System and method for utilizing a hybrid model

• US 8,577,481 B2
• Filed: 10/06/2011
• Issued: 11/05/2013
• Est. Priority Date: 09/13/2006
• Status: Active Grant

• Current Assignee: Rockwell Automation Technologies Incorporated (Rockwell Automation, Inc.)
• Original Assignee: Rockwell Automation Technologies Incorporated (Rockwell Automation, Inc.)
• Inventors: Boe, Eugene, Martin, Gregory D., Piche, Stephen W.
• Primary Examiner(s): Padmanabhan, Kavita
• Application Number:
  US13/267,584
• Publication Number:
  US 20120022670A1
• Time in Patent Office: 761 Days
• Field of Search: 700/29, 700/37, 700/39, 700/44, 703/2, 703/16, 703/23
• US Class Current: 700/44
• CPC Class Codes: G05B 13/042 in which a parameter or coefficient is automatically adjusted to optimise the performance
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G05B 17/02 electric

Abstract

A system and method for predicting operation of a plant or process receive an input value from the plant or process. An integrity of a non-linear model corresponding to a local input space of the input value may be determined. The non-linear model may include an empirical representation of the plant or process. If the integrity is above a first threshold, non-linear model may be used to provide a first output value. However, if the integrity is below the first threshold, a linearized first principles model may be used to provide a second output value. The linearized first principles model may include an analytic representation of the plant or process. Additionally, the analytic representation of the plant or process may be independent of the empirical representation of the plant or process. The first output value and/or the second output value may be usable to manage the plant or process.

Claims

1. A non-transitory memory medium comprising program instructions executable by a processor, wherein the program instructions comprise:

a non-linear model comprising an empirical representation of a plant or process, wherein the non-linear model is configured to receive an input value from the plant or process, and to generate a first output value using the empirical representation of the plant or process; and

a linearized first principles model comprising an analytic representation of the plant or process, wherein the linearized first principles model is configured to receive the input value from the plant or process, and to generate a second output value using the analytic representation of the plant or process.

2. The non-transitory memory medium of claim 1, wherein the program instructions comprise a domain analyzer operable to determine whether the input value falls within a region where the non-linear model has an integrity that is less than a first threshold.

3. The non-transitory memory medium of claim 2, wherein the program instructions comprise a domain switching device configured to switch operation of a predictive system to the non-linear model when the integrity is above the first threshold and to switch operation of the predictive system to the linearized first principles model when the integrity is below the first threshold.

4. The non-transitory memory medium of claim 3, wherein the domain analyzer is configured to determine whether the input value falls within a region where the non-linear model has an integrity that is less than a second threshold, wherein the second threshold is lower than the first threshold.

5. The non-transitory memory medium of claim 4, wherein the domain switching device is configured to switch operation of the predictive system to the non-linear model when the integrity is above the first threshold, to switch operation of the predictive system to a first principles model when the integrity is above the second threshold and below the first threshold, and to switch operation of the predictive system to the linearized first principles model when the integrity is below the second threshold.

6. The non-transitory memory medium of claim 1, wherein the non-linear model comprises a steady-state model.

7. The non-transitory memory medium of claim 1, wherein the non-linear model comprises a neural network or a support vector machine.

8. The non-transitory memory medium of claim 1, wherein the linearized first principles model comprises a local linearization of a first principles model local to the input value.

9. The non-transitory memory medium of claim 1, wherein the linearized first principles model comprises a global linearization of a first principles model.

10. A method, comprising:

receiving an input value from a plant or process;

determining, via program instructions executed by a processor, an integrity of a non-linear model comprising an empirical representation of the plant or process;

using the non-linear model to provide a first output value when the integrity is above a first threshold; and

using a linearized first principles model comprising an analytic representation of the plant or process to provide a second output value when the integrity is below the first threshold.

11. The method of claim 10, comprising:

using the non-linear model when the integrity is above the first threshold and a second threshold which is lower than the first threshold;

using a first principles model when the integrity is above the second threshold; and

using the linearized first principles model when the integrity is below the second threshold.

12. The method of claim 10, wherein the integrity of the non-linear model corresponds to a local input space of the input value.

13. The method of claim 10, wherein the linearized first principles model comprises a local linearization of a first principles model local to the input value.

14. The method of claim 10, wherein the linearized first principles model comprises a global linearization of a first principles model.

15. The method of claim 14, wherein the global linearization is based on a range of previous input values.

16. A non-transitory memory medium comprising program instructions executable by a processor to:

receive an input value from a plant or process;

determine an integrity of a non-linear model comprising an empirical representation of the plant or process;

use the non-linear model to provide a first output value when the integrity is above a first threshold; and

use a linearized first principles model comprising an analytic representation of the plant or process to provide a second output value when the integrity is below the first threshold.

17. The non-transitory memory medium of claim 16, wherein the program instructions are executable to:

use the non-linear model when the integrity is above the first threshold and a second threshold which is lower than the first threshold;

use a first principles model when the integrity is above the second threshold; and

use the linearized first principles model when the integrity is below the second threshold.

18. The non-transitory memory medium of claim 16, wherein the integrity of the non-linear model corresponds to a local input space of the input value.

19. The non-transitory memory medium of claim 16, wherein the linearized first principles model comprises a local linearization of a first principles model local to the input value.

20. The non-transitory memory medium of claim 16, wherein the linearized first principles model comprises a global linearization of a first principles model.