the input parameters to the same as the statistical distributions of the input parameters; and

re-determining the statistical distributions of the input parameters based on the changed respective ranges until the statistical distributions of the input parameters match the respective range of the input parameters.

9. A non-transitory computer-readable storage medium storing a set of instructions for enabling a processor to:

obtain data records relating to a plurality of input parameters and a plurality of output parameters of components of a system associated with the product, the data records including time-series values of the input parameters and the output parameters;

pre-process the data records, including;

identifying a target output parameter associated with a first component of the system;

determining respective lag times required for a current value of the target output parameter to correlate to values of the output parameters of second components of the system different from the first component;

identifying, using the obtained data records, values of the output parameters of the second components corresponding to the lag times;

identifying, among the obtained data records, a data record containing the current value of the target output parameter; and

replacing the values of the output parameters of the second components contained in the identified data record with the identified values corresponding to the lag times;

select one or more of the input parameters;

generate a computational model indicative of interrelationships between the selected input parameters and the output parameters based on the pre-processed data records;

provide a set of constraints to the computational model representative of a compliance state for the product; and

use the computational model and the provided set of constraints to generate statistical distributions for the selected input parameters and the output parameters, wherein the selected input parameters and the output parameters represent a design for the product.

10. The computer-readable storage medium of claim 9, wherein the instructions for enabling the processor to pre-process the data records further enable the processor to:

separate the data records into a plurality of data groups;

calculate a corresponding plurality of cluster centers of the data groups;

determine a respective plurality of distances between a data record and the plurality of cluster centers; and

process the data records based on the plurality of distances.

11. The computer-readable storage medium of claim 10, wherein the instructions further enable the processor to:

create a distance matrix with a plurality of columns respectively representing the plurality of data groups and a plurality of rows respectively representing the data records, each element of the distance matrix being a distance between a data record and a cluster center of a data group; and

replace the data records with the distance matrix.

12. A computer-based product design system for designing a product, comprising:

a database containing data records relating to a plurality of input parameters and a plurality of output parameters of components of a system associated with the product, the data records including time-series values of the input parameters and the output parameters; and

a processor configured to;

obtain the data records;

pre-process the data records, including;

identifying a target output parameter associated with a first component of the system;

determining respective lag times required for a current value of the target output parameter to correlate to values of the output parameters of second components of the system different from the first component;

identifying, using the obtained data records, values of the output parameters of the second components corresponding to the lag times;

identifying, among the obtained data records, a data record containing the current value of the target output parameter; and

replacing the values of the output parameters of the second components contained in the identified data record with the identified values corresponding to the lag times;

select one or more of the input parameters;

generate a computational model indicative of interrelationships between the selected input parameters and the output parameters based on the pre-processed data records;

provide a set of constraints to the computational model representative of a compliance state for the product; and

use the computational model and the provided set of constraints to generate statistical distributions for the selected input parameters and the output parameters, wherein the selected input parameters and the output parameters represent a design for the product.

13. The computer-based product design system of claim 12, wherein to pre-process the data records, the processor is further configured to:

separate the data records into a plurality of data groups;

calculate a corresponding plurality of cluster centers of the data groups;

determine a respective plurality of distances between a data record and the plurality of cluster centers; and

process the data records based on the plurality of distances.

14. The computer-based product design system of claim 13, wherein the processor is further configured to:

create a distance matrix with a plurality of columns respectively representing the plurality of data groups and a plurality of rows respectively representing the data records, each element of the distance matrix being a distance between a data record and a cluster center of a data group; and

replace the data records with the distance matrix.